Data-Driven Market-Making via Model-Free Learning
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Special Track on AI in FinTech. Pages 4461-4468. https://doi.org/10.24963/ijcai.2020/615
This paper studies when a market-making firm should place orders to maximize their expected net profit, while also constraining risk, assuming orders are maintained on an electronic limit order book (LOB). To do this, we use a model-free and off-policy method, Q-learning, coupled with state aggregation, to develop a proposed trading strategy that can be implemented using a simple lookup table. Our main training dataset is derived from event-by-event data recording the state of the LOB. Our proposed trading strategy has passed both in-sample and out-of-sample testing in the backtester of the market-making firm with whom we are collaborating, and it also outperforms other benchmark strategies. As a result, the firm desires to put the strategy into production.
AI for trading: AI for algorithmic trading
AI for trading: AI for strategic trading and strategy design
AI for trading: AI for trading incentive and strategy optimization