AQAI QuantAI research lab for systematic strategies

Weekly research digest

AIQF Weekly digest — 3 strategies, 140 new papers

Sent 9 September 2026 · 140 new papers · 3 strategies

The week in numbers

Papers analysed
401
last 23 days
Testable on our data
63
Median Sharpe
0.52
over 87 autonomous runs
AI Quant portfolioAI QuantS&P 500
Week to 8 Sep+0.3%+0.5%
Since inception+12.1%+14.5%
Since inception, at market β+44.8%+14.5%
Sharpe3.142.01
Beta0.271.00

At market β restates the record at the market's beta — the same strategies held at 3.70× the exposure: the return is multiplied by that factor, the drawdown re-measured on the scaled line, and Sharpe is unchanged by it. Arithmetic on the record, not a second track record — no leverage was used and no financing cost is modelled.

From the blog

New public strategies

Quant Paper Radar · 5 of 140

  1. 1

    Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation

    we backtested it — Sharpe 0.75 · quant relevance 1.00

    The paper proposes and backtests a daily, market-neutral US equity-selection strategy using technical, fundamental, macro and text-sentiment data. The core framework can be implemented with available data, but its search-attention inputs and long pre-2020 alternative-data history cannot be replicated.

    original paper

  2. 2

    Benchmarking deep reinforcement learning and classical models for portfolio optimization across market efficiency regimes

    we backtested it — Sharpe 0.78 · quant relevance 0.98

    The paper compares deep-reinforcement-learning portfolio allocation with classical construction methods across rolling market-efficiency regimes. Its tradable idea uses a fuzzy autoregression-based inefficiency measure to select or condition the portfolio optimizer and risk budget.

    original paper

  3. 3

    Entropic Value-at-Risk portfolio optimization for tempered stable Lévy processes

    we backtested it — Sharpe 0.24 · quant relevance 0.98

    The paper develops parametric EVaR portfolio optimization under multivariate tempered-stable Lévy return models and tests minimum-risk and entropic reward-risk allocations in US sector ETFs. In rolling out-of-sample results, several entropic portfolios achieve higher realized Sharpe ratios than matched CVaR portfolios and standard allocation benchmarks.

    original paper

  4. 4

    Market timing and short-term portfolio selection based on state price density

    we backtested it — Sharpe 0.61 · quant relevance 0.98

    The paper derives market-timing and short-horizon portfolio-ranking rules from state-price densities recovered from option-implied-volatility smiles. Its empirical comparisons show that the timing rules generally outperform index buy-and-hold and that the portfolio criteria can beat equal-weight index portfolios.

    original paper

  5. 5

    What survives honest evaluation? Leakage-safe, search-aware assessment of LLM-driven trading strategy discovery

    we backtested it — Sharpe -0.10 · quant relevance 0.98

    The paper presents a framework for evaluating LLM-discovered trading strategies without look-ahead leakage and while accounting for the full set of searched candidates. In real-data backtests on US stocks and ETFs, passive benchmarks pass its tests, while every evaluated LLM-discovered strategy fails after out-of-sample and multiple-testing-aware evaluation.

    original paper

140 new papers cleared the quant-relevance screen in this period. Open the Quant Paper Radar →

This issue was emailed to our subscribers. Subscribe to get the next one — daily or weekly, your choice.

Backtest and model results are research artifacts, not live trading results and not a guarantee of future performance. Informational and educational purposes only. Not individualised investment advice.