New Strategies:
#1283 – Volume-Price-Adjusted MACD Trading Strategy
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: ETFs, futures, CFDs
Complexity: Complex
Backtest period: 2023-2026
Indicative performance: 23.45%
Estimated volatility: 15.53%
Source paper:
Lin, Luyun and Lin, Lixing and Zhang, Zhen and Zheng, Moxuan and Wang, Yiqing: A Volume-Price-Adjusted MACD Trading Strategy with Sensitivity Calibration for U.S. Equity Indices
https://arxiv.org/abs/2604.26063
Abstract: Traditional moving average convergence divergence (MACD) trading rules are often constrained by signal lag and susceptibility to false signals. To address these limitations, this study develops a volume-price-adjusted MACD (VP-MACD) framework that incorporates volume, volatility, and intraday price structure into the conventional indicator, and introduces a sensitivity parameter, λ, to allow earlier trade entry and improve responsiveness to market movements. Using the S&P 500, Nasdaq-100, and Dow Jones Industrial Average as representative U.S. equity indices, the model is calibrated over historical records from 2018 to 2022 and evaluated out of sample over 2023 to February 2026. The results indicate that the proposed framework generally delivers better economic performance than the baseline MACD strategy in terms of profitability, risk-adjusted return, and downside-risk control, while generating fewer but more selective trading signals. These findings suggest that incorporating additional market information into technical trading rules may enhance signal quality in U.S. equity index markets.
#1284 – Cross-Sectional Dispersion and the State Dependence of Cryptocurrency Momentum
Period of rebalancing: Daily
Markets traded: cryptos
Instruments used for trading: cryptos
Complexity: Complex
Backtest period: 2000-2026
Indicative performance: 7.74%
Estimated volatility: 9.69%
Source paper:
Makgolo, Olorato MacDonald and Zhang, Cong: Cross-Sectional Dispersion and the State Dependence of Cryptocurrency Momentum
https://ssrn.com/abstract=6648082
Abstract: This paper studies the state dependence of cross-sectional cryptocurrency momentum in a dynamic, survivorship-aware universe built from a broad CoinGecko top-500-derived candidate pool with rolling screens for age, market capitalization, trading activity, and return quality. Momentum remains economically meaningful, but lagged cross-sectional dispersion, not generic market volatility, is the variable most closely associated with subsequent breakdown. In horse-race regressions, orthogonalization tests, and asset-level panel specifications, dispersion predicts weaker later momentum returns after controlling for Bitcoin realized volatility and average cross-asset correlation. The effect is nonlinear and concentrated in the upper tail of dispersion, consistent with deterioration in the reliability of the ranking signal. Dispersion-based scaling improves full-sample drawdown and certainty-equivalent outcomes, whereas Bitcoin-volatility scaling performs better in post-2020 long-only implementation exercises. The results distinguish mechanism variables from reduced-form stress proxies and show that inference about cryptocurrency momentum is sensitive to dynamic universe construction.
#1285 – Cross-sectional FOMC Announcement Premium in Stocks
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: stocks, options
Complexity: Very Complex
Backtest period: 2012-2023
Indicative performance: 4.65%
Estimated volatility: 2%
Source paper:
Gerchik, Daniil: When the Chair Speaks: Communication and the FOMC Announcement Premium
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6614558
Abstract: The modern FOMC announcement day contains two distinct public communications: the written statement and the Chair’s live press conference. Using intraday changes in option-implied volatility to measure firm-level exposure separately across these two windows, this paper shows that the FOMC announcement premium in the cross-section of equity returns is concentrated in the press-conference window. From 2018 onward, firms more exposed to press-conference news outperform less exposed firms by 106 basis points per event, with the average return earned across the broader FOMC day rather than only inside the press-conference hour. A measure estimated from the statement through the press conference is weaker and adds little once the press-conference window is isolated. The premium is concentrated among high-valuation, low-leverage firms, and the return gap between high- and low-exposure firms is sharpest when press-conference surprises are dovish.
#1286 – Multi-Asset Commodities Volatility Portfolio
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: options
Complexity: Very Complex
Backtest period: 2013-2023
Indicative performance: 8%
Estimated volatility: 9%
Source paper:
Dottin, Charlton and Zekarias, Leoul and Watson, Arthur: Multi-Asset Commodities Volatility Portfolio
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6710319
Abstract: We present a systematic equal-risk long-short volatility and relative value portfolio across a basket of commodity underlyings. The strategy monetizes the persistent volatility risk premium embedded in commodity options by selling delta-hedged straddles while self-financing tail protection through long out-of-the-money put positions. Position sizing is conditioned on an inventory-based signal derived from rolling five-year z-scores of U.S. commodity inventory data, allowing the portfolio to scale exposure dynamically in response to physical market conditions. In addition to the directional volatility sleeve, the portfolio incorporates relative value trades between structurally linked commodities: WTI versus Brent crude oil and corn versus soybeans. These positions isolate persistent gaps in implied volatility pricing that arise from differences in physical market structure, inventory elasticity, and demand composition. Back-tested over a ten-year period, the risk-weighted portfolio produced a cumulative return of approximately 120%, translating to an annualized return of 8% with 9% annualized volatility and a Sharpe ratio of 0.9. The results demonstrate that combining volatility carry with cross-commodity relative value produces a diversified, regime-resilient return stream with limited drawdowns.
#1287 – Regret-Based Portfolio Allocation
Period of rebalancing: 6 Months
Markets traded: equities, commodities, bonds, REITs
Instruments used for trading: ETFs
Complexity: Very Complex
Backtest period: 2010-2025
Indicative performance: 14.82%
Estimated volatility: 16.6%
Source paper:
Bajo Traver, Mario: Regret-Based Portfolio Allocation: Minimizing Opportunity Cost and Its Dispersion
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6322898
Abstract: Investors increasingly judge portfolios by how much they lag ex-post winners rather than by absolute Sharpe ratios, turning missed opportunities into a first-order driver of dissatisfaction. This paper addresses the resulting gap between regret-based evaluation and traditional risk models that manage the dispersion of portfolio returns instead of the dispersion of regret. We develop a Mean–MAD Regret framework that treats regret—not returns—as the primary object of risk management. The model defines period-by-period regret as the shortfall between a dynamic benchmark and portfolio returns, and then minimizes a Mean Absolute Deviation objective on this regret series using a single parameter to govern the trade-off between average regret and regret dispersion. In a diversified multi-asset universe of equities, fixed income, commodities and real assets, regret-based portfolios with low to moderate dispersion aversion deliver higher compound returns and competitive or superior risk-adjusted performance relative to standard diversification heuristics and risk-based strategies, at the cost of greater concentration and drawdown risk. The main contribution is to provide an operational way to manage the level and volatility of opportunity cost relative to a dynamic benchmark, offering institutional investors a transparent tool to align portfolio construction with how performance is actually assessed.
#1288 – Reviving Anomalies
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 2004-2023
Indicative performance: 16%
Estimated volatility: 15.8%
Source paper:
Beckmeyer, Heiner and Berg, Florian and Wiedemann, Timo and Wortmann, Jonas: Reviving Anomalies
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6468806
Abstract: Prior literature finds that most anomalies fail to deliver significant returns, especially when considering implementation costs. We develop a framework to revive anomalies by incorporating expected returns and transaction costs into portfolio formation. Our approach identifies implementable anomalies across different fund sizes by (i) using machine learning return forecasts and (ii) accounting for scale-dependent price impacts. A 1/N investment strategy in implementable anomalies yields out-of-sample Sharpe ratios between 0.64 and 1.01 with highly significant alphas across all fund sizes. We further document that mutual funds tilt their holdings toward implementable anomalies and that such tilts predict higher subsequent fund returns.
New research papers related to existing strategies:
#33 – Post-Earnings Announcement Effect
Duggaraju, Bharadwaj: Impact of Earnings Surprises on Short-Term Asset Price Momentum
https://ssrn.com/abstract=6174938
Abstract: Earnings surprises, which are instances where a company’s reported earnings deviate from consensus analyst expectations, are among the most potent catalysts for short-term asset price movements in equity markets. This report provides a comprehensive, evidence-based analysis of how positive and negative earnings surprises affect stock prices in the days immediately following earnings announcements. Drawing on classic and contemporary academic literature, recent empirical data (including 2024-2026 market evidence), and sectoral and firmsize heterogeneity, the report explores the mechanisms underlying post-announcement price momentum, including investor underreaction, information diffusion, and behavioral biases. Methodological approaches such as event studies, regression models, and portfolio tests are discussed in detail, alongside the latest advances in measuring earnings surprises. The report also examines the role of market conditions, sectoral dynamics, and firm characteristics in shaping the magnitude and persistence of post-earnings momentum. Policy implications, practical trading strategies, and avenues for future research are addressed, providing a holistic view of this enduring market anomaly.
#883 – High-Momentum in Liquid Cryptocurrencies
Xu, Zezhou and Wu, Fenglin: Size-Momentum Puzzle in Cryptocurrencies
https://ssrn.com/abstract=6628860
Abstract: This paper documents a robust size-dependent pattern in cryptocurrency return predictability. Small coins exhibit strong short-term reversal, whereas large coins exhibit momentum, and the relation varies monotonically across the size distribution. We further show that these two sides of the pattern reflect different return dynamics: small-coin reversal is driven mainly by rebounds among recent losers, while large-coin momentum reflects their continued underperformance. Liquidity frictions and idiosyncratic volatility explain part of this pattern, but not all of it. These findings point to a “size-momentum puzzle” in cryptocurrencies.
#826 – News Sentiment and Equity Returns – BERT ML Model
Prakash, Harshavardhan: Predicting U.S. Stock Sectors Using AI-Driven News Sentiment Analysis
https://ssrn.com/abstract=6653318
Abstract: This paper explores the predictability of U.S stock sectors using an AI-driven sentiment analysis model. This is a logistic regression model that analyzes news headlines and predicts stock fluctuations. Using approximately 11,000 GDELT news headlines from 2017 to 2025, the model generates trading signals, which are then backtested by sector. The results of the model show the Sharpe ratios, a reliable measure of an investment’s return relative to its risk, for each sector. The model has both an unbalanced and a balanced mode: the unbalanced mode predicts each sector based on its frequency in the news, whilst the balanced mode predicts each sector with an equal number of trades per sector. Our results show that the technology and financial sectors appear to be consistent and highly correlated (Sharpe ratios of 0.6 to 1.1) with news headlines. Conversely, the healthcare and real estate sectors have negative Sharpe ratios, indicating poor tradability based on news headlines. In summary, AI-driven news sentiment analysis may be dependent on sectors and their frequency in news headlines.
#645 – Statistical Arbitrage With CNN and Transformer Networks
#1176 – OHLCT Multi-Scale CNN Strategy
Kazim, Zeeshan: Intraday Decision Support for Traders: Explainable CNN-Based Directional Price Forecasting from Candlestick Chart Images
https://ssrn.com/abstract=6506658
Abstract: Short-horizon trader-support systems in financial markets should be judged not only by predictive skill but also by auditability, inspectability, and suitability for decision support under uncertainty. This paper studies an auditable 20-bar chart-image branch built from a retained MOEX Si futures artifact bundle. Starting from 14 contract-level one-minute candle files plus an auxiliary participant-position file, the pipeline resamples to 15-minute candles, selects the daily front contract by realized volume, applies a conservative liquidity filter, constructs a clean continuous-front series of 29,926 bars across 502 trading days, and generates 10,350 same-day, same-contract 20-bar windows rendered as 64 x 60 grayscale candlestick images. A three-block convolutional neural network (CNN) and a Grad-CAM-style local explanation layer are then embedded in a dashboard-centered inspection workflow. On the held-out test split (1,646 windows), the model attains 0.552 accuracy, 0.530 balanced accuracy, 0.408 F1, 0.557 ROC-AUC, and 0.063 MCC. Performance is modest and, at the default 0.50 threshold, trails the naive majority-class baseline on raw accuracy, while remaining better than random in threshold-free ranking terms. Results are contract-concentrated: SiZ5 materially outperforms SiU5. Quantitative explanation summaries show that heat mass is concentrated mainly in the price panel (0.807) rather than volume (0.193), but remains broad and only weakly focused on the final bar (0.043). The contribution is therefore bounded: not novelty of chart-image CNN forecasting or Grad-CAM in futures, both of which already exist, but the integration of chronology-aware futures engineering, auditable chart-image modeling, local explanation outputs, and row-level dashboard inspection in a trader-facing decision-support artifact. Fee-aware economic validation and formal user evaluation remain separated as pending next-stage work.
And several interesting free blog posts that have been published during the last month:
Building an AI Powered Quant Research Assistant with Quantpedia API
Artificial intelligence is gradually changing the way quantitative researchers interact with financial data. Instead of manually browsing databases, comparing strategies one by one and filtering spreadsheets, modern research workflows increasingly rely on conversational systems capable of retrieving and summarizing structured information automatically.
One practical application is combining the Quantpedia API with an LLM such as ChatGPT, Claude or Cursor AI to create a lightweight quant research assistant. In this setup, Quantpedia API provides structured access to quantitative trading strategies, performance metrics, classifications, equity curves, trading codes, and related research metadata through the official Quantpedia API, while the LLM acts as a conversational layer capable of interpreting the retrieved data and transforming it into readable research outputs.
Building Meta-Strategies with Quantpedia API
Quantitative investors usually start their research by analyzing individual trading strategies. They compare performance, risk, implementation complexity, market exposure, and the economic intuition behind each anomaly. However, once historical equity curves of individual strategies are available, a different research question becomes possible. Instead of asking only which individual strategy looks attractive, we can ask how to allocate capital across a broad universe of strategies.
This is where meta-strategies become useful. A meta-strategy does not invest directly in stocks, ETFs, futures, or other financial instruments. Instead, it invests in underlying trading strategies. These strategies become portfolio building blocks, and the researcher can apply allocation rules such as momentum, risk parity, volatility targeting, or mean-variance optimization directly to their return streams.
The Quantpedia API makes this type of analysis practical. It provides access not only to strategy metadata, but also to historical strategy equity curves. Therefore, users can move from strategy discovery to systematic strategy portfolio construction.
How Wise is the Crowd in Prediction Markets
If you’ve ever scrolled through Polymarket or Kalshi wondering whether the “wisdom of crowds” is actually wisdom—or just organized noise—you’re not alone. A new paper, “How Wise is the Crowd? Bias and Edge in Prediction Markets,” tears into the microstructure of modern prediction markets to ask a practical question: Who’s actually making money, and who’s just paying for the privilege of being loud? By engineering a high-frequency data pipeline that ingests tick-level order flow, on-chain wallet histories, and social commentary across decentralized finance and regulated venues, the authors expose structural inefficiencies that most traders overlook. The verdict? Market efficiency in Web3 betting isn’t dead—but it’s wearing a very clever disguise.
Reconstructing a Century of U.S. Corporate Bonds
How much do we really know about corporate bond returns before the modern data era? Until recently, the answer was: not enough. Most empirical work in corporate bond pricing has relied on relatively short samples, especially the post-2002 TRACE period, leaving open the question of whether observed risk premia are robust over longer horizons. Ghaderi, Plante, Roussanov, and Seo (2026) Ghaderi, Plante, Roussanov, and Seo (2026) address this limitation by constructing a historical database of U.S. corporate bond returns from 1895 to 2022. Using hand-collected monthly bond quotes from sources such as the Commercial and Financial Chronicle, Standard & Poor’s Bond Guide, and Mergent/Moody’s Bond Record, they assemble a large panel of corporate bonds that allows for a much longer view of credit risk, return predictability, and factor pricing in fixed income.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
1266 – Dynamic Factor Allocation via Momentum-Based Regime Switching
1267 – A Forecast Model For Crypto Currencies
1275 – Skewness Dispersion and Stock Market Returns
