Processing Terabytes of Data in Credit Scoring
summary
Describes how a bank moved from traditional interpretable scoring methods to neural networks that make credit decisions using terabytes of data. Covers the problem of scaling credit scoring to huge datasets and the practical use of neural network models and infrastructure to process and serve those terabyte-scale inputs.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 2:35Credit scoring problem
- 7:09Model metrics and business impact
- 9:15Credit scoring evolution at Alfa-Bank
- 11:42Neural network data sources
- 17:24Neural network architectures
- 20:36Training models on terabytes
- 24:11Neural network deployment results
- 27:01Production and infrastructure evolution
- 29:51Future plans and service architecture
- 32:03Q&A
related talks
39mMachine Learning in Financial Credit Risk Assessment
58mNew-type Scoring Models: Analyzing Customer Actions
50mData Science in a modern financial institution
31mData Science for Financial Inclusion
35mBank evolution to data science-driven business model
41mAI For All: Enhancing Digital Financial Services using Data Science
22mUsing data to innovate credit decisioning for Small-to-Medium Enterprises
18mTransforming Financial Decision Intelligence Through Advanced NNs