Can We Learn to Beat the Best Stock
arXiv:1107.0036 · doi:10.1613/jair.1336
Abstract
A novel algorithm for actively trading stocks is presented. While traditional expert advice and "universal" algorithms (as well as standard technical trading heuristics) attempt to predict winners or trends, our approach relies on predictable statistical relations between all pairs of stocks in the market. Our empirical results on historical markets provide strong evidence that this type of technical trading can "beat the market" and moreover, can beat the best stock in the market. In doing so we utilize a new idea for smoothing critical parameters in the context of expert learning.
Cited by in corpus (13)
- Online Learning: A Comprehensive Survey
- A Framework for Online Investment Algorithms
- Optimal Investment Under Transaction Costs: A Threshold Rebalanced Portfolio Approach
- Learning the dynamics of technical trading strategies
- Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution
- Generalized Self-Concordant Functions: A Recipe for Newton-Type Methods
- Empirical investigation of state-of-the-art mean reversion strategies for equity markets
- Learning zero-cost portfolio selection with pattern matching
- Online Portfolio Selection: A Survey
- Online Learning of Portfolio Ensembles with Sector Exposure Regularization
- Optimal Investment Under Transaction Costs
- Online Learning of Commission Avoidant Portfolio Ensembles
- Application of Deep Q-Network in Portfolio Management