aiqbench analysis
This research applies Monte Carlo Tree Search to solve the combinatorial challenge of feature selection in high-dimensional financial regression, offering a robust alternative to standard Lasso regularization. By optimizing for out-of-sample performance rather than training error, the method effectively handles multicollinearity among thousands of engineered variables while maintaining model interpretability. The approach demonstrates significant gains in explanatory power for tasks like factor attribution, highlighting its utility where transparency and stability are critical alongside predictive accuracy.
$L_0$ Feature Selection via Monte Carlo Tree Search in High-Dimensional Financial Regression
arXiv:2610.13574v1 Announce Type: new Abstract: Feature selection is a central problem in high-dimensional financial regression, where large numbers of engineered variables and strong correlations among predictors reduce model stability and interpretability. $L_1$ regularization (Lasso) is widely used for sparse regression, but its shrinkage can be restrictive when informative signals are spread across correlated variables. Exact sparse regression avoids this shrinkage but requires solving a combinatorial optimization problem that is computationally difficult and is typically fit to minimize in-sample rather than out-of-sample error. This paper presents a feature selection framework based on Monte Carlo Tree Search with Generalized Nested Rollout Policy Adaptation (GNRPA). Feature selection is formulated as a sequential decision process, and candidate subsets are scored by their out-of-sample validation performance rather than training error. The method also supports a lexicographic objective accounting for subset size and multicollinearity. We study this approach on a contemporaneous explanatory regression task: explaining the weekly return of the NASDAQ-100 index from 1,072 engineered features spanning market, macroeconomic, and factor data. This isolates the value of subset selection under multicollinearity from the separate problem of predictive forecasting. On this task, the proposed method identifies sparse feature subsets with higher out-of-sample explanatory power than an optimized Lasso baseline, reaching an out-of-sample $R^2$ of 0.6961 versus 0.6313 for Lasso. These results suggest that Monte Carlo Tree Search is a practical alternative to convex regularization for sparse explanatory feature selection in financial regression, with potential value for factor attribution and risk decomposition where transparency matters as much as out-of-sample fit.
Abstract:Feature selection is a central problem in high-dimensional financial regression, where large numbers of engineered variables and strong correlations among predictors reduce model stability and interpretability. $L_1$ regularization (Lasso) is widely used for sparse regression, but its shrinkage can be restrictive when informative signals are spread across correlated variables. Exact sparse regression avoids this shrinkage but requires solving a combinatorial optimization problem that is computationally difficult and is typically fit to minimize in-sample rather than out-of-sample error. This paper presents a feature selection framework based on Monte Carlo Tree Search with Generalized Nested Rollout Policy Adaptation (GNRPA). Feature selection is formulated as a sequential decision process, and candidate subsets are scored by their out-of-sample validation performance rather than training error. The method also supports a lexicographic objective accounting for subset size and multicollinearity. We study this approach on a contemporaneous explanatory regression task: explaining the weekly return of the NASDAQ-100 index from 1,072 engineered features spanning market, macroeconomic, and factor data. This isolates the value of subset selection under multicollinearity from the separate problem of predictive forecasting. On this task, the proposed method identifies sparse feature subsets with higher out-of-sample explanatory power than an optimized Lasso baseline, reaching an out-of-sample $R^2$ of 0.6961 versus 0.6313 for Lasso. These results suggest that Monte Carlo Tree Search is a practical alternative to convex regularization for sparse explanatory feature selection in financial regression, with potential value for factor attribution and risk decomposition where transparency matters as much as out-of-sample fit.
Accepted at the 7th ACM International Conference on AI in Finance (ICAIF '26). 8 pages, 2 figures
Machine Learning (cs.LG); Computational Finance (q-fin.CP); Statistical Finance (q-fin.ST)
arXiv:2610.13574 [cs.LG]
(or arXiv:2610.13574v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.13574 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 364 words
Related coverage
Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
arXiv · Oct 15, 2026
Auditing LLM Program Search for Bermudan Stopping with Primal--Dual Certificates
arXiv · Oct 15, 2026
Monte Carlo Tree Search with Tensor Factorization for Optimization Problems in Robotics
arXiv · Oct 15, 2026
Adaptive Differential Evolution and Multistart Search for Noisy QAOA Optimization
arXiv · Sep 22, 2026