Geschriebene Artikel über Big Data Analytics

Benjamin Aunkofer - Podcast - KI in der Wirtschaftsprüfung

Podcast – KI in der Wirtschaftsprüfung

Die Verwendung von Künstlicher Intelligenz (KI) in der Wirtschaftsprüfung, wie Sie es beschreiben, klingt in der Tat revolutionär. Die Integration von KI in diesem Bereich könnte enorme Vorteile mit sich bringen, insbesondere in Bezug auf Effizienzsteigerung und Genauigkeit.

Benjamin Aunkofer - KI in der WirtschaftsprüfungDie verschiedenen von Ihnen genannten Lernmethoden wie (Un-)Supervised Learning, Reinforcement Learning und Federated Learning bieten unterschiedliche Ansätze, um KI-Systeme für spezifische Anforderungen der Wirtschaftsprüfung zu trainieren. Diese Methoden ermöglichen es, aus großen Datenmengen Muster zu erkennen, Vorhersagen zu treffen und Entscheidungen zu optimieren.

Der Artificial Auditor von AUDAVIS, der auf einer Kombination von verschiedenen KI-Verfahren basiert, könnte beispielsweise in der Lage sein, 100% der Buchungsdaten zu analysieren, was mit herkömmlichen Methoden praktisch unmöglich wäre. Dies würde nicht nur die Genauigkeit der Prüfung verbessern, sondern auch Betrug und Fehler effektiver aufdecken.

Der Punkt, den Sie über den Podcast Unf*ck Your Datavon Dr. Christian Krug und die Aussagen von Benjamin Aunkofer ansprechen, ist ebenfalls interessant. Es scheint, dass die Diskussion darüber, wie Datenautomatisierung und KI die Wirtschaftsprüfung effizienter gestalten können, bereits im Gange ist und dabei hilft, das Bewusstsein für diese Technologien zu schärfen und ihre Akzeptanz in der Branche zu fördern.

Es wird dabei im Podcast betont, dass die Rolle des menschlichen Prüfers durch KI nicht ersetzt, sondern ergänzt wird. KI kann nämlich dabei helfen, Routineaufgaben zu automatisieren und komplexe Datenanalysen durchzuführen, während menschliche Experten weiterhin für ihre Fachkenntnisse, ihr Urteilsvermögen und ihre Fähigkeit, den Kontext zu verstehen, unverzichtbar bleiben.

Insgesamt spricht Benjamin Aunkofer darüber, dass die Integration von KI in die Wirtschaftsprüfung bzw. konkret in der Jahresabschlussprüfung ein aufregender Schritt in Richtung einer effizienteren und effektiveren Zukunft sei, der sowohl Unternehmen als auch die gesamte Volkswirtschaft positiv beeinflussen wird.

Benjamin Aunkofer - Podcast - KI in der Wirtschaftsprüfung

Benjamin Aunkofer – Podcast – KI in der Wirtschaftsprüfung

Kappa vs Lambda Architecture

Big Data Analytics stands apart from conventional data processing in its fundamental nature. In the realm of Big Data, there are two prominent architectural concepts that perplex companies embarking on the construction or restructuring of their Big Data platform: Lambda architecture or Kappa architecture.


 

Read more here: Lambda vs Kappa Architecture for Data Cloud Platforms

 

Object-centric Data Modelling for Process Mining and BI

Object-centric Process Mining on Data Mesh Architectures

In addition to Business Intelligence (BI), Process Mining is no longer a new phenomenon, but almost all larger companies are conducting this data-driven process analysis in their organization.

The database for Process Mining is also establishing itself as an important hub for Data Science and AI applications, as process traces are very granular and informative about what is really going on in the business processes.

The trend towards powerful in-house cloud platforms for data and analysis ensures that large volumes of data can increasingly be stored and used flexibly. This aspect can be applied well to Process Mining, hand in hand with BI and AI.

New big data architectures and, above all, data sharing concepts such as Data Mesh are ideal for creating a common database for many data products and applications.

The Event Log Data Model for Process Mining

Process Mining as an analytical system can very well be imagined as an iceberg. The tip of the iceberg, which is visible above the surface of the water, is the actual visual process analysis. In essence, a graph analysis that displays the process flow as a flow chart. This is where the processes are filtered and analyzed.

The lower part of the iceberg is barely visible to the normal analyst on the tool interface, but is essential for implementation and success: this is the Event Log as the data basis for graph and data analysis in Process Mining. The creation of this data model requires the data connection to the source system (e.g. SAP ERP), the extraction of the data and, above all, the data modeling for the event log.

Simple Data Model for a Process Mining Event Log

Simple Data Model for a Process Mining Event Log.

As part of data engineering, the data traces that indicate process activities are brought into a log-like schema. A simple event log is therefore a simple table with the minimum requirement of a process number (case ID), a time stamp and an activity description.

Event Log in Process Mining

Example Event Log for Process Mining

An Event Log can be seen as one big data table containing all the process information. Splitting this big table into several data tables is due to the goal of increasing the efficiency of storing the data in a normalized database.

The following example SQL-query is inserting Event-Activities from a SAP ERP System into an existing event log database table (one big table). It shows that events are based on timestamps (CPUDT, CPUTM) and refer each to one of a list of possible activities (dependent on VGABE).

Attention: Please see this SQL as a pure example of event mining for a classic (single table) event log! It is based on a German SAP ERP configuration with customized processes.

An Event Log can also include many other columns (attributes) that describe the respective process activity in more detail or the higher-level process context.

Incidentally, Process Mining can also work with more than just one timestamp per activity. Even the small Process Mining tool Fluxicon Disco made it possible to handle two activities from the outset. For example, when creating an order in the ERP system, the opening and closing of an input screen could be recorded as a timestamp and the execution time of the micro-task analyzed. This concept is continued as so-called task mining.

Task Mining

Task Mining is a subtype of Process Mining and can utilize user interaction data, which includes keystrokes, mouse clicks or data input on a computer. It can also include user recordings and screenshots with different timestamp intervals.

As Task Mining provides a clearer insight into specific sub-processes, program managers and HR managers can also understand which parts of the process can be automated through tools such as RPA. So whenever you hear that Process Mining can prepare RPA definitions you can expect that Task Mining is the real deal.

Machine Learning for Process and Task Mining on Text and Video Data

Process Mining and Task Mining is already benefiting a lot from Text Recognition (Named-Entity Recognition, NER) by Natural Lamguage Processing (NLP) by identifying events of processes e.g. in text of tickets or e-mails. And even more Task Mining will benefit form Computer Vision since videos of manufacturing processes or traffic situations can be read out. Even MTM analysis can be done with Computer Vision which detects movement and actions in video material.

Object-Centric Process Mining

Object-centric Process Data Modeling is an advanced approach of dynamic data modelling for analyzing complex business processes, especially those involving multiple interconnected entities. Unlike classical process mining, which focuses on linear sequences of activities of a specific process chain, object-centric process mining delves into the intricacies of how different entities, such as orders, items, and invoices, interact with each other. This method is particularly effective in capturing the complexities and many-to-many relationships inherent in modern business processes.

Note from the author: The concept and name of object-centric process mining was introduced by Wil M.P. van der Aalst 2019 and as a product feature term by Celonis in 2022 and is used extensively in marketing. This concept is based on dynamic data modelling. I probably developed my first event log made of dynamic data models back in 2016 and used it for an industrial customer. At that time, I couldn’t use the Celonis tool for this because you could only model very dedicated event logs for Celonis and the tool couldn’t remap the attributes of the event log while on the other hand a tool like Fluxicon disco could easily handle all kinds of attributes in an event log and allowed switching the event perspective e.g. from sales order number to material number or production order number easily.

An object-centric data model is a big deal because it offers the opportunity for a holistic approach and as a database a single source of truth for Process Mining but also for other types of analytical applications.

Enhancement of the Data Model for Obect-Centricity

The Event Log is a data model that stores events and their related attributes. A classic Event Log has next to the Case ID, the timestamp and a activity description also process related attributes containing information e.g. about material, department, user, amounts, units, prices, currencies, volume, volume classes and much much more. This is something we can literally objectify!

The problem of this classic event log approach is that this information is transformed and joined to the Event Log specific to the process it is designed for.

An object-centric event log is a central data store for all kind of events mapped to all relevant objects to these events. For that reason our event log – that brings object into the center of gravity – we need a relational bridge table (Event_Object_Relation) into the focus. This tables creates the n to m relation between events (with their timestamps and other event-specific values) and all objects.

For fulfillment of relational database normalization the object table contains the object attributes only but relates their object attribut values from another table to these objects.

Advanced Event Log with dynamic Relations between Objects and Events

Advanced Event Log with dynamic Relations between Objects and Events

The above showed data model is already object-centric but still can become more dynamic in order to object attributes by object type (e.g. the type material will have different attributes then the type invoice or department). Furthermore the problem that not just events and their activities have timestamps but also objects can have specific timestamps (e.g. deadline or resignation dates).

Advanced Event Log with dynamic Relations between Objects and Events and dynamic bounded attributes and their values to Events - And the same for Objects.

Advanced Event Log with dynamic Relations between Objects and Events and dynamic bounded attributes and their values to Events – And the same for Objects.

A last step makes the event log data model more easy to analyze with BI tools: Adding a classical time dimension adding information about each timestamp (by date, not by time of day), e.g. weekdays or public holidays.

Advanced Event Log with dynamic Relations between Objects and Events and dynamic bounded attributes and their values to Events and Objects. The measured timestamps (and duration times in case of Task Mining) are enhanced with a time-dimension for BI applications.

Advanced Event Log with dynamic Relations between Objects and Events and dynamic bounded attributes and their values to Events and Objects. The measured timestamps (and duration times in case of Task Mining) are enhanced with a time-dimension for BI applications.

For analysis the way of Business Intelligence this normalized data model can already be used. On the other hand it is also possible to transform it into a fact-dimensional data model like the star schema (Kimball approach). Also Data Science related use cases will find granular data e.g. for training a regression model for predicting duration times by process.

Note from the author: Process Mining is often regarded as a separate discipline of analysis and this is a justified classification, as process mining is essentially a graph analysis based on the event log. Nevertheless, process mining can be considered a sub-discipline of business intelligence. It is therefore hardly surprising that some process mining tools are actually just a plugin for Power BI, Tableau or Qlik.

Storing the Object-Centrc Analytical Data Model on Data Mesh Architecture

Central data models, particularly when used in a Data Mesh in the Enterprise Cloud, are highly beneficial for Process Mining, Business Intelligence, Data Science, and AI Training. They offer consistency and standardization across data structures, improving data accuracy and integrity. This centralized approach streamlines data governance and management, enhancing efficiency. The scalability and flexibility provided by data mesh architectures on the cloud are very beneficial for handling large datasets useful for all analytical applications.

Note from the author: Process Mining data models are very similar to normalized data models for BI reporting according to Bill Inmon (as a counterpart to Ralph Kimball), but are much more granular. While classic BI is satisfied with the header and item data of orders, process mining also requires all changes to these orders. Process mining therefore exceeds this data requirement. Furthermore, process mining is complementary to data science, for example the prediction of process runtimes or failures. It is therefore all the more important that these efforts in this treasure trove of data are centrally available to the company.

Central single source of truth models also foster collaboration, providing a common data language for cross-functional teams and reducing redundancy, leading to cost savings. They enable quicker data processing and decision-making, support advanced analytics and AI with standardized data formats, and are adaptable to changing business needs.

DATANOMIQ Data Mesh Cloud Architecture - This image is animated! Click to enlarge!

DATANOMIQ Data Mesh Cloud Architecture – This image is animated! Click to enlarge!

 

Central data models in a cloud-based Data Mesh Architecture (e.g. on Microsoft Azure, AWS, Google Cloud Platform or SAP Dataverse) significantly improve data utilization and drive effective business outcomes. And that´s why you should host any object-centric data model not in a dedicated tool for analysis but centralized on a Data Lakehouse System.

About the Process Mining Tool for Object-Centric Process Mining

Celonis is the first tool that can handle object-centric dynamic process mining event logs natively in the event collection. However, it is not neccessary to have Celonis for using object-centric process mining if you have the dynamic data model on your own cloud distributed with the concept of a data mesh. Other tools for process mining such as Signavio, UiPath, and process.science or even the simple desktop tool Fluxicon Disco can be used as well. The important point is that the data mesh approach allows you to easily generate classic event logs for each analysis perspective using the dynamic object-centric data model which can be used for all tools of process visualization…

… and you can also use this central data model to generate data extracts for all other data applications (BI, Data Science, and AI training) as well!

Wie man Web Scraping für den Vertrieb nutzt

Vertrieb in Unternehmen ist wie der Motor, der eine Maschine antreibt. Nur wenn Produkte verkauft werden und neue Kunden sich für ein Unternehmen begeistern, kann der nötige Cashflow generiert werden, der Gebäude, Löhne und alle anderen Kosten rund um das Unternehmen tragen kann.

Wie man diesen Bereich eines Unternehmens mit Data Mining und Web Scraping aktiv unterstützen kann, zeige ich euch in diesem Artikel.

Kernthema im Vertrieb: Leadgenerierung

Jeder Verkauf beginnt mit einer Person, die an unserem Produkt interessiert ist und es kaufen möchte. Ein zentraler Punkt im Vertrieb sind deshalb die “Leads” – Kontaktadresse von Kunden, mit denen wir ins Gespräch kommen können, um ein Angebot zu machen und schließlich unsere Produkte zu verkaufen. Die Leads sind die Basis in jedem Vertriebsprozess, weil wir über diese Daten mit Menschen ins Gespräch kommen können und Beziehungen zu potentiellen Kunden aufbauen können. Je besser diese vorselektiert sind und auf unsere Zielgruppe angepasst sind, desto einfacher wird die Arbeit für unseren Vertrieb.

Leadgenerierung meint dabei das Sammeln von Daten zu Unternehmen oder Personen, die zu unserer Zielgruppe passen und mit möglichst hoher Wahrscheinlichkeit einen Bedarf an unserem Produkt haben. Um in einem Unternehmen einen konstanten Umsatz zu erwirtschaften und die Produktion das ganze Jahr über auszulasten, müssen regelmäßig Aufträge in das Unternehmen kommen. Damit der Vertrieb diese Aufträge an Land ziehen kann, müssen die Vertriebsmitarbeiter immer wieder neue Kundengespräche führen. Und damit diese Gespräche stattfinden können, muss ein Unternehmen auf zuverlässige und wiederholbare Weise immer wieder Leads generieren. Immer wieder neue, potenzielle Interessenten zu finden, ist dabei eine der herausforderndsten Aufgaben jeder Vertriebsleitung.

Leads generieren mit Web Scraping

Mit Web Scraping Leads zu generieren bedeutet Kontaktdaten aus dem Internet zu sammeln mit Hilfe einer Software. Vorwiegend werden dabei Webseiten und frei zugängliche Daten aus allen Ecken des Internets durchsucht mit einem Programm, welches anschließend die Daten in eine übersichtliche Datei, wie beispielsweise Excel, verpackt. Dadurch können diese Daten wiederum sehr einfach in die meisten gängigen CRM (Customer Relationship Management) Systeme hochgeladen werden, wo die Vertriebsteams diese direkt bearbeiten können. Mit dieser Methode lassen sich in kurzer Zeit auf die Zielgruppe spezialisierte Listen erstellen, die dem Unternehmen helfen, neue Kundenkontakte zu finden und zu erstellen.

Die Daten dabei können Namen von Personen oder Unternehmen sein, Adressen, Telefonnummern, E-Mail-Adressen, URLs und mehr. Unternehmen und Start-ups ersparen sich damit die mühsame Arbeit dutzende Webseiten und Datenbanken nach möglichen Kontaktadressen zu suchen. Web Scraper sind dabei auch um einiges effizienter als ein manueller Suchvorgang, weil die Programme oft mit komplexen Algorithmen arbeiten, die immer wieder optimiert werden, um bestmögliche Ergebnisse zu erreichen.

Die Vorteile von Web Scraping zur Leadgenerierung

Durch die Automatisierung eines sonst sehr zeitaufwendigen Prozesses werden die Ressourcen im Unternehmen besser eingesetzt. Vor allem Vertriebsmitarbeiter können sich dadurch besser ihrer eigentlichen Aufgabe widmen: Zeit mit Kunden verbringen.

Viele Mitarbeiter im Vertrieb sind auch spezialisiert auf den Umgang mit Menschen und sind möglicherweise etwas unbeholfen, wenn es darum geht, Daten zu sammeln und dabei Tage nur vor dem Bildschirm zu verbringen. Mit Web Scraping wird diese eintönige Tätigkeit aus dem Alltag dieser Mitarbeiter herausgenommen. Die Mitarbeiter können den Tätigkeiten auf die sie spezialisiert sind mehr Zeit widmen, und es müssen auch keine teuren Mitarbeiter mehr abgestellt werden für eine Tätigkeit, die ohnehin maschinell besser gelöst werden kann.

Durch die Analyse von unzähligen Daten beim Web Scraping lassen sich manchmal auch bereits Hypothesen über unsere Zielgruppe überprüfen. Dadurch lernen wir bereits vorab, wie unsere Kunden arbeiten, was für sie relevante Themen sind und wie wir sie am besten ansprechen können. Mit Hilfe dieser Daten können wir wiederum bessere Entscheidungen im Marketing und Vertrieb treffen, basierend auf dem echten Verhalten unserer Kunden anstatt nur auf Vermutungen.

Mit Hilfe der Kombination aus effizientem Ressourceneinsatz sowohl von personeller, zeitlicher als auch monetärer Perspektive und die gleichzeitige Auswertung von Daten über Kunden und deren Verhalten lassen sich langfristige Vorteile für ein Unternehmen erzeugen mit denen man der Konkurrenz einen Schritt voraus ist. Richtig umgesetzt lassen sich damit Geschäftsmöglichkeiten und Umsatzpotenziale lukrieren, noch bevor diese am Markt öffentlich bekannt werden.

Die Herausforderungen beim Web Scraping

Wenn diese Taktik so umwerfend funktioniert, warum macht es dann nicht jeder?

Natürlich gibt es auch beim Web Scraping einige Herausforderungen, die zu beachten sind.

Das offensichtlichste davon ist die Qualität der Daten. Auch das komplexeste Programm kann nur die Daten aus dem Internet filtern, die dort öffentlich zugänglich sind. Dies bedeutet aber auch, dass manches davon nicht mehr aktuell ist, anderes wird irrelevant sein und ein Teil davon als Leads für den Vertrieb gar nicht zu gebrauchen.

Dazu kommen Restriktionen beim Crawlen von Webseiten. Viele Seiten blockieren bewusst Crawler und sind sehr sensibel beim Umgang mit deren Daten, was erneut zu Problemen führen kann. In vielen Fällen müssen diese Seiten ausgeschlossen werden oder sind gar nicht für die Leadgenerierung zu gebrauchen. CAPTCHAs sind dabei nur eine der möglichen Hürden, die den Prozess entweder stark verlangsamen oder völlig stoppen können.

Doch auch selbst wenn Daten frei zugänglich zu finden sind, kommen diese oft mehr als ein Mal vor auf diversen Quellen im Netz. Dies sorgt in den Ergebnissen der Scraper oft für Duplikate. Dabei kann auch der Aufbau einer Webseite Schwierigkeiten bereiten, zumal diese unterschiedlich strukturiert und angeordnet sein können, wodurch eine einheitliche Programmierung für das Scraping schwer zu gestalten ist. Hinzu kommen noch technologische Barrieren, die im Netz verbaut sein können, wie die Nutzung von Javascript, dynamischer Content, oder andere Hindernisse auf den verschiedenen Webseiten.

Geeignete Webseiten oder Plattformen finden

Bevor man mit dem Scraping starten kann, muss man zuerst festlegen, welche Seiten oder Plattformen man überhaupt durchsuchen will. Hier sind einige der Faktoren, die man dabei beachten sollte:

Wo finde ich meine Zielgruppe?

Am besten beginnen wir unsere Suche dort, wo unsere Kunden ohnehin bereits sind, wo sie ihre Freizeit verbringen oder nach Informationen suchen. In B2B Märkten können wir alternativ immer die eigenen Webseiten unserer Kunden durchsuchen.

Wie relevant ist die Seite für mein Produkt?

Es ergibt keinen Sinn Seiten zu crawlen, die nichts mit unseren Produkten zu tun haben und bei denen die Nutzer auch nichts mit unserem Produkt anfangen können. Wer beispielsweise Haarpflegeprodukte verkauft, sollte kein Bauforum durchsuchen.

Wie aktuell ist die Webseite?

Wer Daten auf veralteten Webseiten sucht, wird auch nur veraltete Daten finden. Diese sind meistens kaum bis gar nicht brauchbar für den Vertrieb. Die angegebenen Seiten sollten daher möglichst aktuell sein und die Daten darauf regelmäßig aktualisiert werden.

Rechtliche Abklärung

Manche Seiten verbieten explizit das Benutzen jeglicher Daten zu kommerziellen Zwecken. Dies sollte genau analysiert werden, bevor man Daten von einer Seite extrahiert.

Verfügbarkeit und Qualität der Daten:

Manche Seiten machen es Crawlern bewusst schwer an Daten zu kommen, bei manchen bekommt man keinerlei Informationen mehr ohne Captcha Überprüfung, Opt-In Formular, etc. Auch ein Aufbau der Seite in komplexem HTML Code oder Ähnliches kann Scraping zu einer Herausforderung werden lassen, die einem viel Zeit kostet, anstatt sie zu gewinnen.

Beispiele für Web Scraping

Genug mit der Theorie, sehen wir uns nun ein paar konkrete Beispiele an. Im Idealfall hat man einen Programmierer im Unternehmen zur Verfügung, der gerade keine anderen Projekte verfolgen muss und genug Zeit hat, um einen eigenen Web Scraper zu bauen, zielgerichtet auf die Bedürfnisse des Unternehmens. Dieser kann genau auf die Produkte, rechtlichen Anforderungen und die optimalen Kunden für den Vertrieb programmiert werden. Realistisch gesehen, kommt dieses Szenario nur äußerst selten vor. Deshalb stellen wir euch hier einige vorgefertigte Lösungen vor. Die richtige Lösung wird sich bei jedem Unternehmen nach Produkten, Marktlage, Kundenverhalten etc. unterscheiden und muss individuell an jedes Unternehmen angepasst sein.

io

Am Beginn des Vertriebsprozesses brauchen wir eine große Anzahl an Leads. Import.io ist genau einer der Anbieter, die dabei helfen können, große Mengen an Daten aus dem Internet zu erzeugen. Wichtig dabei ist, dass unser restlicher Vertriebsprozess soweit fortgeschritten sein muss, dass wir genau unsere Zielgruppe kennen und wissen, wo und wie man diese Personen finden kann.

Das praktische an dieser Plattform ist, dass man absolut nichts coden oder programmieren muss. Übrigens ist Import.io ursprünglich nicht für Vertriebs- und Marketingzwecke entworfen worden, wird aber immer wieder von gewieften Sales Managern und Marketern als Geheimtipp genutzt. Die Technologie eignet sich hervorragend, um große Listen an Leads mit Web Scraping zu erzeugen.

Die Daten können als .csv Datei gesammelt und von dort optimal in das CRM System der Wahl integriert werden.

Scrape-it Marktplatz

Wer Kundendaten vorwiegend über öffentliche Seiten wie Yellow Pages, Booking.com oder Google Maps finden kann, hat hier ein breites Angebot an verschiedenen Scraper zur Auswahl. Alle davon erfordern keinerlei Programmierung und sind bereit zum Einsatz nach dem Download. Wer beispielsweise Architekten in Barcelona oder Restaurants in Paris als Leads nutzen kann, für den bieten diese Lösungen einen schnellen Zugang zu einer Menge an Daten.

Octoparse

Eine weitere Lösung, die ohne jede Programmierung und Vorkenntnis angewendet werden kann, um schnell große Mengen an Leads zu generieren. Dieses Programm hat eine besonders einfach zu bedienende Oberfläche und wurde direkt für die Leadgenerierung entwickelt.

80legs

Ebenfalls ein sehr nützliches Tool zum Web Scraping, mit dem man viele spezifische Einstellungen vornehmen kann. Zusätzlich bietet dieses Tool auch noch die Möglichkeit, die Daten sofort herunterzuladen. Es ist bestens geeignet um eine breite Basis an Leads zu generieren

Webharvy

Eine einfache Point-and-Click Software als Web Scraper, die einen URLs, E-Mail Adressen, Bilder und Texte von Webseiten sammeln kann. Auch dieses Tool lässt sich einfach ohne jede Programmierung intuitiv bedienen

Scraper

Eine Erweiterung für Google Chrome, die zwar nur begrenzte Daten sammeln kann, aber dennoch ein sehr hilfreiches Tool für die Onlinerecherche. Es ist geeignet für Beginner und Profis gleichermaßen, die Daten lassen sich bequem extrahieren und wie bei den anderen Programmen in eine .csv oder Ähnliche Datei verpacken.

com

Als open-source-basierter Cloud-Service für Webscraping handelt es sich hier um einen unabhängigen und hoch effektiven Web Scraper. Dadurch wird das Programm auch stetig upgedatet und verbessert. Die Software verwendet einen intelligenten Proxy Rotator, der darauf spezialisiert ist, die gängigen Maßnahmen gegen Bots auf Webseiten zu umgehen und trotz vorhandener Gegenmaßnahmen verlässlich die Daten zu sammeln. Sollte man Probleme mit dem Tool haben, steht ein zuverlässiges Support Team zur Verfügung, um bei Fragen zu helfen.

Fazit

Wer im Vertrieb arbeitet oder beispielsweise als Unternehmer auf einen starken, zuverlässigen Vertriebsprozess angewiesen ist, für den lässt sich das Thema Data Mining und Web Scraping heute nicht mehr länger ignorieren. Gerade in den noch “konservativen” Branchen, in denen nicht viel mit diesen digitalen Tools gearbeitet wird, lässt sich durch gekonnten Einsatz von Technologie ein Wettbewerbsvorteil erzeugen. Die Unternehmen, die gewillt sind sich auf diese neue Technologie einzulassen, können damit schneller und gezielter neue Kunden ansprechen und deren Produkte um ein Vielfaches effektiver vermarkten als jene Konkurrenten, die diese Tools nicht einsetzen.

Why using Infrastructure as Code for developing Cloud-based Data Warehouse Systems?

In the contemporary age of Big Data, Data Warehouse Systems and Data Science Analytics Infrastructures have become an essential component for organizations to store, analyze, and make data-driven decisions. With the evolution of cloud computing, many organizations are now migrating their Data Warehouse Systems to the cloud for better scalability, flexibility, and cost-efficiency. Infrastructure as Code (IaC) can be a game-changer in this scenario. By automating the provisioning and management of cloud resources through code, IaC brings a host of advantages to the development and maintenance of Data Warehouse Systems in the cloud.

So why using IaC for Cloud Data Infrastructures?

Of course you – as a human user – can always login into the admin portal of any cloud provider and manually get your resources like SQL databases, ETL tools, Virtual Networks and tools like Synapse, snowflake, BigQuery or Databrikcs in place by clicking on the right buttons….. But here is why you should better follow the idea of having your code explaining which resources are in what order in place in your cloud:

Version Control for your Cloud Infrastructure

One of the primary advantages of using IaC is version control for your Data Warehouse – or Data Lakehouse – Architecture. Whether you’re using Redshift, Snowflake, or any other cloud-based data warehouse solutions, you can codify your architecture settings, allowing you to track changes over time. This ensures a reliable and consistent development environment and makes it easier to identify issues, rollback updates, or replicate the architecture for other projects.

Scalability Tailored for Data Needs

Data Warehouse Systems often require to scale quickly to handle larger datasets or more queries. Traditional manual scaling methods are cumbersome and slow. IaC allows for efficient auto-scaling based on real-time needs. You can write scripts to automatically provision or de-provision resources depending on your data workloads, making your data warehouse highly adaptive to your organization’s changing requirements.

Cost-Efficiency in Resource Allocation

Cloud resources are priced based on usage, so efficient allocation is crucial for managing costs. IaC enables precise control over cloud resources, allowing you to turn them off when not in use or allocate more resources during peak times. For Data Warehouse Systems that often require powerful (and expensive) computing resources, this level of control can translate into significant cost savings.

Streamlined Collaboration Among Teams

Data Warehouse Systems in the cloud often involve cross-functional teams — data engineers, data scientists, and system administrators. IaC allows these teams to collaborate more effectively. Everyone works with the same infrastructure configurations, reducing discrepancies between development, staging, and production environments. This ensures that the data models and queries developed by data professionals are consistent with the underlying infrastructure.

Enhanced Security and Compliance

Data Warehouses often store sensitive information, making security a paramount concern. IaC allows security configurations to be codified and automated, ensuring that every new resource or service deployed complies with organizational and regulatory guidelines. This proactive security approach is particularly beneficial for industries that have to adhere to strict compliance rules like HIPAA or GDPR.

Reliable Environment for Data Operations

Manual configurations are prone to human error, which can compromise the reliability of a Data Warehouse System. IaC mitigates this risk by automating repetitive tasks, ensuring that the infrastructure is consistently provisioned. This brings reliability to data ETL (Extract, Transform, Load) processes, query performances, and other critical data operations.

Documentation and Disaster Recovery Made Easy

Data is the lifeblood of any organization, and losing it can be catastrophic. IaC allows for swift disaster recovery by codifying the entire infrastructure. If a disaster occurs, the infrastructure can be quickly recreated, reducing downtime and data loss.

Most common IaC solutions

The most common tools for creating Cloud Infrastructure as Code are probably Terraform and Pulumi. However, IaC solutions can be very different in their concepts. For example: While Terraform is a pure declarative configuration language that just describes how the infrastructure will look like (execution then by the Terraform-supporting Cloud Provider), Pulumi on the other hand will execute the deployment by a programming language iteratively deploying the wished cloud resources (e.g. using for loops in Python). While executing Pulumi in any supported programming language like Python or C#, Pulumi generates declarative Infrastructure build plans for the Cloud. Any IaC solution is declaring how the infrastrcture looks like.

Terraform

Terraform is one of the most widely used Infrastructure as Code (IaC) tools, developed by HashiCorp. It enables users to define and provision a data center infrastructure using a declarative configuration language known as HashiCorp Configuration Language (HCL).

The following Terraform script will create an Azure Resource Group, a SQL Server, and a SQL Database. It will also output the fully qualified domain name (FQDN) of the SQL Server, which you can use to connect to the database:

The HCL code needs to be placed into the Terrafirm main.tf file. Of course, Terraform and the Azure CLI needs to be installed before.

Pulumi

Pulumi is a modern Infrastructure as Code (IaC) tool that sets itself apart by allowing infrastructure to be defined using general-purpose programming languages like Python, TypeScript, Go, and C#.

Example of a Pulumi Python script creating a SQL Database on Microsoft Azure Cloud:

Running the script will need the installation of Python, Pulumi and the Azure CLI.

Cloud Provider specific IaC Solutions

Cloud providers might come up with their own IaC solutions, here are the probably most common ones:

Microsoft Azure Bicep is an open-source domain-specific language (DSL) developed by Microsoft, aimed at simplifying the process of deploying Azure resources. It serves as a declarative alternative to JSON for writing Azure Resource Manager (ARM) templates. Bicep compiles down to ARM templates, offering a more concise syntax and easier tooling while leveraging the proven, underlying ARM deployment engine.

AWS CloudFormation is a service offered by Amazon Web Services (AWS) that allows you to define cloud infrastructure in JSON or YAML templates.

Google Cloud Deployment Manager is quite similar to AWS CloudFormation but tailored for Google Cloud Platform (GCP), it allows you to define and deploy resources using YAML or Python templates.

IaC Tools for Server Configuration

There are many other IaC solutions and some of them are more focused on configuration of servers. In common they offer software provisioning as well and a lot detailing in regards to micro-configuration of single applications running on the server.

The most common IaC software for Server Configuration might be Ansible, a YAML-based configuration management tool that uses an agentless architecture. It’s easy to set up and widely used for automating tasks like software provisioning and configuration management. Puppet, Chef and SaltStack are further alternatives and master-agent architecture-based.

Other types of IaC Solutions

IaC solutions with a more narrow focus are e.g. Vagrant as a primarily used IaC tool for setting up virtual development environments, especially for the automation of VM (Virtual Machine) provisioning. The widely used Docker Compose is a tool for defining and running multi-container Docker applications, which can be defined using YAML files.

Furthermore we have tools that are working closely together with IaC tooling, e.g. Prometheus as an open-source monitoring toolkit often used in conjunction with other IaC tools for monitoring deployed resources.

Conclusion

Infrastructure as Code significantly enhances the development and maintenance of Cloud-based Data Infrastructures. From versioning your warehouse architecture and scaling resources according to real-time data needs, to facilitating team collaboration and ensuring security compliance, IaC serves as a foundational technology that brings agility, reliability, and cost-efficiency. As organizations continue to realize the importance of data-driven decision-making, leveraging IaC for cloud-based Data Warehouse Systems will likely become a best practice in data engineering and infrastructure management.

DATANOMIQ Cloud Architecture for Data Mesh - Process Mining, BI and Data Science Applications

Data Mesh Architecture on Cloud for BI, Data Science and Process Mining

Companies use Business Intelligence (BI), Data Science, and Process Mining to leverage data for better decision-making, improve operational efficiency, and gain a competitive edge. BI provides real-time data analysis and performance monitoring, while Data Science enables a deep dive into dependencies in data with data mining and automates decision making with predictive analytics and personalized customer experiences. Process Mining offers process transparency, compliance insights, and process optimization. The integration of these technologies helps companies harness data for growth and efficiency.

Applications of BI, Data Science and Process Mining grow together

More and more all these disciplines are growing together as they need to be combined in order to get the best insights. So while Process Mining can be seen as a subpart of BI while both are using Machine Learning for better analytical results. Furthermore all theses analytical methods need more or less the same data sources and even the same datasets again and again.

Bring separate(d) applications together with Data Mesh

While all these analytical concepts grow together, they are often still seen as separated applications. There often remains the question of responsibility in a big organization. If this responsibility is decided as not being a central one, Data Mesh could be a solution.

Data Mesh is an architectural approach for managing data within organizations. It advocates decentralizing data ownership to domain-oriented teams. Each team becomes responsible for its Data Products, and a self-serve data infrastructure is established. This enables scalability, agility, and improved data quality while promoting data democratization.

In the context of a Data Mesh, a Data Product refers to a valuable dataset or data service that is managed and owned by a specific domain-oriented team within an organization. It is one of the key concepts in the Data Mesh architecture, where data ownership and responsibility are distributed across domain teams rather than centralized in a single data team.

A Data Product can take various forms, depending on the domain’s requirements and the data it manages. It could be a curated dataset, a machine learning model, an API that exposes data, a real-time data stream, a data visualization dashboard, or any other data-related asset that provides value to the organization.

However, successful implementation requires addressing cultural, governance, and technological aspects. One of this aspect is the cloud architecture for the realization of Data Mesh.

Example of a Data Mesh on Microsoft Azure Cloud using Databricks

The following image shows an example of a Data Mesh created and managed by DATANOMIQ for an organization which uses and re-uses datasets from various data sources (ERP, CRM, DMS, IoT,..) in order to provide the data as well as suitable data models as data products to applications of Data Science, Process Mining (Celonis, UiPath, Signavio & more) and Business Intelligence (Tableau, Power BI, Qlik & more).

Data Mesh on Azure Cloud with Databricks and Delta Lake for Applications of Business Intelligence, Data Science and Process Mining.

Data Mesh on Azure Cloud with Databricks and Delta Lake for Applications of Business Intelligence, Data Science and Process Mining.

Microsoft Azure Cloud is favored by many companies, especially for European industrial companies, due to its scalability, flexibility, and industry-specific solutions. It offers robust IoT and edge computing capabilities, advanced data analytics, and AI services. Azure’s strong focus on security, compliance, and global presence, along with hybrid cloud capabilities and cost management tools, make it an ideal choice for industrial firms seeking to modernize, innovate, and improve efficiency. However, this concept on the Azure Cloud is just an example and can easily be implemented on the Google Cloud (GCP), Amazon Cloud (AWS) and now even on the SAP Cloud (Datasphere) using Databricks.

Databricks is an ideal tool for realizing a Data Mesh due to its unified data platform, scalability, and performance. It enables data collaboration and sharing, supports Delta Lake for data quality, and ensures robust data governance and security. With real-time analytics, machine learning integration, and data visualization capabilities, Databricks facilitates the implementation of a decentralized, domain-oriented data architecture we need for Data Mesh.

Furthermore there are also alternate architectures without Databricks but more cloud-specific resources possible, for Microsoft Azure e.g. using Azure Synapse instead. See this as an example which has many possible alternatives.

Summary – What value can you expect?

With the concept of Data Mesh you will be able to access all your organizational internal and external data sources once and provides the data as several data models for all your analytical applications. The data models are seen as data products with defined value, costs and ownership. Each applications has its own data model. While Data Science Applications have more raw data, BI applications get their well prepared star schema galaxy models, and Process Mining apps get normalized event logs. Using data sharing (in Databricks: Delta Sharing) data products or single datasets can be shared through applications and owners.

Monitoring of Jobskills with Data Engineering & AI

On own account, we from DATANOMIQ have created a web application that monitors data about job postings related to Data & AI from multiple sources (Indeed.com, Google Jobs, Stepstone.de and more).

The data is obtained from the Internet via APIs and web scraping, and the job titles and the skills listed in them are identified and extracted from them using Natural Language Processing (NLP) or more specific from Named-Entity Recognition (NER).

The skill clusters are formed via the discipline of Topic Modelling, a method from unsupervised machine learning, which show the differences in the distribution of requirements between them.

The whole web app is hosted and deployed on the Microsoft Azure Cloud via CI/CD and Infrastructure as Code (IaC).

The presentation is currently limited to the current situation on the labor market. However, we collect these over time and will make trends secure, for example how the demand for Python, SQL or specific tools such as dbt or Power BI changes.

Why we did it? It is a nice show-case many people are interested in. Over the time, it will provides you the answer on your questions related to which tool to learn! For DATANOMIQ this is a show-case of the coming Data as a Service (DaaS) Business.

Lambda Architecture vs Kappa Architecture for Big Data Cloud Platforms? Let us discuss which architecture suits best for what use cases.

Big Data – Lambda or Kappa Architecture?

Big Data Analytics stands apart from conventional data processing in its fundamental nature. In the realm of Big Data, there are two prominent architectural concepts that perplex companies embarking on the construction or restructuring of their Big Data platform: Lambda architecture or Kappa architecture. Thus, it is crucial for such companies to contemplate and decide which architectural approach best aligns with their goals.

Lambda – Architecture

Introduced in 2011 during the peak of Big Data’s prominence, the Lambda architecture remains a significant presence in the field. Despite being the older of the two architectures, it offers a more comprehensive approach by incorporating three layers: the batch layer, the speed layer (also known as the stream layer), and the serving layer.

The Batch Layer is responsible for processing the entire dataset, ensuring the generation of the most accurate results. However, this comes at the cost of higher latency due to the batch loading of data. On the flip side, the batch layer can handle complex calculations without time constraints. It stores incoming raw data and filters it for subsequent applications.

Batch runs are suitable for non-time-sensitive data that require regular updates, such as daily or weekly incremental loads. Additionally, batch runs are necessary for complete data migration or overwriting (Full Load) scenarios.

The Speed Layer operates with low latency, producing almost real-time results. It calculates real-time views that complement the batch views. The speed layer receives incoming data and provides incremental updates to the batch layer results. By implementing incremental deduction logic, the speed layer significantly reduces computational costs.

Here is a simplified depiction of the Lambda architecture, showcasing the multi-store concept and the serving layer. In this representation, there is a separate store for events within the speed layer and another store for data loaded during batch processing. The serving layer acts as a mediator, enabling subsequent applications to access the data. It is important to note that in the Lambda architecture, the serving layer can be omitted, allowing batch processing and event streaming to remain separate entities.

Here is a simplified depiction of the Lambda architecture, showcasing the multi-store concept and the serving layer. In this representation, there is a separate store for events within the speed layer and another store for data loaded during batch processing. The serving layer acts as a mediator, enabling subsequent applications to access the data. It is important to note that in the Lambda architecture, the serving layer can be omitted, allowing batch processing and event streaming to remain separate entities.

The batch views within the Lambda architecture allow for the application of more complex or resource-intensive rules, resulting in superior data quality and reduced bias over time. On the other hand, the real-time views provide immediate access to the most current data.

The Serving Layer serves as a conduit for various data queries originating from both the batch and speed layers. It receives batch views from the batch layer and near-real-time views from the speed layer, utilizing this data to facilitate standard reporting and ad hoc analytics.

The Lambda architecture effectively balances speed, reliability, and scalability. However, it is worth mentioning that while the batch layer and real-time stream handle different scenarios, their underlying processing logic often shares similarities. As a result, the development and maintenance efforts for both layers should not be underestimated.

Kappa – Architecture

Jay Kreps introduced the Kappa architecture in 2014 as an alternative to the Lambda architecture. It addresses the redundancy present in the Lambda architecture by completely removing the batch component. By eliminating the parallel operation of two pipelines, the Kappa architecture simplifies the overall architectural complexity.

In the Kappa architecture, only the speed layer, represented by an event-based streaming pipeline, remains. The fundamental concept is to handle real-time data processing and continuous data reprocessing using a single stream processing engine. This approach allows for the avoidance of a multi-layer lambda architecture while ensuring the quality of data processing is maintained.

Illustrated simplified Kappa Architecture. This architectural concept relies on event streaming as the core element of data delivery.

Illustrated simplified Kappa Architecture. This architectural concept relies on event streaming as the core element of data delivery.

In practical implementation, the Kappa architecture is commonly deployed using Apache Kafka or Kafka-based tools. Applications can directly read from and write to Kafka or an alternative message queue tool. For existing event sources, listeners are utilized to stream writes directly from database logs or similar data stores. This approach eliminates the need for inbound batch processing and reduces resource requirements.

By treating every data point as a streaming event, the Kappa architecture enables the ability to near-realtime analytics and observe the state of all data in the organization at any given point. Queries can be performed at a single location, eliminating the need to compare batch and velocity views.

However, there are challenges associated with this architecture. Data processing must be done as a data stream, leading to difficulties such as managing duplicate events, cross-referencing events, and maintaining correct operation order. While batch processing can handle retrospective consolidation of multiple data sets, these challenges persist in the Kappa architecture. As a result, implementing architectures based on the Kappa concept can be more complex compared to those based on the Lambda concept, even though the latter may appear clearer in architectural sketches.

The Kappa architecture is particularly suitable when event streaming or real-time processing use cases are predominant. It offers the advantage of having a single ETL platform to develop and maintain. It is well-suited for developing data systems that emphasize online learning and do not require a separate batch layer. The sequence of events and queries is not predefined but generated in later steps based on business logic, prioritizing speed.

Use cases – When to use which architecture?

It is important to note that Kappa architecture does not serve as a direct substitute for Lambda architecture, as there are certain use cases supported by Lambda that cannot be seamlessly migrated. The Lambda architecture is better suited for implementing complex data processes and ensuring consistently complete data provisioning compared to the pure event processing approach of Kappa. As a result, many Data Lakehouse systems are built upon the foundations of the Lambda architecture.

Requirements that clearly speak for Lambda

  • If data is to be processed ad-hoc on quasi unchanging, quality-assured databases, or if the focus of the database is on data quality and the avoidance of inconsistencies.
  • When fast responses are required, but the system must be able to handle different update cycles.

Requirements that clearly speak in favor of Kappa:

  • When the algorithms applied to the real-time data and the historical data are identical.
  • If the analytics system is online learning capable and therefore does not require a batch layer.
  • The order of events and queries does not matter, but the stream processing platforms can exchange data with the database instantly at any time.

If your requirements prioritize a highly reliable Data Lakehouse update process and efficient machine learning model training for accurate event predictions, the Lambda architecture is the recommended choice. By leveraging both the batch layer and the speed layer, the Lambda architecture ensures minimal errors and optimized processing speed.

Alternatively, if you seek a streamlined Big Data architecture that excels in handling distinct and continuously emerging events (e.g., fueling data for numerous mobile applications), the Kappa architecture is the ideal solution for data platforms with the main purpose of real-time data processing. Its focus on unique, ongoing events allows for effective and responsive data processing.

How to reduce costs for Process Mining

Process mining has emerged as a powerful Business Process Intelligence discipline (BPI) for analyzing and improving business processes. It involves extracting data from source systems to gain insights into process behavior and uncover opportunities for optimization. While there are many approaches to create value with process mining, organizations often face challenges when it comes to the cost of implementing the necessary solution. In this article, we will highlight the key elements when it comes to process mining architectures as well as the most common mistakes, to help organizations leverage the power of process mining while maintain cost control.

Process Mining - Elements of Process Mining and their cost aspects

Process Mining – Elements of Process Mining and their cost aspects

Data Extraction for process mining

Most process mining projects underestimate the complexity of data extraction. Even for well-known sources like SAP-ERP’s, the extraction often consumes 50% of the first pilot’s resources. As a result, the extraction pipelines are often built with the credo of “asap” and this is where the cost-drama begins. Process Mining demands Big Data in 99% of the cases, releasing bad developed extraction jobs will end in big cost chunks down the value stream. Frequently organizations perform full loads of big SAP tables, causing source system performance impact, increasing maintenance, and moving hundred GB’s of data on daily basis without any new value. Other organizations fall for the connectors, provided by some process mining platform tools, promising time-to-value being the best. Against all odds the data is getting extracted then into costly third-party platforms where they can be only consumed by the platforms process mining tool itself. On top of that, these organizations often perform more than one Business Process Intelligence discipline, resulting in extracting the exact same data multiple times.

Process Mining - Data Extraction

Process Mining – Data Extraction

The data extraction for process mining should be well planed and match the data strategy of the organization. By considering lightweighted data preprocessing techniques organizations can save both time and money. When accepting the investment character of big data extractions, the investment should be done properly in the beginning and therefore cost beneficial in the long term.

Cloud-Based infrastructure with process mining?

Depending on the data strategy of one organization, one cost-effective approach to process mining could be to leverage cloud computing resources. Cloud platforms, such as Amazon Web Services (AWS), Microsoft Azure, or Google Cloud Platform (GCP), provide scalable and flexible infrastructure options. By using cloud services, organizations can avoid the upfront investment in hardware and maintenance costs associated with on-premises infrastructure. They can pay for resources on a pay-as-you-go basis, scaling up or down as needed, which can significantly reduce costs. When dealing with big data in the cloud, meeting the performance requirements while keeping cost control can be a balancing act, that requires a high skillset in cloud technologies. Depending the organization situation and data strategy, on premises or hybrid approaches should be also considered. But costs won’t decrease only migrating from on-premises to cloud and vice versa. What makes the difference is a smart ETL design capturing the nature of process mining data.

Process Mining Cloud Architecture on "pay as you go" base.

Process Mining Cloud Architecture on “pay as you go” base.

Storage for process mining data

Storing data is a crucial aspect of process mining, as in most cases big data is involved. Instead of investing in expensive data storage solutions, which some process mining solutions offer, organizations can opt for cost-effective alternatives. Cloud storage services like Amazon S3, Azure Blob Storage, or Google Cloud Storage provide highly scalable and durable storage options at a fraction of the cost of process mining storage systems. By utilizing these services, organizations can store large volumes of event data without incurring substantial expenses. Moreover, when big data engineering technics, consider profound process mining logics the storage cost cut down can be tremendous.

Process Mining - Infrastructure Cost Curve - On-Premise vs Cloud

Process Mining – Infrastructure Cost Curve: On-Premise vs Cloud

Process Mining Tools

While some commercial process mining tools can be expensive, there are several powerful more economical alternatives available. Tools like Process Science, ProM, and Disco provide comprehensive process mining capabilities without the hefty price tag. These tools offer functionalities such as event log import, process discovery, conformance checking, and performance analysis. Organizations often mismanage the fact, that there can and should be more then one process mining tool available. As expensive solutions like Celonis have their benefits, not all use cases make up for the price of these tools. As a result, these low ROI-use cases will eat up the margin, or (and that’s even more critical) little promising use cases won’t be investigated on and therefore high hanging fruits never discovered. Leveraging process mining tools can significantly reduce costs while still enabling organizations to achieve valuable process insights.

Process Mining Tool Landscape

Process Mining Tool Landscape (examples shown)

Collaboration

Another cost-saving aspect is to encourage collaboration within the organization itself. Most process mining initiatives require the input from process experts and often involve multiple stakeholders across different departments. By establishing cross-functional teams and supporting collaboration, organizations can share resources and distribute the cost burden. This approach allows for the pooling of expertise, reduces duplication of efforts, and facilitates knowledge exchange, all while keeping costs low.

Process Mining Team Structure

Process Mining Team Structure

Conclusion

Process mining offers tremendous potential for organizations seeking to optimize their business processes. While many organizations start process mining projects euphorically, the costs set an abrupt end to the party. Implementing a low-cost and collaborative architecture can help to create a sustainable value for the organization. By leveraging cloud-based infrastructure, cost-effective storage solutions, big data engineering techniques, process mining tools, well developed data extractions, lightweight data preprocessing techniques, and fostering collaboration, organizations can embark on process mining initiatives without straining their budgets. With the right approach, organizations can unlock the power of process mining and drive operational excellence without losing cost control.

One might argue that implementing process mining is not only about the costs. In the end each organization must consider the long-term benefits and return on investment (ROI). But with a cost controlled and sustainable process mining approach, return on investment is likely higher and less risky.

This article provides general information for process mining cost reduction. Specific strategic decisions should always consider the unique requirements and restrictions of individual organizations.

Praxisbeispiel: Data Science im Banking

Wie sich mit Data Science die Profitabilität des Kreditkartengeschäfts einer Bank nachhaltig steigern lässt.

Die Fragestellung

Das Kreditkartengeschäft einer Bank brachte nicht die erhofften Gewinne ein, weshalb die Pricing-Strategie dieses Geschäftszweiges optimiert werden sollte. Hierbei sollte allerdings unbedingt vermieden werden, dass Kund:innen aufgrund erhöhter Zinskosten abspringen.

Die Frage, die sich hieraus ergab, lautete: Welche der Kund:innen würden höhere Zinskosten akzeptieren und welche würden bei einer Erhöhung der Zinsen ihre Kreditkarte kündigen? Um Kündigungen zu vermeiden, sollten deshalb zunächst eindeutige Kundensegmente identifiziert werden. Das Ziel war weiterhin, den weniger preissensitiven Kund:innen neue, lukrativere Kreditprodukte anzubieten, ohne gleichzeitig die Loyalität der Kund:innen zu gefährden.

Das Vorgehen

Um die verschiedenen Kundengruppen zu identifizieren, sollten die Kund:innen mithilfe einer Clustering-Analyse in klar voneinander abgegrenzte Segmente eingeteilt werden. Bei einer Clustering-Analyse handelt es sich um ein maschinelles Lernverfahren, bei dem Datenpunkte, in diesem Fall also Kund:innen zu Clustern oder Segmenten zusammengefasst werden. Bei einer solchen Analyse werden jene Kund:innen zu Clustern zusammengefasst, die sich in vielen Eigenschaften ähneln.

Der Vorteil an diesem Vorgehen ist, dass bei einer Clustering-Analyse eine Vielzahl an Eigenschaften gleichzeitig betrachtet werden kann. Außerdem können die erstellten Segmente dynamisch angepasst werden, wenn neue Daten in die Analyse eingehen. Zudem bietet ein Clustering-Modell die Möglichkeit, neue Kunden zu bewerten und einem bestehenden Cluster zuzuordnen, sofern die entsprechenden Daten über sie vorliegen.

Kunden segmentieren

Die Bank verfügte über vielfältige Daten den Kund:innen. Dazu gehörten persönliche Informationen wie Alter, Geschlecht, Bonität, Anzahl und Art der genutzten Kreditprodukte, Anzahl und Art der mit der Kreditkarte getätigten Transaktionen, aber auch Informationen zur bisherigen Beziehung zwischen Kund:in und Bank, wie beispielsweise Kontaktaufnahmen mit dem Kundenservice, Beschwerden, Net Promoter Score u.s.w.

Nachdem die Kund:innen anhand all dieser Eigenschaften einer Clustering-Analyse unterzogen worden waren, konnten verschiedene Gruppen identifiziert werden. Ein Vergleich dieser Gruppen untereinander ergab, dass es Kund:innen gibt, für die der Umfang der gebotenen Leistungen der Bank wichtiger war als der Zinssatz, also der Preis dieser Leistungen. Diese Kund:innen waren entsprechend als weniger preissensitiv bezüglich der Zinskosten einzuschätzen. In einem weiteren Segment wurden Kunden identifiziert, die eine Steigerung des Zinssatzes akzeptieren würden, weil sie die Kreditkarte sehr häufig verwendeten.

Durch die Bestimmung dieser wenig preissensitiven Cluster war die Bank zunächst in der Lage, diesen Kund:innen neue und lukrativere Kreditprodukte anzubieten.

Kundenloyalität messen

Darüber hinaus war der Bank wichtig, auch die Kundenzufriedenheit und -loyalität genauer zu beobachten, um Abwanderungen zu vermeiden.

Eine Möglichkeit, die Zufriedenheit und Loyalität von Kund:innen einzuschätzen besteht darin, ihre Sprache zu untersuchen, wenn sie im Austausch mit dem Kundenservice stehen. Aufgrund ihrer Wortwahl – ob mündlich oder schriftlich – können KI-Technologien den Emotionszustand der Kund:innen bestimmen. Positive Emotionen können hierbei allgemein als Zeichen der Loyalität und Zufriedenheit gedeutet werden, wohingegen negative Emotionen vor allem in Beschwerden oder schlechten Bewertungen vorkommen, die einen Kundenverlust zur Folge haben können. Das Ziel der Bank war es, Anfragen mit negativen Emotionen, also wahrscheinlich Beschwerden oder negative Bewertungen schneller zu erkennen, um diese priorisiert beantworten zu können und so einen drohenden Kundenverlust zu vermeiden.

In der Sprache ausgedrückte positive oder negative Emotionen können mit einer sogenannten Sentiment Analysis untersucht werden, wobei die Sprache der Kunden – ob schriftlich oder mündlich – mit KI-Technologien untersucht wird. Dafür kommt Natural Language Processing – eine Reihe der KI-Technologien zur Analyse menschlicher Sprache – zur Anwendung. Anhand dieser KI-Technologie wurden eingehende Nachrichten und Bewertungen einer automatischen Voruntersuchung unterzogen. Nachrichten und Bewertungen, die mit negativen Emotionen assoziiert wurden, wurden priorisiert bearbeitet. Durch die priorisierte Bearbeitung konnte eine 50%ige Reduktion der Antwortzeiten auf Beschwerden erzielt werden.

Die Ergebnisse

In diesem Projekt konnte die Bank durch verschiedene Ansätze das Kreditkartengeschäft optimieren sowie die Kundenreaktion auf die Zinssteigerung bzw. die Kundenloyalität in Echtzeit messen:

  • Mithilfe von Clustering konnten Kund:innen in Cluster eingeteilt werden, die sich in bestimmten, für die Bank wichtige Eigenschaften stark ähnelten. Durch die Bestimmung wenig preissensitiver Cluster war die Bank in der Lage, diesen Kund:innen neue und lukrativere Kreditprodukte anzubieten, was das Kreditkartengeschäft profitabler machte.
  • Mithilfe von Natural Language Processing konnten die Stimmungen der Kund:innen am Telefon mit dem Kundenservice oder per Email erfasst und ausgewertet werden. Negative Nachrichten wurden demzufolge priorisiert bearbeitet, was sich wiederum positiv auf die Kundenzufriedenheit und -loyalität auswirkte.

Neugierig geworden?

Dies ist nur eins von vielen Beispielen, wie Sie mit Data Science im Banking zu Erkenntnissen gelangen, die Sie gewinnbringend bzw. kostensparend einsetzen können.

Qualifizieren Sie sich mit den Seminaren und Trainings der Haufe Akademie rund um das Thema Data Science weiter!

Sie wollen auf Augenhöhe mit Data Scientists kommunizieren und im richtigen Moment die richtigen Fragen stellen können?

Oder Sie wollen selbst tief in die Welt der Data Science eintauchen und programmieren können? Wir bieten Ihnen die Qualifizierungen, die für Sie passen!

Aktuelle Kursangebot des Data Science Blog Sponsors, die Haufe Akademie: