Detecting Financial Fraud at Scale with Machine Learning & Databricks
On Demand Webinar
Detecting fraudulent patterns is challenging in an ever-changing world. Legacy systems cannot keep up with the scale of data needed to effectively identify financial fraud today. Fraud detection is a complex problem that brings along a complex set of rules that are not only difficult to identify and implement, but also to run at scale. Furthermore, these rules are not modular, cannot be changed easily and do not run in real time, making it harder and harder to keep up with fraudulent behavior.

In this webinar, you will learn how a large Databricks customer migrated from a legacy system, doing rules-based fraud detection, to Databricks. We will walk through how rule-based patterns may be converted to features to create a fraud detection framework. Then we will discuss how to select appropriate Machine Learning (ML) algorithms to make for a successful and reliable fraud detection program.

Learn the following with actual code samples:
  • How to create a fraud-detection data pipeline
  • How to leverage a framework for building features from large datasets
  • How to create modular code to re-use and maintain new machine learning models
  • How to choose appropriate models and algorithms for a given fraud-detection problem


Elena Boiarskaia, Databricks
Navin Albert, Databricks
Elena Boiarskaia
Data Scientist, Databricks
Navin Albert
Solutions Marketing, Databricks

Watch On Demand