New-type Scoring Models: Analyzing Customer Actions
summary
Describes using machine learning to build new scoring models that analyze customer behavioral data—especially financial transaction histories—to automatically and quickly assess client risk without human experts and with minimal form input. Also covers customer segmentation techniques for large, high-dimensional financial datasets and practical ML methods used to solve these problems.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 3:57Data monetization challenges
- 10:22Regulation limits in fintech
- 15:07Case: transactional lending models
- 21:52Innovation vs traditional approaches
- 25:23Model interpretability and regulations
- 33:49Fintech and biotech specifics
- 41:19Task formulation importance
- 48:03Corporate client models
- 50:11Complex models and big data
- 53:20Success factors and team role
- 54:24Q&A
related talks
23mChallenges in using machine learning for financial monitoring
39mMachine Learning in Financial Credit Risk Assessment
27mData Science and ML with an emphasis on Banking...
37mThe Role of Machine Learning in Today’s Payment Ecosystems
28mRecent approaches in retail banking marketing optimization
45mAnti-Fraud in Reverse and the Use of ML Methods in It
01h 19mOn financial modelling, credit scoring, and risk assessment
48mProcessing Terabytes of Data in Credit Scoring