Daily research update
we backtested it — Sharpe -0.52 · quant relevance 0.94
The paper studies long-only portfolio allocation when cross-asset dependence is uncertain, using VaR, Expected Shortfall, Range-VaR, and volatility objectives. It is directly relevant to robust portfolio construction and proposes blending risk under a reference model with risk under worst-case dependence.
quant relevance 0.98
The paper proposes a constrained, entropy-based method for factor estimation and portfolio weighting in robust benchmark replication. It compares investable index and ETF tracking, turnover, trading-friction-adjusted returns, and stress-period behavior against OLS.
quant relevance 0.98
The paper develops intraday cryptocurrency strategies based on polynomial autoregression and polynomial moving-regression bands. In six months of live trading, buy-and-hold outperformed the automated strategies across the tested cryptocurrencies.
The rest of the batch
The paper develops a convex multi-period transaction-cost model that combines cross-impact among related contracts with power-law transient impact over time.
This critical review covers AI applications to equity and cryptocurrency return prediction, portfolio construction, and execution, with a focus on the evidence required to establish net tradable alpha.
and 12 more · see the full 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.