This is a summary of links recently featured on Quantocracy as of Tuesday, 09/22/2026. To see our most recent links, visit the Quant Mashup. Read on readers!
-
Building and Testing Trend-Following Strategies on One-Minute SPY Data [Quantpedia]Intraday trading strategies have gained increasing attention as advances in computing power and market data availability have made intraday strategy analysis more accessible. While many trading strategies are traditionally developed and evaluated using daily price data, shorter timeframes can provide additional opportunities to identify and exploit market trends within a single trading session. In
-
I Tried A Foundational Financial LLM Model to See If It Holds Up to It s Claims: It Doesn t [Paper to Profit]Since the dawn of the LLM age (only few years ago), there has been a flurry of alternative approaches and fundamental remixed on the classic ChatGPT style attention transformer. In 2023, Bloomberg released BloombertGPT which was the first financial LLM and claimed that it could outperform the current state-of-the-art in financial sentiment analysis. Just last year, a PhD student in
-
State-Dependent (In)Efficiency: Meta-Learning a Directional-Change Threshold [Aligrithm]Barak, Razmi and Mousavi report an out-of-sample Sharpe ratio of 1.34 against 0.59 for the best static version of the identical trading logic, on 50 crypto futures from January 2022 to January 2024, with a Ledoit-Wolf bootstrap p-value of 0.008 on the difference. The machine doing the work is a LightGBM classifier that picks tomorrow's directional-change threshold out of {0.01, 0.02, 0.04}.
-
Is the Altman Z-score still relevant? The 1968 formula tested on the S&P 500 [Quanter Lab]In 1968 Edward Altman took sixty-six manufacturers, half of which had gone bankrupt, and found five numbers from their accounts that together told the two halves apart. His Z-score is still taught, and it is now used for a different job: as a quality screen, a way of choosing which shares to own. The reasoning is easy to follow. A low score means trouble, so a high score should mean a sound
-
The Holdout That Made the Sharpe Bigger [Jonathan Kinlay]The panel in my September post was supposed to have zero alpha. It didnt quite. The market factor carried a drift of 0.0002 per day and the betas were drawn N(1, 0.3), so a book that tilted towards high-beta names had a true Sharpe of about +0.22 on a panel I described as containing nothing. The generator also clipped daily returns asymmetrically, at [0.5, +1.0], which leaves a name whose
-
How much can machine learning improve losing trading strategies? [Daru Finance]Take a library of rules that loses money, put a model on top and let it decide which trades to take, then measure what that recovers across 420 rules, two markets and 43 months. A common pitch for machine learning in systematic trading leaves the strategies alone and puts a model on top of them. The rules keep generating signals, while a model trained on their past trades decides which signals to
-
Good vs Bad COVOL in Crypto: A Common-Volatility Tilt [Aligrithm]Pham, Han, Nguyen, Pham and Do build one index and then trade it backwards. In Section 5.4 they write that an RCI near zero marks "widespread panic selling and a potentially buying opportunity," and that exuberance at the top "can indicate a market peak and a potential selling opportunity." Nine pages later, in Section 6, they lever the portfolio up to 125% when the same index
-
How long should you wait before trading a newly listed perpetual? [Daru Finance]Crypto exchanges list new perpetual futures every week, and Binance alone has listed 832 USDT-margined perpetuals, so a research universe built on that exchange mixes contracts listed last week with contracts that have traded for years. Both kinds usually share one cost assumption and one strategy library, even though a new contract has no settled basis, no settled funding schedule and far more