Approaches to Fraud Detection: Autoencoder, Isolation Forest and More

This webinar is co-hosted with Data Science Dojo, a globally recognized e-learning platform for data science.

“Experts estimate federal government losses from potential fraud at nearly $150 billion” (source) and new data shows the federal trade commission received 2.8 million reports of fraud in 2021 from consumers (source). In this webinar, we will show how to fight fraud with KNIME, a free and low-code tool, that can perform fraud detection without a single line of code nor brittle if-then rules!

In the first part of this webinar, we will work with labelled data to perform classical machine-learning approaches to fraud detection such as the random forest. Then we will cover a deep learning technique, the autoencoder, to find fraudulent data points.

In the second part of the webinar, we will focus on data without labels of fraudulent activity using visualisations, classical statistics, and machine learning. You will learn how easy it is to generate multiple visualisations, perform statistical analysis, and use two machine learning algorithms – Isolation Forest and DBSCAN – all to detect fraudulent activity in the free, open-source KNIME Analytics Platform.

In this session you will learn:

• How to identify fraud using a variety of techniques including visualisations, statistics, and machine learning

• How to use machine learning and deep learning algorithms for fraud detection regardless of whether you have labelled data or not