Keynote: AI for Financial Services
summary
Company researchers present concrete systems: a realistic OTC market multi-agent reinforcement learning simulator trains market-maker policies using Ray RLlib and PPO and produces measurable behaviors — learned price skewing and inventory management — with skew intensity rising as risk aversion increases and falling as connectivity increases. A separate project builds a graph-based pipeline and the RobustEntityTuner for multiplex networks that infers and corrects thousands of missing data-flow links, improving network coherence on large enterprise datasets.
AI-written summary · about
chapters (10)
- 0:00Introduction and speaker background
- 1:27JP Morgan AI research overview
- 3:16AI research aspirational goals
- 6:00OTC markets multi-agent simulation
- 9:55Reinforcement learning with Ray
- 10:16Market maker behavior results
- 12:49Ray’s impact on research
- 13:10AI for safe data liberation
- 14:34Multiplex network inference
- 16:41Conference announcement and closing
related talks
50mKeynote Panel: AI in Finance
59mAI in Finance: Scope and Examples- 59mAI in Finance: Scope and Examples
26mAI Agents as Financial Co-Pilots | AI-Driven Strategy & Decision Making
23mComplex AI Forecasting Methods for Investments
26mKeynote: AI in the Real World: Today and Tomorrow
29mComplex AI Forecasting Methods for Investments Portfolio Optimization
55mAlgorithmic Trading and Machine Learning