Weekly research digest
| AI Quant portfolio | AI Quant | S&P 500 |
|---|---|---|
| Week to 2 Oct | -0.2% | -0.2% |
| Since inception | +11.9% | +15.4% |
| Since inception, at market β | +44.0% | +15.4% |
| Sharpe | 2.84 | 1.91 |
| Beta | 0.27 | 1.00 |
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.
How we review new strategy candidates, fix implementation errors and rebuild the test portfolio every day.
A class-weighted ridge-logistic model estimates the probability of near-term VIX stress and continuously scales a long-only SPY allocation, leaving the balance in cash. Volatility targeting, drawdown control, and exposure smoothing further reduce risk.
we backtested it — Sharpe 0.11 · quant relevance 1.00
The paper tests a cointegration-based PEP–KO pairs strategy and finds that its in-sample profitability weakens out of sample. Much of the earlier performance was concentrated around the COVID-19 dislocation, and the daily-price strategy and robustness tests are reproducible subject to the platform's available end date.
we backtested it — Sharpe 0.89 · quant relevance 1.00
The paper proposes a daily PPO allocation policy that combines learned SPY exposure with a target based on trend and VIX. Its 2020–2022 SPY test reports higher risk-adjusted returns and lower maximum drawdown than buy-and-hold, alongside high turnover and limited evidence of robustness across assets.
we backtested it — Sharpe 0.00 · quant relevance 0.96
The paper uses a LASSO path to compute mean–variance efficient frontiers for portfolios with long-only or leverage constraints. Its empirical tests assess numerical accuracy and computation time, not trading performance.
we backtested it — Sharpe 2.30 · quant relevance 0.95
The paper develops a data-driven approach to selecting derivative hedges and reports results using synthetic and real data. Its daily, end-of-day application can be tested with listed US equity options and underlying stocks, but the excerpt does not identify the contracts in the real-data experiments.
we backtested it — Sharpe -0.21 · quant relevance 0.94
The paper derives a rule for liquidating an existing asset position under price dynamics with distinct support and resistance levels. It reports no measured trading performance, and estimating its continuous-time level effects from minute bars would be approximate.
59 new papers written up in this period. Open the Quant Paper Radar →
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.