Join us in our Berlin office for the first 2020 Data Talks meetup! We'll focus on customers: how to understand their preferences and how to protect them from fraudulent actions.
This is a free event, open to everybody who is interested. Food and drinks will be provided.
Disclaimer: At KNIME, we love real data science and favor dry facts over buzz words. We have an open-source and free analytics platform but we also provide a complementary commercial solution. For this event, however, we keep our marketing team strictly limited to organizing the pizza and posting a tweet or two.
A quick heads up: we still have ongoing construction and no elevator in the building. Please be prepared to climb four floors on foot!
Talk 1: Customer Relationship Upgrade through Customer Journey Analytics by Peter Neckel (mayato)
Today's customers leave more and more data behind when completing purchase transactions. By analyzing these data with machine learning, the customer journey can be analyzed for marketing, sales, or other purposes. In theory. In practice it often looks different: scattered and incomplete customer data, business processes that have been frozen for years, and little flexibility from corporations to adopt new techniques. How do you upgrade customer relationships with machine learning? Peter will show us in a practical example.
Peter Neckel studied business administration and business informatics and, since 2001, has worked in management consulting for different industries (banks, insurance companies, energy suppliers and retailers) and companies (Hewlett-Packard and SAP). Peter is now Head of the Customer Analytics Division at mayato GmbH and author of over 50 publications, including the book "Customer Relationship Analytics" (dpunkt.verlag, 2015).
Talk 2: Tutorial on Credit Card Fraud Detection by Maarit Widmann (KNIME)
Fraud detection in credit card transactions is a very wide and complex field. Most techniques can be reduced depending whether fraudulent transactions are available in the collected data or not. If they are, classic machine learning techniques, that is all supervised machine learning algorithms for classification will do the work. Otherwise techniques from the outlier detection or the anomaly detection field, like autoencoder deep learning or isolation forest, can be used instead. Maarit will show those different techniques and demonstrate some applications that implement them.
Maarit Widmann is a data scientist at KNIME. She started out with quantitative sociology and holds her Bachelor degree in social sciences. The University of Konstanz made her drop the “social” part when she completed her Master of Science! She now communicates concepts behind data science in videos and blog articles.