All articles
financial compliance · regulation as code · continuous audit
Research note
Financial compliance is still assembled from spreadsheets, siloed point solutions, and headcount — and its central ritual is the point-in-time attestation: a consultant or an internal review examines the firm as it stand…
open source · data stack · DuckDB
Research note
Surveys of the open-source data ecosystem — Mezhanskiy's (2026) is the best current one — catalog a landscape of remarkable depth: four credible options per layer, a dozen layers, comparison tables with commit velocities…
agents · embedded databases · DuckDB
Research note
Note No. 11 described the memory our agents share; this note describes the data they don't. When we let language-model agents and batch validation jobs loose on our research infrastructure, the first casualty was the cen…
Obsidian · Claude Code · knowledge graph
Research note
This note describes the knowledge system behind everything else in this series — and, unusually for this series, you can copy it in ten minutes. The entire setup is a folder of markdown files (an Obsidian vault) plus one…
stop-loss · drawdown governance · volatility clustering
Research note
Having established in an earlier note that trade-level protection sells the right tail, we examined whether protection fares better one level up: a portfolio-level stop that halts the strategy after a sufficiently bad mo…
adoption criteria · effect size · resampling
Research note
Between the graveyard and the reference configuration there is a third place, and this note is about it. Several ideas in our recent research cycle produced effects we judge to be genuine — statistically present over lon…
short selling · anomaly asymmetry · limits to arbitrage
Research note
If a ranking signal is profitable at its top, the reflex conclusion is that it must be profitable — mirrored — at its bottom. We tested the reflex: a short portfolio built from the lowest-ranked names, run through the sa…
portfolio construction · breadth · signal weighting
Research note
We report, in qualitative terms, the outcome of a family of portfolio-construction experiments: sweeping the number of names held, replacing rank-based selection with signal-strength weighting, substituting volatility-sc…
earnings announcements · scheduled news · overnight risk
Research note
A systematic strategy that holds positions through scheduled information events invites an obvious refinement: step aside on the dangerous nights. We tested the refinement. Excluding event nights removed a material fract…
holding period · parameter sweeps · in-sample drift
Research note
A recurring temptation in short-horizon strategy research is the holding-period extension: sweep the exit clock, observe that longer holds earn more in the backtest, and conclude that the strategy has been leaving perfor…
combinatorial cross-validation · purging · probability of backtest overfitting
Research note
We describe the validation protocol that governs what enters our reference configuration: combinatorially purged cross-validation with kill criteria fixed before any test is run. The protocol's defining property is that…
noise floor · random baselines · null model
Research note
Before any candidate signal earns a place in our validation queue, it must clear a threshold most public backtests never compute: it must outperform a randomized version of itself. We describe this "noise floor" practice…
exit rules · profit concentration · right tail
Research note
We examine a family of protective exit overlays — partial profit-taking, trailing stops, breakeven floors, and their laddered combinations — applied, in long-sample backtests, to a systematic strategy. Every design teste…
negative results · backtesting · research process
Research note
Over an extended period we subjected a large number of candidate trading signals to a fixed validation protocol. The overwhelming majority did not survive. We argue that this mortality rate is not evidence of failure but…
Medium
Are Quantum Concepts Just Theory — or the Next Breakthrough in Market Prediction? Introduction: What If Markets Follow Nature’s Laws More Than We Think? We typically interpret financial markets through psychology, econom…
stock-market · finance · openai
Medium
Imagine a trading bot that not only executes trades but also learns from its past performance , refining its strategies over time without human intervention. By leveraging OpenAI’s o1 model — a reasoning AI that thinks b…
machine-learning · coding · data-science
Medium
How AlexNet Transformed Artificial Intelligence In the world of AI, few innovations have reshaped the landscape as fundamentally as AlexNet. When it emerged in 2012, AlexNet introduced groundbreaking advancements in deep…