AIQF Daily digest — 6 new papers

Quant Paper Radar · 4 of 6

1. 1

   WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion

   Aashish Bohra, Vivek Vijay · ARXIV

   we backtested it — Sharpe 0.03 · quant relevance 0.98

   The paper proposes a daily equity-index directional forecasting and trading system based on OHLCV-derived technical indicators, wavelet denoising and a dual-branch deep-learning model. The reported results cover the paper’s own index universe, and causal feature construction is required to avoid look-ahead bias.

   original paper

2. 2

   Nature-inspired multi-objective artificial intelligence for short-horizon volatility-regime early warning and defensive asset allocation

   Hamza Boukeffa, Selman Djeffal, Abdelhamid Ghoul · OPENALEX

   we backtested it — Sharpe 0.89 · quant relevance 0.96

   The paper develops a daily volatility-regime early-warning classifier and jointly optimizes probability calibration, feature selection, the decision threshold and a defensive SPY allocation policy. On the holdout, its complex metaheuristics do not generalize better than random search or a simple ridge-logistic/VIX baseline.

   original paper

3. 3

   Investor sentiment and stock portfolio construction: A study based on the black-litterman model

   Linan Sun, Boyang Fu, Wenwen Liu · OPENALEX

   quant relevance 0.98

   The paper combines Eastmoney forum sentiment, BERT-based sentiment classification, LSTM return forecasts and Black-Litterman optimization to allocate across eight Chinese large-cap stocks. It reports substantially improved prediction accuracy and backtested portfolio performance for the BERT-sentiment Black-Litterman specification.

   original paper

The rest of the batch

• SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity

  Georgios Chionas, Charalampos Kleitsikas, Stefanos Leonardos et al. · ARXIV · relevance 0.94

  The paper presents a modular reinforcement-learning simulation framework for dynamically allocating liquidity ranges in concentrated-liquidity AMMs and evaluates agents in simulated market environments.

and 2 more · see the full radar