Action-based feature representation for reverse engineering trading strategies
| Autor: | Roy Hayes, William T. Scherer, Peter A. Beling |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Reverse engineering
business.industry Supervised learning Context (language use) computer.software_genre Machine learning Apprenticeship learning Economics Feature (machine learning) Portfolio Trading strategy Artificial intelligence Algorithmic trading business computer General Environmental Science |
| Zdroj: | Environment Systems and Decisions. 33:413-426 |
| ISSN: | 2194-5411 2194-5403 |
| Popis: | This paper considers the problem of reverse engineering strategies for trading in the financial markets. We investigate this problem in the context of a trading tournament in which student teams used delta hedging and other mechanisms to attempt to achieve benchmark performance in managing a hedge fund in a simulated market. Our hypothesis is that machine learning models can be trained to solve the apprenticeship learning problem; that is, these models can learn to trade like tournament participants. After reviewing classical return-matching approaches and recent work in inverse reinforcement learning, we propose a supervised learning methodology that makes use of recursive partitioning (RP). Our proposed RP approach is based on a feature representation for actions that, we argue, corresponds to the information structures readily available to tournament participants. RP achieves high accuracy in predicting the type and scale of participant trades and in tracking overall portfolio performance. Our results suggest that further research on our proposed approach is warranted and should include an expansion to testing on data from real markets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink