New Strategies:
#1259 – LPPLS for Bubbles in Speculative Markets
Period of rebalancing: Weekly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 2019-2024
Indicative performance: 20.12%
Estimated volatility: 40.24%
Source paper:
Huang, Ethan: LPPLS for Bubbles in Speculative Markets
https://www.quantconnect.com/research/20262/lppls-for-bubbles-in-speculative-markets/p1
Abstract: The Log-Periodic Power Law Singularity (LPPLS) has been shown to be predictive of financial bubbles and systemic market crashes throughout history, including research done in the 2008 Great Recession. The LPPLS model assumes that market bubbles are characterized by a transition from steady linear growth to super-exponential acceleration, driven by positive feedback loops. In an age of social media, this phenomenon becomes more likely due to the hype created by economic swings. In these regimes, volatility oscillates with increasing frequency as the system approaches a critical singularity, the proposed bubble pop. We can extrapolate this idea into modern markets which have gone through periodic trends of volatility through American economic uncertainty and AI hype post-2023.
#1260 – Hedged Industry Momentum
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderately Complex
Backtest period: 1965-2022
Indicative performance: 5.79%
Estimated volatility: 5.26%
Source paper:
Gao, Cheng and Li, Sophia Zhengzi and Yuan, Peixuan and Zhou, Guofu: Systematic Reversal and Industry Momentum
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6371558
Abstract: Individual stocks exhibit strong one-month reversal, whereas industry, characteristic, and factor portfolios display short-term momentum. We reconcile these patterns by identifying a residual-to-systematic reversal (RSR) effect: a negative relation between the idiosyncratic return of a momentum portfolio and its future systematic returns. This reversal component depresses industry momentum and obscures its origin. Hedging this component substantially strengthens industry momentum profits and demonstrates that industry momentum is economically distinct from factor momentum. Standard spanning regressions misattribute the source of industry momentum by omitting this reversal component, whereas Fama-MacBeth regressions are less sensitive to this omission and better capture the underlying mechanism.
#1261 – Geopolitical Risk in Currency Markets
Period of rebalancing: Monthly
Markets traded: currencies
Instruments used for trading: futures, forwards, swaps
Complexity: Moderately Complex
Backtest period: 1988-2024
Indicative performance: 3.28%
Estimated volatility: 8.37%
Source paper:
Melone, Alessandro and Stathopoulos, Andreas: Geopolitical Risk in Currency Markets
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6438919
Abstract: We document that sorting currencies into portfolios on the exposure of their expected returns to the level of global geopolitical turmoil yields a substantial return spread that cannot be explained by loadings to standard currency risk factors. We, then, propose a traded currency factor that reflects global geopolitical risk and show that it is priced in the cross-section of currency returns. Furthermore, we show that geopolitical risk factor loadings are related to the sensitivity of expected capital flows to geopolitical turmoil: countries that tend to attract higher-than-average net capital flows in times of turmoil have currencies that hedge geopolitical risk, whereas countries that experience the opposite have geopolitically risky currencies. In contrast, geopolitical factor loadings are unrelated to the exposure of currency expected returns to measures of policy uncertainty.
#1262 – Seasonality in Real Estate Spread Trading
Period of rebalancing: Monthly
Markets traded: REITs
Instruments used for trading: ETFs
Complexity: Simple
Backtest period: 1926-2025
Indicative performance: 9.72%
Estimated volatility: 19.05%
Source paper:
Beluská, Soňa and Vojtko, Radovan: Anomaly-Based Trading Strategies in the Real Estate Sector. Can the Market Be Beaten?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6428819
Abstract: This study examines the effectiveness of several anomaly-based trading strategies applied to the real estate sector represented by the RlEst index from the Fama–French 48 industry portfolios. Using monthly data from July 1, 1926, to December 1, 2025, we analyze whether selected strategies are capable of generating superior risk-adjusted returns compared to both the standalone RlEst index and the broader market represented by the Fama–French 12-industry portfolios. The tested approaches include trend-following strategies based on moving averages, momentum strategies based on the rate of change of the index, and seasonality-based strategies utilizing different look-back periods.
#1963 – Niche ETF Reversal Strategy
Period of rebalancing: Daily
Markets traded: equities, commodities, bonds, currencies
Instruments used for trading: ETFs
Complexity: Moderately Complex
Backtest period: 2007-2026
Indicative performance: 19.37%
Estimated volatility: 10.04%
Source paper:
Belobrad, David and Vojtko, Radovan: Evaluating Reversal Potential in Niche Alternative ETFs
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6324478
Abstract: Alternative ETFs sit at an unusual intersection of public-market accessibility and hedge-fund-style investment techniques. They package managed futures, merger arbitrage, and option-based income strategies into exchange-traded products, yet they remain thinly traded and relatively niche compared to mainstream equity or bond ETFs. This combination makes them intriguing: they offer exposure to alternative risk premia, and their limited liquidity raises possibilities to build short-term reversal strategies.
New research papers related to existing strategies:
#670 – Machine Learning Pairs Trading Strategy
Kolapwar, Pranjala and Kulkarni, U. V. and Waghmare, J. M.: A Regime-Aware Hybrid Pairs Trading System with Sentiment-Driven Intelligence
https://ssrn.com/abstract=6450750
Abstract: Pairs trading, a widely used statistical arbitrage strategy, is often constrained by static pair selection methods and limited adaptability to dynamic market conditions. Existing approaches primarily focus on numerical indicators, neglecting the influence of market sentiment and collective behavioral patterns on trading outcomes. This paper proposes a hybrid pairs trading strategy (HPTS), formulated as a computational social system that integrates numerical indicators with sentiment-driven social signals to enable adaptive and robust trading decisions. HPTS combines sentiment analysis from financial news using the VADER model, a random forest-based pair selection guided by correlation and volatility, and a regime-aware sector rotation mechanism to align positions with bullish, bearish, and neutral market states. By embedding social signals into computational models, HPTS bridges quantitative finance with behavioral market dynamics, enhancing both adaptability and profitability. Empirical evaluation on historical equity datasets demonstrates that HPTS consistently outperforms conventional pairs trading methods, offering superior responsiveness to regime shifts, improved trade selection, and higher risk-adjusted returns. These results underscore the value of hybrid expert systems that fuse numerical and textual data for intelligent, resilient market strategies.
#1053 – How to Improve Commodity Momentum Using Intra-Market Correlation
Fan, John Hua and Zhang, Tingxi: Correlation and Commodity Risk Premia
https://ssrn.com/abstract=6247358
Abstract: We document a novel correlation premium in commodity futures. A long-short correlation portfolio delivers positive average returns but is largely spanned by exposures to the aggregate market, hedging pressure, and skewness factors. The correlation premium reflects compensation to liquidity providers for absorbing hedger-driven market impact in illiquid markets, as high comovement signals market-wide flows and hedging pressure that amplify systematic risk. Factor performance is state-dependent, with momentum underperforming in high-comovement and high-volatility regimes while hedging pressure strengthens. Overall, our findings explain the absence of commodity low-volatility premia, clarify why volatility-managed factors often fail, and establish average correlation as a conditioning variable for cross-sectional and conditional commodity returns.
#719 – Cross-sectional Momentum in Large Cryptos
#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.
And several interesting free blog posts that have been published during the last month:
When Crypto Stopped Diversifying: The ETF Regime Shift
Can crypto still help diversify an equity portfolio—or has that edge disappeared? That’s the practical question behind Crypto Contagion. The paper looks at how shocks move between crypto and U.S. equities, and more importantly, how that relationship changed after the launch of crypto ETFs. Instead of relying on simple correlations, the authors use a combination of jump detection (to isolate real stress events) and machine learning techniques to identify actual spillovers. By comparing periods before and after ETFs, they effectively show how the market structure—and with it, the behavior of crypto—has shifted.
One Year Later: Is ChatGPT Finally Worth Using for Quantitative Analysis?
One year ago, in our article “Can We Finally Use ChatGPT as a Quantitative Analyst?”, we explored the feasibility of leveraging ChatGPT for quantitative analysis. Since then, a lot has changed: newer models are now available (from OpenAI and also other vendors), and the ecosystem around AI-assisted analysis has evolved significantly. Back then, we encountered numerous challenges, ranging from model hallucinations and faulty code generation to excessive overfitting. In this article, we revisit these issues to assess what has improved and what remains unresolved, with the goal of finally answering whether we can use LLMs to assist with quantitative analysis tasks.
Systematic Tactical Allocation in Emerging Markets vs. U.S.: A Momentum-Based Approach
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.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
1221 – Large Moves in the Foreign Exchange Market
1254 – Government Shutdown Signal Strategy
1262 – Seasonality in Real Estate Spread Trading
1263 – Niche ETF Reversal Strategy
