The sequence of buys and sells for a particular stock, the order flow, we model as an Input-Output Hidden Markov Model fit to historical data. When combined with the dynamics of the order book, this creates a highly non-linear and difficult dynamic system. Our reinforcement learning algorithm, based on likelihood ratios, is run on this partially-observable environment. We demonstrate learning results for two separate real stocks.
Adlar J. Kim, Christian R. Shelton, and Tomaso Poggio (2002). "Modeling Stock Order Flows and Learning Market-Making from Data." Technical report. MIT AI Lab, AI Memo 2002-009. |
@techreport{KimShePog02, author = "Adlar J. Kim and Christian R. Shelton and Tomaso Poggio", title = "Modeling Stock Order Flows and Learning Market-Making from Data", institution = "{MIT} {AI} Lab", type = "AI Memo", year = 2002, number = "2002-009", month = jun, }