New Strategies:
#1271 – High Volume Stocks Outperform Overnight
Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex
Backtest period: 1992-2024
Indicative performance: 29.08%
Estimated volatility: 22.77%
Source paper:
Fan, Alfred Qi and He, Zhiheng: Expected Return in Night and Day: The Role of Trading Volume
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6371518
Abstract: We document a novel high-volume overnight premium and intraday discount. Stocks with high trading volume exhibit remarkable future outperformance (underperformance) during the overnight (intraday) period. This phenomenon is highly persistent and prevalent across global equity markets. We rationalize such contrasting night-day effect using a model with information asymmetry. Driven primarily by the overconfidence of late-informed investors, the cycling belief dispersion peaks at market open and dissipates at close, with trading volume capturing the intensity of this dispersion. This mechanism is supported by high-frequency evidence that real-time idiosyncratic volatility, acting as a proxy for investor disagreement, decays over the intraday period.
#1272 – Similarly Priced Stocks Momentum
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 1997-2024
Indicative performance: 3.91%
Estimated volatility: 9.25%
Source paper:
Liu, Chun and Wang, Huaixin and Wang, Yuehan and Yu, Jianfeng: Categorical Thinking and the Experience Effect: Evidence from Price-Based Return Predictability
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6305280
Abstract: Price-based categorical thinking and experience effects jointly imply that investor demand for a stock would be higher after similarly priced stocks earned high returns in the past. We show that price-comparable peers’ recent performance positively predicts focal stocks’ subsequent returns. A long-short strategy exploiting this price-based return predictability delivers 1.13% per month. Using stock splits as a quasi-natural experiment that reshapes price categories and disrupts experience associations, we show that the predictability declines sharply post-split. These findings suggest the unique role of categorical thinking and the experience effect in shaping investor tastes and attention.
#1273 – Anomaly-Driven Demand Factor
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 1990-2023
Indicative performance: 4.03%
Estimated volatility: 6.61%
Source paper:
Kjær, Mads Markvart and Posselt, Anders Merrild: Anomaly-driven demand
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6342599
Abstract: We show that trading on anomalies generates price pressure in the underlying stocks. We construct a proxy for anomaly-driven demand (ADD), capturing demand generated when investors rebalance into and out of anomaly long and short legs. Stocks with high ADD earn significantly higher subsequent returns than stocks with low ADD. This effect carries over to anomalies: anomalies whose constituent stocks have the highest ADD earn 8.04 percentage points higher annualized returns than those whose constituent stocks have the lowest ADD. These results suggest that investor demand for anomalies induce price pressure that becomes incorporated into observed anomaly returns.
#1274 – Liquidity Improvements Factor
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex
Backtest period: 1963-2018
Indicative performance: 8.08%
Estimated volatility: 40.4%
Source paper:
Bro, Jeppe: Momentum Returns and the Role of Liquidity Improvements
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6483840
Abstract: This paper demonstrates that the momentum anomaly arises from cross-sectional liquidity dynamics rather than representing an independent risk premium. I show that past winners systematically improve in liquidity prior to the portfolio formation period, whereas past losers severely deteriorate. By exploiting this asymmetry, I construct a liquidity improvement factor (LIQIM ) that captures the reallocation of trading activity across stocks. I provide causal evidence that lagged, pre-formation liquidity changes strongly predict subsequent momentum price drift. Consequently, LIQIM completely absorbs the momentum alpha across standard asset pricing models. These results indicate that momentum profits are structurally generated by the market’s gradual price adjustment to changing asset-level liquidity states, fundamentally distinguishing this mechanism from aggregate liquidity risk.
#1275 – Skewness Dispersion and Stock Market Returns
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: ETF, funds, futures, CFDs
Complexity: Complex
Backtest period: 2005-2022
Indicative performance: 8.36%
Estimated volatility: 9.39%
Source paper:
Babiak, Mykola and Baruník, Jozef and Kurka, Josef: Skewness Dispersion and Stock Market Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6543219
Abstract: Cross-sectional dispersion in firm-level realized skewness is significantly and negatively related to future stock market returns. This predictive relation is robust in-sample and out-of-sample and is incremental to a broad set of existing predictors, with only a few alternatives retaining independent explanatory power. Skewness dispersion also delivers substantial economic gains in portfolio allocation. Its forecasting power is concentrated in months with monetary policy announcements, reflecting an information-based mechanism. The empirical evidence suggests that skewness dispersion captures the gradual incorporation of investor expectations into prices, driven by both variation in perceived aggregate risk and the adjustment of valuation discrepancies.
#1276 – Momentum EM-US Tactical Allocation
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: ETFs
Complexity: Simple
Backtest period: 1997-2026
Indicative performance: 7.13%
Estimated volatility: 12.64%
Source paper:
Vojtko, Radovan and Dujava, Cyril: Systematic Tactical Allocation in Emerging Markets vs. U.S.: A Momentum-Based Approach
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6544098
Abstract: The global investment environment is going through a period of meaningful structural change. The dominance of the U.S. dollar is increasingly being questioned, geopolitical tensions are rising, and macroeconomic uncertainty remains elevated. Together, these forces challenge the post-Global Financial Crisis environment in which U.S. equities consistently outperformed most international markets. As a result, investors may be approaching a turning point where relative returns between U.S. equities and international markets—especially Emerging Markets (EM)—begin to shift. This research focuses on a practical portfolio allocation question: when should investors increase or reduce exposure to Emerging Market equities relative to U.S. equities? Building on our earlier work analyzing the EAFE-USA spread, we extend the framework to Emerging Markets. Our hypothesis is that the relative performance between U.S. and EM equities is not random. Instead, it shows patterns driven by momentum and broader market trends. These patterns likely reflect persistent capital flows and the gradual way macroeconomic information spreads across global markets. Rather than relying on static asset allocation approaches, we develop a dynamic allocation model that uses momentum and trend signals to generate practical timing signals between U.S. and EM equities. Emerging Markets are particularly interesting in this context because they tend to experience stronger regime shifts and larger performance cycles than developed international markets.
#1277 – Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 2021-2024
Indicative performance: 42.11%
Estimated volatility: 19.05%
Source paper:
Huang, Allen Yikuan and Fan, Zheqi: Beyond Prompting: Autonomous Factor Investing via Agentic AI
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6416881
Abstract: This paper develops an autonomous framework for systematic factor investing via agentic AI. Rather than relying on sequential manual prompts, our approach operationalizes the model as a self-directed engine that endogenously formulates interpretable trading signals. To mitigate data snooping biases, this closed-loop system imposes strict empirical discipline through out-of-sample validation and economic rationale requirements. Applying this methodology to the U.S. equity market, we document that long-short portfolios formed on the simple linear combination of signals deliver an annualized Sharpe ratio of 2.75 and a return of 54.81%. Finally, our empirics demonstrate that self-evolving AI offers a scalable and interpretable paradigm.
New research papers related to existing strategies:
#719 – Cross-sectional Momentum in Large Cryptos
#883 – High-Momentum in Liquid Cryptocurrencies
#1122 – Volatility-Scaled Momentum in Cryptocurrencies
#1195 – Elastic Momentum Factor in Cryptocurrencies
Chen, Kaston and Chen, Jaslyn: A Forecast Model For Crypto Currencies
https://ssrn.com/abstract=6300843
Abstract: This paper examines whether the well known equity momentum effect exists in cryptocurrency markets. We estimate daily cross-sectional regressions of forward returns on past returns with daily price data from Binance for about 50 most actively traded cryptocurrencies. The resulting time series of regression coefficients serves as a measure of the momentum effect’s strength and evolution over time. With the results, we propose a dollar-neutral trading strategy that goes long the top quartile and short the bottom quartile of cryptocurrencies ranked by their momentum signal. Our historical simulation shows the strategy has better sharpe ratio and drawdown profile than simply buying and holding Bitcoin alone.
#645 – Statistical Arbitrage With CNN and Transformer Networks
#1176 – OHLCT Multi-Scale CNN Strategy
Guan, Ketian and Li, Sida and Si, Jia: Understanding the Convolutional Neural Network’s Stock Return Predictability
https://ssrn.com/abstract=6389479
Abstract: Jiang, Kelly, and Xiu (2023) demonstrate that a convolutional neural network (CNN) trained on stock price chart images achieves striking out-of-sample return predictability. Building on their framework, this paper aims to understand the origin of the CNN’s predictive power. We investigate which visual elements drive the CNN’s predictions, whether richer image content can improve them, and where the model focuses its attention within the image. Using controlled ablation experiments, we establish a clear hierarchy among image elements: OHLC (open-high-low-close) price geometry is the dominant source of predictive power, the moving average line is redundant, and volume bars contribute marginally. We further show that augmenting images with 52-week high-low price anchors, grayscale price-level channels, or market index overlays uniformly degrades performance — a “less is more” result indicating that the CNN’s optimal input is the parsimonious OHLC representation. Gradient-based saliency maps reveal that the CNN concentrates attention on closing prices near daily high-low extremes in the most recent trading days, with volume spikes as secondary cues. Comparing saliency patterns across image designs uncovers a novel attention-performance paradox: more focused attention is associated with worse out-of-sample performance, while broader, more diffuse scanning of the OHLC geometry yields superior predictions. Our baseline long-short strategy achieves an annualized Sharpe ratio of 3.744 over 2020-2024, confirming that CNN-based predictability remains robust after the original sample period of the paper.
#246 – Trading on the Dividend Paydate
Li, Siyang and Yang, Siyuan and Zhang, Xiaoyan: Pennies from Heaven, Barriers to Reinvestment: Nominal Price and Predictable Price Pressure
https://ssrn.com/abstract=6459800
Abstract: This paper demonstrates that the predictable price pressure arising from dividend reinvestment is higher for lower priced stocks. Simple difference portfolios yield abnormal returns of 0.165% on payment days and 0.520% over the subsequent 20 trading days. To establish a casual price effect, we show that reinvestment returns vary with split driven changes in nominal price. Trading and holdings data reveal that both retail and institutional investors tend to reinvest dividends into low-price stocks. The tendency is reinforced by round-lot trading conventions. Fractional trading mitigates-but does not eliminate-these frictions. As a result, firms with low-priced stocks appear to cater to investors by adopting higher dividend payout intensity.
#417 – Analyst Days
Cabrera, Gabriel and Kolokolova, Olga and Zhang, Sarah: Save The Date: Analyst/Investor Days as a Trading Signal
https://ssrn.com/abstract=6666218
Abstract: Firms increasingly use Analyst/Investor (A/I) days as discretionary disclosure channels. We show that announcing an A/I day leads to positive abnormal returns and a sustained pre-event price run-up. The run-up is more pronounced when firms issue additional pre-event voluntary disclosures and is followed by return reversals after the event. In contrast, events without any incremental disclosures exhibit positive post-event returns driven by event informativeness and changes in risk expectations. Exploiting these patterns, we design implementable long-short trading strategies that earn economically and statistically significant abnormal returns. A strategy based solely on the announcement yields positive alphas of around 0.095% before and 0.08% after transaction and borrowing costs. A deep-reinforcement-learning optimal stopping rule further improves performance, generating a positive alpha of 0.13% before costs, highlighting the importance of A/I days as a voluntary disclosure channel and the role of announcement and pre-event behaviour in shaping market prices.
And several interesting free blog posts that have been published during the last month:
When Big Gets Small: Trading the Lower Tier of Large Caps and Upper Mid Caps
The growing dominance of passive investing has fundamentally altered the dynamics of equity markets. A substantial share of trading volume is now driven by index-tracking strategies, which mechanically allocate capital based on index membership rather than company-specific fundamentals. This raises an important question: can predictable flows associated with index rebalancing be systematically exploited?
Commodity Portfolio Strategy for a Potential 2026 Inflationary and Supply Shock Regime
Commodity markets are in the spotlight. Two factors currently stand out. Firstly, the geopolitical tensions, as ongoing instability in the Middle East continues to create uncertainty in energy markets, particularly on the supply side. Secondly, less discussed are climate conditions as the El Niño–Southern Oscillation (ENSO) is a recurring climate cycle that affects temperature and precipitation patterns globally and has historically influenced agricultural yields and supply dynamics.
Together, these forces create a plausible environment for stronger commodity performance, or at least increased dispersion across individual commodities. Instead of expressing this view through a simple buy-and-hold allocation, we approach the problem as a systematic portfolio construction task.
The Attention Factor: The Link That Connects Crypto and Public Equity Markets
In an era of increasingly fragmented market microstructure, the emergence of cross-asset connectedness between Crypto and public equity markets presents a critical challenge for modern portfolio construction. This blog post examines the recent working paper by Harin de Silva, “The Attention Factor: The Speculative Risk You May Already Own,” which identifies a previously underappreciated transmission channel: a speculative cohort of marginal investors whose sentiment shifts propagate correlated price movements across BTC, zero-day-to-expiration (0DTE) options, commission-free brokerages, and social-sentiment-driven equities. The author introduces the Attention factor—a capital-backed measure of collective conviction—as a systematic risk driver that persists after controlling for traditional macro factors, fundamentally reshaping how we model Equity Risk in multi-asset portfolios. For quantitative practitioners, this work underscores the need to augment conventional Risk Models with sentiment-aware factors to capture residual connectedness that standard factor frameworks may overlook.
Dual Momentum Allocation Between Physical Gold and Bitcoin (Digital Gold)
From the trading desk to the portfolio committee, investors face a familiar question: how should alternative stores of value fit into a diversified portfolio? This research explores that question through a systematic dual-momentum framework comparing Bitcoin and physical gold in a rules-based tactical allocation model. Rather than debating ideology, we focus on practical portfolio construction and risk-adjusted returns. The goal is to examine whether “digital gold” can complement its physical counterpart within a disciplined investment process, and whether the distinct behavior of these assets can be used to build a more effective systematic strategy.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
1172 – Can We Finally Use ChatGPT As Quant Analyst?
1252 – Systematic Trend-Following with Adaptive Portfolio Construction in Cryptocurrencies
1264 – Effects of Monsoon on Indian Stock Market
1265 – The Intramonth Momentum Cycle
