AIQF Daily digest — 1 strategy, 20 new papers

New public strategies

• Conventional Binomial MSM Forecast-Driven Volatility Targeting

  The strategy holds SPY long with exposure scaled from a one-day-ahead binomial Markov-switching multifractal volatility forecast. It targets 12% annualized portfolio volatility and exits when forecast SPY volatility exceeds 35%.

  Sharpe 0.90 · total return 54.5% · max drawdown -20.2%

Quant Paper Radar · 8 of 20

1. 1

   CAST: A Cross-Asset State-Space Trading System for Drawdown Control in Stock Markets

   Yu Peng, Matloob Khushi, Josiah Poon · ARXIV

   quant relevance 0.98

   CAST combines a cross-asset online Kalman predictor with an uncertainty-penalized model-predictive controller for systematic equity trading and drawdown control. Its daily price-panel inputs and re-optimization can use US equity daily bars, although applying it to US stocks substitutes that universe for the paper’s four-market evaluation.

   original paper

2. 2

   Diffusion models for dynamic volatility surface generation and data-driven hedging

   Yinbin Han, Jack Yuxiang Zhang, Manuel Torres et al. · ARXIV

   quant relevance 0.98

   The paper uses conditional diffusion models to generate daily implied-volatility-surface scenarios, with static-arbitrage penalties applied to the output. It uses these scenarios to optimize option hedges and reports near-zero tracking errors and lower tail risk than classical delta, delta-vega, and GAN-based hedges, including during COVID-19.

   original paper

3. 3

   Special Markowitz: Thermodynamic Formalism for the Joint Regularisation of Returns and Covariance

   David Reinhardt · ARXIV

   we backtested it — Sharpe 0.30 · quant relevance 0.93

   The paper presents a method for jointly regularizing expected returns and covariance estimates in Markowitz portfolio optimization. It uses per-mode reliability weights to shrink return estimates and covariance eigenvalue deviations toward a reference state, with random-matrix-theory calibration suggested to identify unreliable spectral modes.

   original paper

The rest of the batch

• ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learning Trading

  Asser Moustafa, Rares-Mihail Neagu, Jugal Kalita · ARXIV · relevance 1.00

  ViperQ is a reinforcement-learning trading system that applies Auction Market Theory and order-flow features to TSLA and NVDA at one-second frequency.

• Same Book, Different Fills: Partial Identification of FIFO Execution from Aggregate Order Books

  Riya Danait, Yuliana Zamora, Ioana Boier · ARXIV · relevance 0.98

  The paper shows that fill and implementation-shortfall estimates based on L2 data depend materially on the unobserved allocation of cancellations within a FIFO queue.

• Public Opinion as an Option: Leveraging Prediction Markets to Hedge Exposure to Spot Crypto Volatility

  Prashanth Bhaskara, Aadit Jerfy · ARXIV · relevance 0.96

  The paper proposes a dynamic BTC hedge that trades Kalshi Bitcoin price-event contracts when market-implied probabilities diverge from a Black-Scholes-style probability estimate based on historical volatility.

• VertiFuseX: Generalizable Financial Forecasting via Multi-Stream Temporal Fusion

  Aashish Bohra, Vivek Vijay · ARXIV · relevance 0.96

  The paper presents a fused multi-stream LSTM architecture for forecasting equity-index prices and reports lower forecast errors alongside improved risk-adjusted returns and drawdowns in an algorithmic-trading simulation.

• Strategic Index Reconstitution: Differential Games, Closed-Loop Equilibria and Mean-Field Dynamics

  Lukas-Benedikt Fiechtner, Jose Blanchet · ARXIV · relevance 0.93

  The paper develops a theoretical market-microstructure and optimal-execution framework for strategic trading around index reconstitutions, covering anticipatory positioning, transient cross-asset impact, and competition among opportunistic traders.

and 12 more · see the full radar