Research Directions
Research on the construction, decay, and replication of momentum, value, quality, low-volatility, and other factors.
31 related activitiesLast 30 days 21 itemsFeatured among them 0 items
AQR has published a research article noting that the market often incorrectly analogizes tax-aware long-short investing (TA LS) to direct indexing strategies, clarifying two core misconceptions.
Read originalAQR research explores whether tax-aware equity strategies can provide sufficient liquidity without full liquidation, while preserving investment objectives. The study finds that substantial capital can be extracted while maintaining tracking error, leverage, and pre-tax information ratio. The tax-efficient extraction capability of long-short strategies is generally superior to that of direct indexing strategies, and improves with higher strategy tracking error and leverage levels.
Read originalThis study focuses on the wealth creation effect in stock returns, exploring how the combination of profitability and investment behavior affects stock returns. The article is published in the Financial Analysts Journal, Vol. 82, No. 3, Q3 2026, pp. 78-110.
Read originalThe authors use random subsample backtests to examine the effectiveness of exponentially weighted window estimates of the Sharpe ratio for portfolio optimization. They compare the out-of-sample Sharpe ratios of EWM spans of 5, 10, 20, and 30 years against full-sample estimates across various in-sample and out-of-sample periods.
Read originalThis article is published in the Financial Analysts Journal, Volume 82, Issue 3, Q3 2026, pages 28-33. Its core argument is that investors should not blame index investing for their own problems.
Read originalThis article is the sixth part of a series on statistical arbitrage for independent traders. It explains the three core modules of triangulated statistical arbitrage and their resource allocation priorities. High-quality pair screening is the core foundation: using 24 months of historical data, the top 10% of pairs are screened monthly and divided into 5 quality tiers, with the best tier achieving a Sharpe ratio of 1.6 and the worst only 0.42. The author discloses only the general methodology and does not reveal specific implementation details.
Read originalThis article is the fifth in a statistical arbitrage series for independent traders, focusing on the triangulated statistical arbitrage method. Using the energy sector spread network as an example, the author explains how to cross-validate multiple overlapping spreads to identify genuinely mispriced individual stocks, rather than treating deviations in a single spread as a direct trading signal.
Read originalThis article introduces a triangulated statistical arbitrage approach. Using 8 spread groups constructed from 6 energy stocks as an example, the z-score signal of each spread is decomposed into opposite votes for the two individual stocks, which are then aggregated into long-short signals at the individual stock level. This allows direct trading of undervalued or overvalued stocks, replacing the traditional pairs-trading model of hedging both legs simultaneously. The approach can improve capital efficiency, reduce transaction costs, and increase signal utilization, while achieving variance control similar to pairs trading through a long-short basket portfolio. The article will further explain how to evaluate the quality of aggregated signals.
Read originalAn examination of Morningstar's 'Mind the Gap' study shows that poor market timing did not cost investors 15% of fund returns. The study is published in the Financial Analysts Journal, Volume 82, Issue 3, pages 34-42, 2026.
Read originalThe author argues that mean reversion, trend, and momentum are merely labels for price movements rather than trading edges. A true edge requires first identifying the underlying structural cause and then validating it with data. The article uses three types of mean-reversion scenarios as examples: forced liquidation by leveraged funds, scheduled rebalancing of crypto leveraged tokens, and month-end stock-bond rebalancing by wealth management institutions. All three scenarios involve identifiable trading flows that are insensitive to price.
Read originalvn.py 4.3.0 has been officially released. The new version adds the WorldQuant Alpha 101 factor feature dataset to the vnpy.alpha module, and introduces the RGR performance metric to the vnpy_ctastrategy backtesting engine.
Read original
