Weekly research digest
| AI Quant portfolio | AI Quant | S&P 500 |
|---|---|---|
| Week to 25 Sep | -0.3% | +1.3% |
| Since inception | +12.1% | +15.6% |
| Since inception, at market β | +44.8% | +15.6% |
| Sharpe | 2.95 | 1.99 |
| 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.
Each month, the strategy fits a multivariate normal tempered-stable model to 12 months of daily ETF returns and allocates capital so centered EVaR Euler contributions are as equal as constraints permit. It trades the long-only, fully invested target at the next session's close.
we backtested it — Sharpe 0.24 · quant relevance 0.99
The paper uses forecasts of market concentration and dispersion to allocate dynamically between equal-weighted and capitalization-weighted US equity portfolios. It reports out-of-sample returns after transaction costs. The strategy can be tested on available US equities, but historical S&P 500 membership and the pre-2010 portion of its backtest cannot be replicated.
quant relevance 0.99
The paper evaluates language-model news sentiment as a US equity trading signal and reports net portfolio performance after trading frictions. A related daily strategy is testable, but the platform cannot reproduce the proprietary news sample or quote-based liquidity tests.
quant relevance 0.99
LiMT applies liquidity-aware signals to daily equity forecasting and long-short portfolio construction. It reports forecasting results for the Chinese CSI300 and CSI500 and CSI300 backtests, including an annualized-return increase from 3.99% to 10.01% and a Sharpe increase from 1.22 to 1.86 versus equal weighting. Its return, volume, volatility, and liquidity-constrained allocation mechanism can be tested on US equities, but the reported Chinese-universe results cannot be replicated.
we backtested it — Sharpe -1.60 · quant relevance 0.94
The paper derives a causal multi-asset allocation rule that scales risky exposure by the remaining drawdown cushion while enforcing a maximum portfolio drawdown under a specified return-support model. Its contribution is theoretical rather than an empirical trading backtest, but the policy can be implemented and evaluated with historical US asset returns.
quant relevance 0.98
The paper proposes a turnover-aware method for combining portfolios estimated over different rolling windows. The supplied text states a theoretical tracking-regret guarantee but gives no measured trading-performance result.
42 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.