Using data to innovate credit decisioning for Small-to-Medium Enterprises
summary
Builds an underwriting pipeline that combines bank statement parsing, marketplace and payments transactions and device- and app-usage signals with KYC and account-aggregator feeds to score SME creditworthiness. Uses ML models and computer-vision receipt/invoice extraction to automate underwriting and flag early-warning signals; loan applications compress to about three minutes from submission to decision. Targets informal kirana/restaurants and micro-traders previously without formal credit, increasing data coverage and enabling higher-throughput, API-driven lending decisions.
AI-written summary · about
chapters (9)
- 0:00Introduction to data-driven credit
- 3:02MSME lending challenges in India
- 6:50Digital platforms for SME financing
- 9:55Data integration for credit decisions
- 12:49Customer profiling and KYC
- 15:24AI and machine learning in lending
- 17:15Policy and regulatory landscape
- 19:13Future of credit innovation
- 20:43Summary and closing remarks
related talks
41mAI For All: Enhancing Digital Financial Services using Data Science
39mMachine Learning in Financial Credit Risk Assessment
19mThe fintech revolution: what's next?
31mData Science for Financial Inclusion
27mHelping SMEs to Get 100% Loan Guarantees through OCR API during Covid
37mThe Role of Machine Learning in Today’s Payment Ecosystems
12mInterview with – Kristina Reicher
01h 00mReimagine SME banking: OpenDATA-enabled innovation at Rabobank