New Strategies:
#1294 – Value-Growth Spread Timing Strategy
Period of rebalancing: Monthly
Markets traded: equities
Instruments used for trading: ETFs, stocks
Complexity: Simple
Backtest period: 2007-2026
Indicative performance: 3.71%
Estimated volatility: 10.65%
Source paper:
Pauchlyová, Margaréta and Vojtko, Radovan: Timing Value vs. Growth: Evidence from 100 Years of Small Value–Large Growth Spread
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7034959
Abstract: The goal of our article is to examine the long-term relationship between small value and large growth stocks using more than 100 years of data and to test whether the spread between small value and large growth portfolios exhibits trends that could help investors switch between the two styles. Using the Fama–French 2×3 and 5×5 size and book-to-market portfolios, we construct the small value minus large growth (SV–LG) spread and apply simple trend-following signals based on moving averages and momentum with horizons ranging from 3 to 12 months. Our results show that trend-following strategies are able to capture part of the value outperformance on the long side. Timing periods when growth stocks dominate is much more difficult.
#1295 – Multi-Asset Skewness Strategy v2
Period of rebalancing: Monthly
Markets traded: currencies, equities, bonds, commodities
Instruments used for trading: futures
Complexity: Simple
Backtest period: 2010-2020
Indicative performance: 7.67%
Estimated volatility: 15.57%
Source paper:
Vojtko, Radovan and Lievaj, Marek: Multi-Asset Skewness Trading Strategy
https://ssrn.com/abstract=3724849
Abstract: This paper examines the relationship between the skewness in returns and future expected returns across different asset classes . At first, a relation for each of three asset classes (currencies, equities, bonds) is revised by building skew-based long/short portfolio from the investment universe of the particular asset class. As the average correlation between monthly returns of particular asset portfolios is minimal, further we propose a multi-asset skewness trading strategy that combines currencies, commodities, equities and bonds into one portfolio. The multi-asset long/short portfolio with inverse volatility asset class weighting would earn an annual return of 7,67% from 11/2010 to 5/2020 when leveraged to the 15% volatility.
#1296 – Composite Seasonal Equity Strategy
Period of rebalancing: Daily
Markets traded: equities
Instruments used for trading: ETFs
Complexity: Simple
Backtest period: 1993-2019
Indicative performance: 7.47%
Estimated volatility: –
Source paper:
Vojtko, Radovan and Padysak, Matus: Composite Seasonal Equity Trading Strategy
https://ssrn.com/abstract=3475660
Abstract: The main focus of this paper is to show that calendar/seasonal anomalies are well-working even in the most recent periods and, additionally, to find a way how to combine them in a search for profit from the practitioner’s point of view. This paper is a case study of possible usage of following anomalies: Turn of the Month in Equity Indexes, Federal Open Market Committee Meeting Effect in Stocks, Option-Expiration Week Effect and The Payday Effect. Firstly, it was found that each individual trading strategy is profitable and those strategies could or probably should be combined into one complex composite seasonal strategy. The analysis has also found that the strategy mentioned above could be enhanced by the addition of a trend factor. To be more precise, data suggest that it is worth to systematically trade only if the trend factor signals to do that. Such addition drastically reduces drawdowns and the resulting strategy simply does not enter into trading positions when the market situation is not favorable.
#1297 – Exotic Commodity Momentum Strategy
Period of rebalancing: Monthly
Markets traded: commodities
Instruments used for trading: futures
Complexity: Simple
Backtest period: 1997-2020
Indicative performance: 6.93%
Estimated volatility: 14.08%
Source paper:
Cisár, Dominik and Vojtko, Radovan: How to Use Exotic Assets for Trading Strategy Improvement
https://ssrn.com/abstract=3916918
Abstract: Popular and liquid assets are usually overpriced compared to less-known (exotic) assets/securities. Additionally, more professional investors usually follow popular assets, because this market segment is probably significantly more efficient and it does not bear liquidity issues. So, we went in this direction to test these popularity and liquidity premiums. We took a well-known commodity momentum factor strategy and investigated its performance among commodity futures that were part of the S&P GSCI respectively BCOM commodity indexes and then compared the strategy’s performance with a variant that traded only non-indexed commodity futures. As we had expected, the trading strategy using exotic assets performed significantly better.
#1298 – Large Cap-Mid Cap Spread Strategy
Period of rebalancing: Quarterly
Markets traded: equities
Instruments used for trading: stocks
Complexity: Moderate
Backtest period: 2000-2026
Indicative performance: 11.23%
Estimated volatility: 28%
Source paper:
Belobrad, David and Demko, Jakub and Vojtko, Radovan: When Big Gets Small: Trading the Lower Tier of Large Caps and Upper Mid Caps
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6724421
Abstract: 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?
#1299 – Industry Factor Structure and Crisis Risk Premium
Period of rebalancing: 6 Months
Markets traded: equities
Instruments used for trading: stocks
Complexity: Very Complex
Backtest period: 2000-2026
Indicative performance: 5.6%
Estimated volatility: 10.05%
Source paper:
Woo, Jihwan and Kim, Nari: The Shape of Beta: Industry Factor Structure and Crisis Risk Premium
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6362168
Abstract: We document that stocks within the same industry share a common factor exposure structure—an “industry beta shape”—and that deviations from this shape predict future returns during financial crises. Using CRSP data covering 4,240 U.S. stocks across 36 industries from 2004 to 2024, we estimate firm-level Fama-French five-factor betas and characterize the cross-sectional structure of beta matrices within each industry. We find that the top two singular values of the industry beta matrix explain 82% of its variance, indicating substantial commonality in factor exposures. Exploiting this structure through cross-sectional shrinkage improves out-of-sample return prediction by 7.5% relative to OLS, with positive improvement in all 36 industries tested. Stocks whose factor exposures deviate from the industry norm earn a crisis risk premium: the quintile spread is economically large during the Global Financial Crisis (+17.8%/year) and COVID-19 (+26.4%/year) but negligible in tranquil periods. This spread survives controls for firm size, is concentrated in large-capitalization stocks ( t = 4 .27), and is robust to transaction costs. The signal requires a rich factor model (FF5 > FF3 > CAPM), suggesting that multi-dimensional factor exposure heterogeneity, rather than simple market beta dispersion, drives the premium.
#1300 – Latency Alpha in Crude Oil Futures
Period of rebalancing: Intraday
Markets traded: commodities
Instruments used for trading: futures
Complexity: Very Complex
Backtest period: 2022-2023
Indicative performance: 31.2%
Estimated volatility: 17.14%
Source paper:
Pape, William: Latency Alpha: Real-Time LLM-Based Semantic Extraction of EIA Petroleum Data for Forecasting and Trading Crude Oil Futures
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6486660
Abstract: This study introduces an event-driven trading framework that converts unstructured macroeconomic data into low-latency signals in crude oil futures markets. We formalize “Latency Alpha” as the economic value derived from minimizing information-processing time. The system ingests the U.S. Energy Information Administration Weekly Petroleum Status Report at release, applies retrieval-augmented large language model analysis, and converts semantic outputs into a numerical signal integrated with a GARCH(1,1) volatility model for risk-adjusted execution. A 24-month backtest (2022–2023) on West Texas Intermediate futures yields a Sharpe ratio of 1.82 and a Sortino ratio of 2.89, outperforming a volatility-only baseline. Results demonstrate that real-time semantic processing enhances short-horizon forecasting and that latency remains a diminishing but exploitable source of market advantage.
#1301 – GARCH-LSTM Pair Trading Strategies on ETH-BTC pair
Period of rebalancing: Daily
Markets traded: crypto
Instruments used for trading: crypto
Complexity: Very Complex
Backtest period: 2021-2024
Indicative performance: 56.71%
Estimated volatility: 18.84%
Source paper:
Lim, Zhe Yee and Liew Zi Qing, Debbie and Ogwuche, Joseph Adakole: GARCH-LSTM Long/Short Pair Trading Strategies on ETH/BTC pair
https://ssrn.com/abstract=6554918
Abstract: Conventional pairs trading strategies rely on historical correlations and assume mean-reversion, which isn’t substantial to highly volatile and non-linear dynamic markets such as the cryptocurrency market. The project proposes leveraging Machine learning, particularly combining Generalized Autoregressive Conditional Heteroskedasticity and Long Short Term Memory model with Attention mechanism and an Altcoin Season Index regime-switching filter to pair trading in such a dynamic market. This project includes model development, backtesting and evaluation, aiming to outperform traditional statistical methods in terms of adaptability and profitability.
#1302 – Token Dilution Premium Strategy
Period of rebalancing: Weekly
Markets traded: crypto
Instruments used for trading: crypto
Complexity: Very Complex
Backtest period: 2020-2026
Indicative performance: 32.36%
Estimated volatility: 28.51%
Source paper:
Guo, Yulin: Token Dilution and the Cross-Section of Cryptocurrency Returns
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6636258
Abstract: We document a token dilution premium in cryptocurrency markets. Using weekly data on 404 coins from 2020–2026, the FDV premium and a 12-week dilution rate predict cross-sectional returns with Newey–West t-statistics of −3.13 and −2.79; portfolio sorts yield annualized long–short spreads of 25–32%. Aggregate dilution risk carries a positive systematic premium (t = +2.72). The premium is absent in the top-five blue-chip tokens and in mature coins but concentrated in the first year of trading, pointing to a pattern consistent with limited investor attention to publicly disclosed vesting schedules and inconsistent with mechanical price pressure.
And several interesting free blog posts that have been published during the last month:
Silicon vs. Satoshi: Tactical Asset Rotation Between NASDAQ-100 and Bitcoin
In the modern retail attention economy, Bitcoin and the NASDAQ-100 are not merely separate assets; they are competing narratives. Both appeal to the same pool of speculative capital, the same appetite for asymmetric upside, and the same behavioral forces of FOMO, herding, and recency bias. When technology stocks dominate the imagination, capital clusters around QQQ and the artificial intelligence trade. When Bitcoin breaks out, the crowd’s attention pivots toward crypto’s promise of explosive upside.
This paper tests whether that rotation in attention leaves a systematic footprint. Using Donchian breakout signals across QQQ and Bitcoin, with cash as a fallback during periods of consolidation, we examine whether investors can harvest momentum without remaining permanently exposed to either asset’s full drawdown profile. The results suggest that the answer is yes: retail attention does not move randomly. It rotates, it concentrates, and—when measured through price breakouts—it can be systematically exploited.
Quantpedia API as an On-Demand Factor Database
Investors often face a simple but important problem. They receive a fund equity curve, a strategy track record, or a portfolio performance series, but they do not know what is actually inside. The manager may provide only a broad description, while the realized return stream may in practice be driven by a mix of momentum, tactical allocation, defensive overlays, cross-asset rotation, or other systematic effects.
One way to approach this type of problem is to use a specialized Multi-Factor Analysis report available in Quantpedia Pro. However, this case study focuses on the second approach: building a custom workflow through the Quantpedia API and AI-assisted methodology design. Instead of treating Quantpedia only as a static library of strategy ideas, the workflow uses it as an on-demand database of factor-like return streams. The unknown curve becomes the object to explain, while the Quantpedia strategy universe becomes the set of candidate explanatory building blocks.
In this test, the unknown equity curve was treated as a blind case. The “correct” answer was not used during the analysis. The task was therefore not to confirm a known decomposition, but to test whether an API-based workflow can identify which known systematic strategies best explain the behavior of a black-box curve.
Plus, the following trading strategies have been backtested in QuantConnect in the previous two weeks:
1291 – The Election Anomaly in Bitcoin Returns
