Long-form notes on portfolio intelligence, quantitative allocation, and the structural gaps between how markets actually behave and how standard risk models assume they do.
| Article | Type · Date |
|---|---|
| The Negative Result Nobody Checks Every quantitative shop guards against the idea that looked good by luck. Almost nobody guards against the idea that looked dead because the test could never have seen it alive — and unlike a false positive, a false negative has nothing downstream to catch it. What we found when we audited our own rejections. | ESSAY July 2026 · 11 min read |
| Why Expected Return Is So Hard to Measure You can measure how much an asset moves from a couple of years of prices. You cannot, from the same prices, measure how much it is expected to earn. The arithmetic behind that gap, why sampling more often does not help, and what it means for anyone judging a track record. | METHODS July 2026 · 9 min read |
| When Trading Costs More Than the Edge Is Worth An edge is quoted per year; a cost is quoted per trade. Multiply the second by how often you trade and the two are routinely the same size. Plus the measurement mistake that hides it, and the diagnostic that tells slow decisions apart from bad fills. | RESULT July 2026 · 10 min read |
| A High Win Rate Is Not an Edge The most persuasive statistic in trading is also the least informative. A strategy that wins nine times in ten can lose money steadily; one that wins three times in ten can be excellent. The line that separates them, and the breadth constraint nobody mentions. | RESULT July 2026 · 9 min read |
| Why the Standard VaR Number Understates Risk The 95% Value-at-Risk number on most risk dashboards is computed under one quiet assumption — that returns are Gaussian. They aren't. A correction Cornish and Fisher published in 1937 fixes the bias, and almost no production risk system uses it. Here is the math. | METHODS May 2026 · 9 min read |
| Why the Forecast Horizon Shouldn't Be Fixed Most quantitative models pick a fixed forecast window — 21 days, 60 days, one quarter — and never revisit the choice. We show why that's wrong, derive a horizon-from-data rule, and explain when stable regimes earn longer forecasts while fast-rotation regimes earn shorter ones. | RESULT May 2026 · 8 min read |
| Why Conviction Is a Risk Factor Classical theory predicts that strong directional consensus stabilizes markets. Twenty years of multi-asset data shows the opposite — and four independent statistical specifications agree. | RESULT April 2026 · 8 min read |
| How We Project Forward: Drift-Velocity Annualization The math behind the "projected portfolio value" panel on our model-portfolio page. Why we don't compound observed alpha geometrically — and the four-step formula you can replicate in a spreadsheet. | METHODS April 2026 · 7 min read |
| The Information Half-Life Problem in Wealth Management Why the time between generating an investment insight and acting on it is the single most important variable in portfolio management — and why most allocators have no idea how long their own decision cycle is. | ESSAY April 2026 · 12 min read |
| Why Field-Based Allocation Behaves Differently at Scale Structural advantages of models derived from stochastic-process structure over classical factor approaches, when applied to portfolio construction at institutional scale. | ESSAY March 2026 · 14 min read |
| Geographic Access and the Future of Portfolio Intelligence Institutional-grade allocation technology has been concentrated in a handful of zip codes for decades. Software is permanently changing that equation — and most distribution channels haven't noticed yet. | ESSAY March 2026 · 9 min read |
| Fee Compression and the Automation Imperative The gap between what wealth management costs to deliver and what clients are charged has never been wider. Automation is the only path that closes it without compromising quality. | RESULT February 2026 · 10 min read |