New Strategies:
#1289 – Volatility-Targeted QQQ–TLT Rotation with a Multi-Scale CNN-LSTM Forecast
Period of rebalancing: Daily
Markets traded: equities, bonds
Instruments used for trading: ETFs
Complexity: Very Complex
Backtest period: 2007-2026
Indicative performance: 15.1%
Estimated volatility: 25.17%
Source paper:
Suri, Sourish and Chhabra, Antara and Chung, Jaden and Gaudani, Tanuj: Volatility-Targeted QQQ–TLT Rotation with a Multi-Scale CNN-LSTM Forecast
https://www.quantconnect.com/research/20371/volatility-targeted-qqq-tlt-rotation-with-a-multi-scale-cnn-lstm-forecast/p1
Abstract: This research presents a volatility-targeting trading strategy that combines a deep learning CNN-LSTM model with monthly walk-forward optimization to dynamically allocate between QQQ (Nasdaq-100 ETF) and TLT (long-duration Treasury ETF). The model learns multi-scale temporal patterns in daily Parkinson Volatility. Parkinsons Volatility is a range-based estimator that measures intraday price dispersion from the daily high-low range rather than close-to-close returns. to forecast short-term market turbulence, scaling equity exposure inversely to predicted volatility. This work draws on techniques from HARNet (Reisenhofer et al., 2022), which demonstrated the viability of convolutional neural networks for realized volatility forecasting.
#1290 – The MAX Effect with VIX-Based Leverage Scaling
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 1997-2026
Indicative performance: 13.27%
Estimated volatility: 22.12%
Source paper:
Melchin, Derek: The MAX Effect with VIX-Based Leverage Scaling
https://www.quantconnect.com/research/20886/the-max-effect-with-vix-based-leverage-scaling/p1
Abstract: The MAX effect describes how stocks with extreme positive daily returns behave like lotteries and subsequently underperform, so the calmer names left behind earn higher risk-adjusted returns. In this research, we test this anomaly on US Equities and add a volatility overlay that scales portfolio leverage with the CBOE Volatility Index (VIX). Each month, we rank the liquid US Equity universe by a MAX factor and hold an equal-weighted portfolio of the lowest-MAX decile, then lever the book up to 1.5x when the VIX is calm and back to 1x when it spikes. Since 1998, the strategy earned a 0.57 Sharpe ratio, outperforming the 0.335 Sharpe ratio of a buy-and-hold position in SPY over the same period.
#1291 – The Election Anomaly in Bitcoin Returns
Period of rebalancing: Daily
Markets traded: crypto
Instruments used for trading: crypto
Complexity: Simple
Backtest period: 2010-2024
Indicative performance: 8.8%
Estimated volatility: –
Source paper:
Shanaev, Savva and Maksikov, Bogdan and Vasenin, Mikhail: The election anomaly in Bitcoin returns
https://ssrn.com/abstract=6823239
Abstract: This study discovers a statistically and economically significant anomaly in Bitcoin performance – returns are, on average, 2.2% higher on major election days in G20 democracies on an exhaustive 2010 -2024 sample that includes a full Bitcoin price history and 60 election events. This price appreciation is shown to be permanent, independent of the election outcome, and it is not accompanied by any significant prior or subsequent abnormal returns. The effect cannot be explained by conventional calendar anomalies or the Bitcoin halving cycle, and it is robust to alternative specifications and weighting schemes. The documented anomaly highlights the importance of cryptocurrencies in hedging political risks and presents a profitable trading opportunity for investors.
#1292 – Commodity Dual Momentum Trend Filter
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: ETFs
Complexity: Simple
Backtest period: 2007-2024
Indicative performance: 7.59%
Estimated volatility: 14.67%
Source paper:
Vojtko, Radovan and Dujava, Cyril: Dual vs. Single Momentum in Commodities: Enhancing Risk-Adjusted Returns through Absolute Trend Filtering
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6953821
Abstract: Commodities represent a vital but highly volatile asset class, characterized by pronounced cyclicality, lack of yield, and susceptibility to severe macroeconomic drawdowns. While cross-sectional (relative) momentum is a well-documented anomaly, its application in commodities often forces portfolios to hold the “least declining” assets during broad-based bear markets, resulting in unacceptable tail-risk. This study empirically evaluates the efficacy of a Dual Momentum framework—combining relative strength ranking with an absolute time-series trend filter—applied to a diversified suite of commodity sector ETFs (DBA, DBB, DBE, DBP) from 2007 to 2026. We demonstrate that while pure relative momentum exhibits high parameter sensitivity and inconsistent benchmark outperformance, the inclusion of an absolute momentum filter structurally mitigates drawdowns and universally outperforms a static, equally weighted benchmark across all tested parameter combinations. The findings suggest that Dual Momentum provides a robust, parameter-agnostic framework for portfolio managers seeking tactical commodity exposure with superior risk-adjusted return profiles.
#1293 – Trend-Following Pullback Reversal Strategy
Period of rebalancing: Daily
Markets traded: equities, bonds, currencies, commodities
Instruments used for trading: ETFs
Complexity: Moderate
Backtest period: 2006-2025
Indicative performance: 5.32%
Estimated volatility: 6.68%
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=6979441
Abstract: This study investigates short-term price reversals—temporary retracements following adverse daily returns—and develops a systematic trading framework to capture this effect across multiple asset classes. Using daily data from six liquid ETFs spanning equities, fixed income, currencies, gold, and commodities over the period 2006–2025, the strategy applies a long-term trend filter based on a 200-day moving average combined with a multi-day pullback trigger. Trades are executed dynamically with volatility-adjusted position sizing and equal-weighted allocation across active signals. Parameter sweeps, sensitivity analyses, and sub-period tests are conducted to evaluate the robustness of the approach, including variations in moving average length, number of consecutive down days, holding periods, and alternative momentum indicators such as short-term RSI. The study also explores the practical integration of AI tools— ChatGPT and Claude—to assist in research, analysis, and visualization, assessing their effectiveness in generating coherent quantitative insights.
New research papers related to existing strategies:
#720 – Reversal in Small Cryptos
Kiefer, Patrick and Nowotny, Michael: Reversal in Cryptocurrency Returns
https://ssrn.com/abstract=6703978
Abstract: We document cross-sectional reversal in cryptocurrency returns over 8- to 10-week formation windows. A contrarian strategy of buying recent losers and selling recent winners (LMW), implemented with Jegadeesh-Titman (1993) overlapping portfolios, earns high mean returns, high Sharpe ratios and is nearly orthogonal to the market. Using Binance USDT spot pairs (2021–2026), we estimate LMW portfolio statistics across seven universes with mark-to-next delisting accounting. Conditioning on high past volatility delivers Sharpe ratios of 1.19–1.35 (Newey-West t up to 3.31). Excluding the largest tokens raises it further (1.38, t = 3.44). A circular block bootstrap corroborates the high-volatility result nonparametrically, with a mean Sharpe ratio of 1.38 and 95% of Sharpe ratios above 0.67. Several economic mechanisms are discussed, including the tendency of discretionary treasury managers to sell into rallies, and Nagel’s (2012) theory that reversal compensates liquidity providers.
#1083 – Adjusted Momentum Strategies in Indian Stocks
Ahluwalia, Eshan: Half a Momentum: The Cost of Long-Only Constraints in Indian Equity Markets Behavioural Origins, Structural Limitations, and the Case for Long-Short Momentum Strategies
https://ssrn.com/abstract=6629958
Abstract: Momentum-the tendency of past winners to continue outperforming past losers over intermediate horizons-is among the most robust anomalies in empirical finance. Its behavioural foundations, rooted in investor overconfidence and self-attribution bias, imply that the full premium can only be harvested through a zero-investment long-short portfolio that simultaneously exploits the continuation of winners and the further decline of losers. Yet every momentum-oriented mutual fund and index product available to Indian investors-including the benchmark Nifty200 Momentum 30 Index and its associated exchange-traded funds-is structurally long-only. We argue that this is not a minor implementation detail but a fundamental misalignment between the economic mechanism generating the momentum premium and the investment vehicle used to capture it. Using the Nifty 50 universe, we construct a standard 12-1 month cross-sectional momentum strategy and demonstrate that the long-short (WML) portfolio delivers materially higher risk-adjusted returns than the long-only winner decile alone. We further document the structural barriersregulatory constraints on short-selling by mutual funds under SEBI regulations, limited Securities Lending and Borrowing (SLB) depth, and product-design inertia-that prevent Indian fund managers from capturing the complete premium. Our findings suggest that Indian momentum funds are more aptly described as heuristic, discretion-laden products than as fully quantitative implementations of the academically established momentum factor. We conclude with proposals for a richer product architecture, including long-short Specialised Investment Funds (SIF) under the recently introduced SEBI framework.
#753 – Overnight Seasonality in Bitcoin
#926 – Overnight Effect during High Volatility Days in Bitcoin
#1073 – How To Profitably Trade Bitcoin’s Overnight Sessions
Aalipour, Nafise and Mehdian, Seyed M. and Rezvanian, Rasoul: Are Day-of-the-Week Effects in Cryptocurrencies Real? Intraday Evidence from Active and Less Active Cryptocurrencies
https://ssrn.com/abstract=6776934
Abstract: This study revisits calendar anomalies in cryptocurrency markets using hourly data for four actively traded cryptocurrencies (Bitcoin, Ethereum, Tether USDt, and BNB) and eight less active cryptocurrencies. While prior studies based on daily returns provide mixed evidence on day-of-the-week (DoW) effects, we show that these patterns are not persistent daily phenomena. Instead, they are driven by a limited number of intraday intervals and do not reflect broad daily behavior.We further document that these effects are localized, asset-specific, and more pronounced among actively traded cryptocurrencies, while largely absent among less active ones.Overall, the findings indicate that cryptocurrency markets exhibit limited and short-lived inefficiencies rather than persistent anomalies. This highlights the importance of employing high-frequency data in studies of continuously traded markets and suggests that digital asset investors may benefit from the presence of abnormal returns only in a limited number of hours on specific days of the week.
And several interesting free blog posts that have been published during the last month:
Dual vs. Single Momentum in Commodities: Enhancing Risk-Adjusted Returns through Absolute Trend Filtering
Commodities represent a vital but highly volatile asset class, characterized by pronounced cyclicality, lack of yield, and susceptibility to severe macroeconomic drawdowns. While cross-sectional (relative) momentum is a well-documented anomaly, its application in commodities often forces portfolios to hold the “least declining” assets during broad-based bear markets, resulting in unacceptable tail-risk. This study empirically evaluates the efficacy of a Dual Momentum framework—combining relative strength ranking with an absolute time-series trend filter—applied to a diversified suite of commodity sector ETFs (DBA, DBB, DBE, DBP) from 2007 to 2026. We demonstrate that while pure relative momentum exhibits high parameter sensitivity and inconsistent benchmark outperformance, the inclusion of an absolute momentum filter structurally mitigates drawdowns and universally outperforms a static, equally weighted benchmark across all tested parameter combinations. The findings suggest that Dual Momentum provides a robust, parameter-agnostic framework for portfolio managers seeking tactical commodity exposure with superior risk-adjusted return profiles.
Why Most Portfolios Are Under Diversified
Diversification is a key principle in portfolio construction, yet equal-weight portfolios often fail to deliver true risk diversification. This study shows that capital-based allocation can mask strong concentration in a small number of underlying risk factors. We analyze a simple multi-asset portfolio of ten ETFs spanning equities, bonds, commodities, credit, private equity, and Bitcoin. Despite equal weights, risk is highly concentrated in a few volatile assets and amplified by strong cross-asset correlations, particularly within equity and credit markets. Risk parity reduces concentration by balancing risk contributions and improves risk-adjusted performance, though at the cost of lower returns. Further improvement is achieved through clustering-based allocation, which groups similar assets and allocates risk across more independent sources of return. The results demonstrate that effective diversification depends on the structure of risk factors rather than the number of assets or equal capital weights.
Testing an AI-Assisted Research Workflow for Multi-Asset Pullback Strategy Discovery
This study investigates short-term price reversals—temporary retracements following adverse daily returns—and develops a systematic trading framework to capture this effect across multiple asset classes. Using daily data from six liquid ETFs spanning equities, fixed income, currencies, gold, and commodities over the period 2006–2025, the strategy applies a long-term trend filter based on a 200-day moving average combined with a multi-day pullback trigger. Trades are executed dynamically with volatility-adjusted position sizing and equal-weighted allocation across active signals. Parameter sweeps, sensitivity analyses, and sub-period tests are conducted to evaluate the robustness of the approach, including variations in moving average length, number of consecutive down days, holding periods, and alternative momentum indicators such as short-term RSI. The study also explores the practical integration of AI tools— ChatGPT and Claude—to assist in research, analysis, and visualization, assessing their effectiveness in generating coherent quantitative insights.
Why Mean-Variance Optimization Breaks Down
Mean-Variance Optimization remains the intellectual cornerstone of modern portfolio theory, yet its real-world deployment via plug-in MVO often delivers unstable, over-leveraged portfolios that collapse out-of-sample. The core insight from VertoxQuant’s analysis is profound: raw plug-in MVO does not merely propagate estimation error—it systematically amplifies it. This error-maximization phenomenon occurs because the optimizer’s inverse-covariance operator assigns extreme weights to directions that appear low-risk, which, in finite samples, are dominated by noise rather than signal. For academics, this reveals a fundamental statistical pathology; for practitioners, it explains why backtests sparkle while live portfolios bleed.
Understanding Investment Products Through Factor Analysis and Replication
Factor-based portfolio analysis provides a structured framework for understanding the drivers of investment performance, risk, and long-term behavior. This article applies a set of complementary methods to decompose portfolios into their underlying exposures, evaluate their statistical and economic significance, and assess their behavior across different market regimes.
The analysis is conducted using Quantpedia Pro tools, specifically The Multi Factor Analysis, Factor Analysis Models, The 100-year Portfolio Analysis and The ETF Replication. Together, these methods form a unified factor-based framework that connects decomposition, validation, and replication of portfolio returns. This approach allows for a more robust understanding of portfolio structure and highlights the extent to which observed performance can be explained through systematic factor exposures.
Guardrails Make the Researcher: What an AI Agent Got Right (And Wrong) Replicating Nine Equity Anomalies
An autonomous research agent replicated nine published US-equity anomalies on clean, survivorship-free data. The question is not only what it found (out-of-sample decay is the rule, and on a faithful build none survive — the lone apparent survivor turned out to be a construction error the discipline caught) but whether you can trust an agent to find it, and the checks that decide the answer.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
1279 – Relative Value Reversal in Precious Metals and Mining
1280 – Gold Bitcoin Dual Momentum Strategy
1283 – Volume Price Adjusted MACD Trading Strategy
1284 – Cross Sectional Dispersion and the State Dependence of Cryptocurrency Momentum
1290 – The MAX Effect with VIX-Based Leverage Scaling
1292 – Commodity Dual Momentum Trend Filter
