RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search
By Tao Ren, Ruihan Zhou, Jinyang Jiang, Jiafeng Liang, Qinghao Wang, Yijie Peng
Rating
1338
Battle Count: 250
Relevance
9/10
The paper presents a novel method for discovering formulaic alphas, which is highly relevant to quantitative trading strategies and portfolio optimization.
Implementation Complexity
7/10
The method involves complex components such as Monte Carlo Tree Search and risk-seeking policy optimization, which may require significant expertise to implement effectively.
Reproducibility
4/5
The paper provides detailed methodology and algorithm descriptions, but the full implementation code is not provided.
About this paper
Methodology: RiskMiner. Problem types: Time Series Forecasting, Regression, Portfolio Optimization.
The interactive Everscope explorer (charts, battles, favorites) loads below.