AI in Finance: Scope and Examples
Talkat 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI '21) · 2021-07-14..07-16·
summary
Image-based models convert time series into pictures with a Mondrian classifier (S&P500 historical data) that distinguishes buy/no-buy and an autoencoder that completes 80%→20% windows with high accuracy; a multi-agent RL system models market makers as parameterized agents (risk aversion, connectivity), learns bid-ask skewing and inventory hedging, and generates realistic synthetic market data; planning+GANS create synthetic payments; a Sphinx table parser normalizes diverse spreadsheets; a Docubot maps language to slide-generation skills and asks clarifying questions.
AI-written summary · about
chapters (6)
- 0:00AI foundations and goals
- 4:23Image-based decision systems
- 12:58Multi-agent reinforcement
- 24:24Synthetic data generation
- 34:44Automated document tools
- 40:55Q&A session
related talks
59mAI in Finance: Scope and Examples
01h 30mAI in Finance From Insight to Action
23mComplex AI Forecasting Methods for Investments
12mScaling AI in Finance: Strategies Behind $78.6 Billion Market
18mKeynote: AI for Financial Services
18mGenerative AI in Financial Industry
38mAI in action: How to use practically in iGaming beyond the hype?
50mKeynote Panel: AI in Finance