AIQF Daily digest — 1 strategy, 10 new papers

New public strategies

• SPY-Relative Drawdown-Targeted Constrained Kelly Overlay

  Daily estimates a constrained Kelly allocation across SPY and GLD, then scales its active deviation from a 100% SPY benchmark to prescribed drawdown-risk targets. Infeasible rebalances are skipped rather than clipped or partially executed.

  Sharpe 0.67 · total return 59.2% · max drawdown -35.9%

Quant Paper Radar · 4 of 10

1. 1

   From Economic Explanation to Performance Improvement in Machine-Learning Portfolios

   Yunqi Liang, Stefan Zohren, Mihai Cucuringu · ARXIV · Machine-learning statistical arbitrage and portfolio attribution

   we backtested it — Sharpe -0.82 · quant relevance 1.00

   The paper uses portfolio-performance attributions to adjust machine-learning statistical-arbitrage allocations without retraining. It reports improved out-of-sample net Sharpe ratios for US equity portfolios, but our shorter data history cannot reproduce its full 2006–2024 test.

   original paper

2. 2

   AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery

   Jie Huang, Yuecheng Hong, Yao Chen et al. · ARXIV · Symbolic factor discovery

   we backtested it — Sharpe 0.83 · quant relevance 0.98

   AlphaRLM trains a language model to generate symbolic stock-selection factors and reports improved backtested excess returns. Its US-equity factor evaluation is testable here, but the literature-conditioned reinforcement-learning method and Chinese-market results are not reproducible with the stated resources.

   original paper

3. 3

   AI-modulated pólya urns (AIM-PU): a unified framework for risk-sensitive contextual bandits, resource allocation and portfolio design

   Debashis Chatterjee, Saran Ishika Maiti · OPENALEX · Risk-sensitive portfolio allocation

   we backtested it — Sharpe 0.98 · quant relevance 0.96

   The paper applies a risk-sensitive, contextual Pólya urn to portfolio allocation and reports Sharpe-ratio and drawdown improvements using SPY, MSFT, DUK, and TSLA. Its allocation mechanism can be tested with the platform’s daily US price data, while the reported performance is a claim about the authors’ own implementation.

   original paper

The rest of the batch

• Entropy-regularized portfolio optimization and financial network entropy: diversification and concentration in a multi-asset ETF portfolio

  Dilawar Ahmad Bhat, Sajad Ahmad Sheikh, Manzoor A. Khanday · OPENALEX · relevance 0.97

  The study compares entropy-regularized minimum-variance allocation in multi-asset ETFs with equal-weight and minimum-variance portfolios.

and 6 more · see the full radar