AIQF Daily digest — 15 new papers

Quant Paper Radar · 4 of 15

1. 1

   Stock-level volatility forecasting using machine learning: A comparative study of GARCH, Random Forest, LSTM, and GRU on US Equities

   R. V. Pragadeeshwaran, R. Tarun Narayanan, R. M. Bhavadharini · OPENALEX · Volatility Forecasting and Risk Targeting

   quant relevance 0.94

   The study compares stock-level volatility forecasts and VaR calibration using daily US equity data, with a concrete application to portfolio risk sizing. It reports forecasting accuracy and computational efficiency, not trading returns; Random Forest achieves a reported mean RMSE of 0.0892. The target description ambiguously mixes next-day rolling volatility with volatility over the next five days, so forecast alignment requires verification before replication.

   original paper

2. 2

   A Study on the Incremental Value of Technical Indicator Features in Predicting the Next-Day Direction of the CSI 300 Index

   Wei Zhang · OPENALEX · Machine-Learning Directional Market Timing

   quant relevance 0.94

   The study tests whether technical indicators improve next-day CSI 300 direction forecasts relative to historical-return features using logistic regression and random forests. Adding indicators worsens out-of-sample accuracy, and the best model does not significantly outperform the naive baseline. The forecasting application is relevant to market timing, but the required Chinese index market is outside platform coverage.

   original paper

3. 3

   QBX: A Compiler for Well-Formed, Auditable Alpha Programs

   Yichong Bai, Kaigui Bian · ARXIV · Formulaic Alpha Mining

   quant relevance 0.94

   QBX is compiler infrastructure for systematic alpha mining, enforcing typed strategy construction, information-availability checks, computation reuse, and auditable trial identities. Its reported benefits primarily concern candidate validity and search efficiency on Chinese A-share panels, rather than demonstrated trading profitability.

   original paper

The rest of the batch

• Volatility spillovers and REIT hedging across sectors: Evidence from us and UK markets

  Jongseok Rim · OPENALEX · relevance 0.94

  The study estimates REIT–equity volatility spillovers using multivariate GARCH models to inform sector-specific allocation and hedge ratios.

and 11 more · see the full radar