End-to-End Policy Learning of a Statistical Arbitrage Auto encoder Architecture
By Fabian Krause, Jan-Peter Calliess
Rating
1383
Battle Count: 57
Relevance
9/10
Highly relevant for statistical arbitrage strategies and portfolio optimization in quantitative trading.
Implementation Complexity
7/10
Requires advanced knowledge of deep learning and financial modeling, but builds on well-known concepts.
Reproducibility
3/5
The paper provides detailed methodology, but full code implementation is not provided.
About this paper
Methodology: End-to-End Policy Learning Autoencoder. Problem types: Time Series Forecasting, Portfolio Optimization, Statistical Arbitrage.
The interactive Everscope explorer (charts, battles, favorites) loads below.