Data Talks: Handling Customer Data

March 11, 2020 - Zurich

We have decided to postpone this event based on recommendations from the canton of Zurich related to coronavirus. We are sorry about having to do this so last minute and hope that you will be able to come when we announce the new date - which we will do as soon as possible.

At this meetup we want to focus on customers: how to understand their preferences and protect them from fraudulent actions. This is a free event, open to everybody who is interested. Food and drinks will be provided.

Talk one: Automating Inferences out of Customer Data: an Example on Fraud Detection in Credit Cards, by Maarit Widmann & Mathilde Humeau (KNIME)

Customer data provide resources for automated processes that serve the final goal of improving business, security, customer satisfaction, and targeted services. Machine learning on the other hand offers a wide range of models to analyse such data. The model that best reaches the purpose could be a supervised model for classification, or an unsupervised model for anomaly detection, such as for example a neural autoencoder. A classification model is trained on historical, labeled data (if we have them), whereas the latter approach has the advantage of working on non-labeled data. In this talk Maarit Widmann and Mathilde Humeau explore this challenge and the relative options using a machine learning based example for credit card fraud detection.

Open data meets KNIME: Excel hell and RESTful heaven, by Christoffer Swanström (Quantum Analytics)

Open data is the idea that some data should be freely available to everyone to use. More and more data are made freely available in this spirit. In this presentation, two examples of how to get open data into KNIME will be shown. The first one involves reading a heavily formatted Excel file that requires considerable wrangling in order to transform the data into a usable structure. The second example shows the elegance of machine readable data that is easy to query and digest through XML or JSON.


Christoffer Swanstroem, Quantum Business Services: Christoffer worked for a number of years in the telecommunications and banking fields, and was Head of Customer Intelligence of a Swiss bank before joining Quantum in 2009. He studied telecommunications and computer science in Finland and France, and has more than a decade of experience in analytics, data mining and business intelligence.

Maarit Widmann, KNIME: Maarit is a data scientist at KNIME. She started 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.

Mathilde Humeau, KNIME: Mathilde is an Account Manager at KNIME. She holds a master’s degree in finance and has years of experience in client management. She is eager to discover the use cases behind data science and also makes sure that the customers remain happy.



6:30 PM
6:45 PM
Automating Inferences out of Customer Data: An Example of Fraud Detection in Credit Cards by Maarit Widmann & Mathilde Humeau (KNIME)
7:15 PM
Open data meets KNIME: Excel hell and RESTful heaven, by Christoffer Swanström (Quantum Analytics)
7:45 PM
Housewarming & networking over food & drinks