Every public repository featured on this site, the paper reproducibility packages, the article companion code, the single-project repos, and the walk-forward backtesting framework, plus the self-contained toolkit core of the in-flight Topology program. Counts are source lines only.
The López-de-Prado Research Review program, per-study Python pipelines that reproduce and forward-test the methods from Advances in Financial Machine Learning, with evaluation, forward-value scoring and table generation. Opens at completion of the review.
The self-contained core of the Topology of Strategy-Space program, the importable Python package (I/O, strategy-space, topology, evaluation, the baseline-model zoo, clustering, the CLI apps, the figure theme). Open-sources at program completion; the program's ~43k further lines of experiment scaffolding, figure scripts and tests aren't counted here.
Reproducibility package for the DEX tradeability paper, the long-only AMM backtester with realistic per-fill costs, the bar-shuffled null control, the walk-forward evaluation and the cross-sectional learner, across 4,990 pairs on 27 chains.
Reproducibility engine for the market-making adverse-selection paper, the event-driven maker-fill simulator, the true-sign markout decomposition, the cost model, and the significance toolkit, with correctness tests on bundled fixtures.
Reproducibility package for the Monte-Carlo filter-evaluation paper, analysis scripts (Python / Rust / R), corrected aggregate tables, and a self-contained reproducer of the floating-point summation-order pitfall documented in the May 2026 revision.
Reproducibility package for the World Cup attention-markets paper, the event-study and null-control pipeline across 11 instruments and five market structures, with the per-nation cuts and the multiple-testing correction.
Reproducibility package for the crypto adverse-selection paper: the entry-markout decomposition, the reference fill rule, clustered inference with an abstention rule, the ten coin-day panels and a command-line tool that applies the decomposition and abstention rule to any book and tape carrying a true aggressor flag.
The walk-forward backtesting & robustness framework, the original Python build.
The Rust port of the backtesting framework, the production build.
Pre-registered study of parameter-surface stability, smooth ridges vs brittle spikes.
Empirical variance decomposition of in-sample → out-of-sample Sharpe degradation.
Geometry of strategy space, dimensionality and manifold structure.
Latent regime classification on market data, then regime-conditional strategy selection.
Extreme-value analysis of cross-asset tail dependence, peaks-over-threshold with GPD fits.
Robust portfolio construction over a strategy universe.
Population-level statistics over a universe of algorithmic trading strategies.
Random-matrix analysis of strategy correlation matrices, noise vs signal decomposition.
Reproducible synthetic demos behind the article “The signal is collective”.
Higher Criticism under dependence + Model-X knockoffs for FDR-controlled strategy selection.
Persistent homology of strategy space, topological data analysis on strategy populations.
Cross-asset correlation cube, pairwise correlations between asset return series.
Source lines only, READMEs, methodology notes, data files and configs aren't counted. 92,704 lines sit in the 20 public repos. Two further codebases open-source at program completion: the López-de-Prado Research Review pipelines (28,753 lines) and the Topology toolkit core (19,210 lines). The Topology program's ~43,000 further lines of experiment scaffolding, figure scripts and tests, and its Rust accelerator crates, are not counted here.
