What question did this study set out to answer?

The research aims to develop a pipeline for equity selection that optimizes stock portfolios using genetic algorithms and ranking models.

April 8, 2026International Journal of Financial StudiesOpen Access

A Hybrid Genetic Algorithm with Learning-to-Rank-to-Optimization for US Equity Portfolio Construction

View Full Paper

Ask AI

Bookmark

Authors

FKFerdinantos Kottas

Discussion

Member takes

Overview

Study evaluates a genetic algorithm approach for stock selection and portfolio optimization, indicating improved performance across market conditions.

Key Points

The research aims to develop a pipeline for equity selection that optimizes stock portfolios using genetic algorithms and ranking models.
Develops an equity selection pipeline that converts quarterly fundamentals to monthly frequency.
Constructs metrics for profitability, leverage, liquidity, and growth characteristics.
Trains a genetic algorithm to optimize mean monthly NDCG@30 and Spearman information coefficient using relevance labels.
Tests the learned ranker out-of-sample using monthly forward returns against the S&P 500 benchmark.
Performs daily dynamic allocation using penalty-driven Max-Sharpe or Min-Variance optimization.
Demonstrates that TTM-based accounting signals, when optimized, lead to strong stock selection.
Shows robust portfolio performance across Pre-COVID, COVID, Post-COVID, and Final Test regimes.
Indicates that ranking objectives and diversification constraints significantly impact performance and stability.

Cite This Study

Ferdinantos Kottas (2026) studied this question.

synapsesocial.com/papers/69d5f13674eaea4b11a7ac47 https://doi.org/10.3390/ijfs14040095

View Full Paper

Ask AI

Bookmark

April 8, 2026International Journal of Financial StudiesOpen Access

A Hybrid Genetic Algorithm with Learning-to-Rank-to-Optimization for US Equity Portfolio Construction

View Full Paper

Ask AI

Bookmark

Authors

FKFerdinantos Kottas

Discussion

Member takes

Overview

Study evaluates a genetic algorithm approach for stock selection and portfolio optimization, indicating improved performance across market conditions.

Key Points

The research aims to develop a pipeline for equity selection that optimizes stock portfolios using genetic algorithms and ranking models.
Develops an equity selection pipeline that converts quarterly fundamentals to monthly frequency.
Constructs metrics for profitability, leverage, liquidity, and growth characteristics.
Trains a genetic algorithm to optimize mean monthly NDCG@30 and Spearman information coefficient using relevance labels.
Tests the learned ranker out-of-sample using monthly forward returns against the S&P 500 benchmark.
Performs daily dynamic allocation using penalty-driven Max-Sharpe or Min-Variance optimization.
Demonstrates that TTM-based accounting signals, when optimized, lead to strong stock selection.
Shows robust portfolio performance across Pre-COVID, COVID, Post-COVID, and Final Test regimes.
Indicates that ranking objectives and diversification constraints significantly impact performance and stability.

Cite This Study

Ferdinantos Kottas (2026) studied this question.

synapsesocial.com/papers/69d5f13674eaea4b11a7ac47 https://doi.org/10.3390/ijfs14040095

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark