Quantpedia Premium Update – May 22nd

New Strategies:

#1129 – Overnight Volume Shock Strategy

Period of rebalancing: Intraday
Markets traded: equities
Instruments used for trading: stocks
Complexity: Complex strategy
Backtest period: 2000-2016
Indicative performance: 16.03%
Estimated volatility: 16.03%

Source paper:

Cartea, Álvaro and Cucuringu, Mihai and Jin, Qi and Wilson, Mungo Ivor: Volume Shocks and Overnight Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5156605
Abstract: We study the effect of intraday volume shocks on stock returns during overnight and intraday periods. We discover a significant positive relationship between volume shocks and subsequent overnight returns, while no such effect exists during the next intraday session. This pattern is consistent regardless of the market capitalization of stocks. Well-known asset pricing risk factors and common explanations that associate abnormal trading volume with investor attention and cost of capital cannot account for the distinct intraday and overnight patterns we observe. We employ linear and machine learning models to forecast volume shocks and construct portfolios that monetize the positive correlation between volume shocks and overnight stock returns. Our approach addresses the issue that volume shock is only known after the close auction when one trades stocks; we show that this issue of non-tradability does not explain the observed relationship between volume shock and overnight stock returns.

#1130 – Auctions, Macro-Economic Announcements, and Abnormal Returns

Period of rebalancing: Daily
Markets traded: currencies
Instruments used for trading: futures, forwards, CFDs, swaps
Complexity: Simple strategy
Backtest period: 2000-2023
Indicative performance: 2.39%
Estimated volatility: –

Source paper:

Krohn, Ingomar and Vala, Rishi: Auctions, Announcements, and Abnormal Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5207418
Abstract: Abnormally large foreign exchange returns on U.S. macroeconomic announcement days occur only when news releases are preceded by Treasury auctions. On these days, foreign currencies appreciate on average by 8 basis points, with pronounced pre-announcement return drift, combined with higher interdealer trading volume, and rising order imbalances. These pre-announcement dynamics can be directly linked to a decline in Treasury demand and primary dealers’ limited intermediation capacity to absorb risk across markets. Our findings reveal that safe asset demand spills over into FX markets and that auction timing critically shapes exchange rate responses to news, with implications for policymakers and market participants.

#1131 – Catching Crypto Trends

Period of rebalancing: Daily
Markets traded: cryptocurrencies
Instruments used for trading: cryptocurrencies
Complexity: Complex strategy
Backtest period: 2015-2025
Indicative performance: 18%
Estimated volatility: 9%

Zarattini, Carlo and Pagani, Alberto and Barbon, Andrea: Catching Crypto Trends; A Tactical Approach for Bitcoin and Altcoins
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5209907
Abstract: In recent years, cryptocurrencies have attracted significant attention from both retail traders and large institutional investors. As their involvement in digital assets grows, so does their interest in active and risk-aware investment frameworks. This paper applies a well-established trend-following methodology, successfully deployed for decades in traditional asset classes, to Bitcoin, and then extends the analysis to a comprehensive, survivorship bias-free dataset covering all cryptocurrencies traded since 2015, to evaluate whether its robustness persists in the emerging digital asset space. We propose an ensemble approach that aggregates multiple Donchian channel-based trend models, each calibrated with different lookback periods, into a single signal, as well as a volatility-based position sizing method. This model, applied to a rotational portfolio of the top 20 most liquid coins, achieved notable net-of-fees returns, with a Sharpe ratio above 1.5 and an annualized alpha of 10.8% versus Bitcoin. While assessing the impact of transaction costs, we propose a straightforward yet effective portfolio technique to mitigate these expenses. Finally, we investigate correlations between crypto-focused trend-following strategies and those applied to traditional asset classes, concluding with a discussion on how investors can execute the proposed strategy through both on-chain and off-chain implementations.

#1132 – Intraday, Overnight and Macro-Economic Announcement Effect in FX Carry

Krohn, Ingomar and Mueller, Philippe and Whelan, Paul: Uncovered Interest Parity in High Frequency
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5230768
Abstract: We examine violations of uncovered interest parity (UIP) in high frequency, accounting for the discrete nature of interest rate payments in foreign exchange markets. Exploiting both regression- and portfolio-based tests, we do not reject UIP during overnight trading but strongly do so during the U.S. intraday period. Furthermore, we document a strong divergence in excess returns for currency trading strategies exploiting UIP violations on announcement versus non-announcement days. The cross-sectional carry strategy earns the bulk of its excess returns on macro and FOMC days, whereas the dollar carry strategy generates positive returns on non-announcement days and depreciates on announcement days.

New research papers related to existing strategies:

#118 – Time Series Momentum Effect

Valeyre, Sebastien: Breaking the Trend: How to Avoid Cherry-Picked Signals
https://arxiv.org/abs/2504.10914
Abstract: Our empirical results, illustrated in Fig.5, show an impressive fit with the pretty complex theoritical Sharpe formula of a Trend following strategy depending on the parameter of the signal, which was derived by Grebenkov and Serror (2014). That empirical fit convinces us that a mean-reversion process with only one time scale is enough to model, in a pretty precise way, the reality of the trend-following mechanism at the average scale of CTAs and as a consequence, using only one simple EMA, appears optimal to capture the trend. As a consequence, using a complex basket of different complex indicators as signal, do not seem to be so rational or optimal and exposes to the risk of cherry-picking.

#112 – Acceleration Effect Combined with Momentum in Stocks
#290 – Consistent Momentum Strategy

Calluzzo, Paul and Moneta, Fabio and Topaloglu, Selim: Momentum at Long Holding Periods
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5199701
Abstract: This paper examines how a unique feature of the academic definition of momentum, which is constructed with a one-month lag, can help infer which stocks will exhibit momentum in the future. We use this information to develop portfolio formation rules that maintain high exposure to momentum over long horizons. Relative to established methodologies for momentum, our proposed strategies can: (1) reduce turnover; (2) lower risk; (3) boost capacity; and (4) increase returns. Using conservative assumptions on the relation between portfolio turnover and trading costs, we estimate that these portfolio formation rules can increase the net (of trading costs) annual returns of momentum strategies by up to five percentage points and increase the resilience of momentum to post-publication return decay.

#823 – Machine Learning and the Cross-Section of Cryptocurrency Returns

Mann, William: Quantitative Alpha in Crypto Markets: A Systematic Review of Factor Models, Arbitrage Strategies, and Machine Learning Applications
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5225612
Abstract: This paper synthesizes over two dozen peer-reviewed studies on systematic cryptocurrency investment strategies spanning 2018-2025. We identify persistent market inefficiencies across three primary categories: cross-exchange arbitrage, factor-based investing, and on-chain metric signaling. Our analysis reveals that traditional factor models can be adapted for cryptocurrency markets, with size, momentum, and liquidity factors demonstrating statistical significance. Machine learning approaches, particularly N-BEATS architecture and CNN-LSTM hybrids, show superior performance in capturing non-linear price patterns compared to traditional statistical methods. We provide implementation frameworks, including modular Python code for backtesting, signal construction, and execution. Results suggest systematic approaches to cryptocurrency investing have demonstrable statistical validity, though implementation challenges remain substantial. This review serves as a comprehensive resource for researchers and practitioners seeking evidence-based quantitative strategies in digital asset markets.

#144 – Trend-following Effect in Stocks

Liu, Shitao: Ride the Right Horse: a Systematic Trend Strategy for Superior Return Using Portfolio Utility Optimization
https://ssrn.com/abstract=5189974
Abstract: We propose a simple, fully automated, and intuitive strategy trading liquid U.S. public equities that achieves superior risk-adjusted performance over index benchmark. The strategy leverages the simple trend-following idea and applies rigorous portfolio optimization techniques to adjust the portfolio on a daily basis. This strategy outperforms the market during the same period after transaction cost with limited draw-down risk, showing great potential for further improvement and possible in-production profitability.

#144 – Trend-following Effect in Stocks
#67 – Industry Momentum – Riding Industry Bubbles

Jarrow, Robert A. and Kwok, Simon: Riding a Bubble: A Study of Market-Timing Trading Strategies
https://ssrn.com/abstract=5200953
Abstract: This paper characterizes the probability distribution of local martingale price bubble processes in order to construct profitable trading strategies which exploit price bubble dynamics. Various such market-timing trading strategies are identified, all are based on the idea of “riding a bubble” by holding a stock during a bubbly period until the time when the bubble’s magnitude hits a predetermined barrier. We study these market-timing trading strategies via both simulations and back-tests using historical market prices. We show both in theory and practice that implementing such strategies in the presence of a bubble leads to increased performance relative to the traditional buy-and-hold trading strategy.

And several interesting free blog posts that have been published during the last 2 weeks:

Are Sector-Specific Machine Learning Models Better Than Generalists?

Can machine learning models better predict stock returns if they are tailored to specific industries, or is a one-size-fits-all (generalist) approach sufficient? This question lies at the heart of a recent research paper by Matthias Hanauer, Amar Soebhag, Marc Stam, and Tobias Hoogteijling. Their findings suggest that the optimal solution lies somewhere in between: a “Hybrid” machine learning model that is aware of industry structures but still trained on the full cross-section of stocks offers the best performance.

What Can We Expect from Long-Run Asset Returns?

What can we realistically expect from investing across different asset classes over the long run? That’s the kind of big-picture question the “Long-Run Asset Returns” paper tackles—offering a sweeping look at how stocks, bonds, real estate, and commodities have performed over the past 200 years. The paper goes beyond just listing historical returns—it explains how reliable (or not) those numbers are by digging into the quirks and issues hidden in very old data. The authors look at what happens to returns when you include countries or time periods that usually get left out, and they show that the past isn’t always as rosy—or as repeatable—as it might seem if you only look at recent decades.

Is Machine Learning Better in Prediction of Direction or Value?

Building machine learning models for trading is full of nuances, and one important but often overlooked question is: what exactly should we try to predict—the direction of the next market move or the actual value of the asset’s return? A recent paper by Cheng, Shang, and Zhao, titled “Direction is More Important than Speed” offers a clear and practical answer. Their research shows that focusing on direction—simply whether returns will be positive or negative—leads to better model accuracy and, more importantly, stronger real-world investment performance. This is especially true when using machine learning methods, where predicting the direction allows models to better capture downside risks and build more effective trading strategies. For anyone using ML in finance, this paper makes a strong case that predicting where the market is headed is often more valuable than predicting how far it will go.