This is a summary of links recently featured on Quantocracy as of Wednesday, 11/11/2026. To see our most recent links, visit the Quant Mashup. Read on readers!
-
The Modified Gerber Statistic [Portfolio Optimizer]A previous blog post described the Gerber statistic1, a measure of co-movement introduced in Gerber et al.1 built upon the idea of excluding small return observations deemed to be noise and of estimating dependence using a function robust to outliers2. Since its publication, different improvements to that statistic have been suggested in the litterature (Smyth and Broby3, Flint and Polakow2),
-
Whole-Contract Futures Portfolio Construction [Handelsmeisterei]Your trading model wants an ideal position of 0.03 futures contracts, but your broker requires a whole number. This article compares a proven greedy algorithm with a mixed-integer optimizer that constructs tradable portfolios. Experiments across portfolios of 50 to over 300 instruments test which method performs better. Advances in Portfolio Construction (PDF, 19 pages, 5.6 MB) The figures below
-
All-weather or 60/40? A portfolio backtest with qis [Artur Sepp]My paper qis: reproducible performance analytics and portfolio backtesting in Python was published in the Journal of Open Source Software on 18 October 2026. qis is the Python package behind the analytics of my research papers, and it has been downloaded 244K times from PyPI as of 11 November 2026. Download history Contents: Why qis: the problem I built it for, and what it covers today. An
-
Insider buying: twenty years of who buys, when, and whether following them pays [Quanter Lab]When a company's own directors and top managers buy its shares with their own money, people take it as a sign of confidence. They know the company better than anyone, so the thinking goes, and nobody buys more of something they expect to fall. These purchases are public: the law makes every insider report each trade to the SEC within days. We used those reports in two ways. First we counted,
-
Bitcoin Abnormal Day Momentum Backtest: 91% Became 41% [YuRa Trading]A 2020 paper says riding Bitcoin's most extreme days wins 86% to 91% of the time. We tested it with a trigger you could really trade. The average trade lost 29.98 basis points before costs, and all 9 settings were negative. Short answer Does trading Bitcoin's abnormal days work? Not in our test. A 2020 paper reports 86% to 91% winners from riding Bitcoin's extreme days to the close,
-
Box Theory Traded Blindly: 3 of 4 Claimed, 32.8% Measured [Nullius Research]A trading channel draws one box on its chart every morning: yesterdays high and yesterdays low, with a line through the middle. Sell at the top, buy at the bottom, stay out of the middle. On camera, traded blindly on the Nasdaq, it showed three winners, one loser, and called the blind version that accurate. Four trades say very little. So I tested the rule on the Nasdaq 100
-
Copying the U.S. Congress: 21,756 Trades and a Disclosure That Arrives 27 Days Late [Dead Signals Lab]Few investment ideas have as large an audience as copying U.S. legislators. There are accounts dedicated to spreading their purchases the same day they are published, exchange-traded funds built for that purpose and a figure who became synonymous with the phenomenon, former Speaker of the House Nancy Pelosi. The intuition behind it is reasonable: whoever drafts and votes on the rules of a sector,
-
MA 9/21 + 200 MA on Gold: 58% Claimed, 42.3% Measured [Nullius Research]A trading video from November 2025 tested a moving-average strategy on gold 100 times. In what it called a good market, it got around a 58% win rate, with a target of 1.5 times the risk. At that target, break-even is 40%. So 58% is a strong claim. I tested the rule on gold from 2017 to 2026, leaving out 2024 and 2025. It did not hold up. But the more useful part of this test is something