Detect backtest overfitting & multiple testing: Deflated Sharpe Ratio, PBO (CSCV), purged/embargoed CV, Harvey-Liu haircut. Research/education only, not investment advice.
-
Updated
Jul 16, 2026 - Python
FFFF
Detect backtest overfitting & multiple testing: Deflated Sharpe Ratio, PBO (CSCV), purged/embargoed CV, Harvey-Liu haircut. Research/education only, not investment advice.
End-to-end ML system for prediction market trading — 521K markets, 78 features, 7 model architectures, walk-forward validation, live VPS A/B across 7 configs. Honest research-stop on alpha decay (NO-GO verdict). AFML methodology: Purged K-Fold, Deflated Sharpe Ratio, meta-labeling, focal loss.
Deflated Sharpe Ratio
An independent, power-aware falsification referee for quantitative finance claims. Multiple-testing-aware and self-calibrating; a referee for research, not a trading system.
Backtest overfitting audit for factor research: probability of backtest overfitting (PBO), deflated Sharpe ratio, point-in-time data, purged walk-forward. Searches published factor libraries and reports what actually survived costs.
Living technical reference for Disuza Quantitative — private quantitative research laboratory, Madrid, Spain. Architecture, anti-overfit methodology (CPCV / DSR / PBO per López de Prado), regulatory posture. Source code proprietary.
Empirical asset-pricing research framework (Python) with formal overfitting control — Combinatorial Purged CV, Deflated Sharpe Ratio, Probability of Backtest Overfitting. ~20 pre-registered experiments on a survivorship-free, point-in-time S&P 500 universe, with an honest public kill-log.
Negative-results & reproducibility case study on free crypto/gold data: no ML/rule/funding/basis strategy beats costs. An independent 7-gate audit + rigorous DSR/PBO/Reality-Check statistics catch three inflated Sharpe claims.
Open-source quantitative portfolio optimization, risk analytics, and anti-overfitting strategy certification in Python. The research core of the CPZAI systematic trading operating system.
A Python package for quantitative portfolio metrics calculations, including Deflated Sharpe Ratio (DSR)
Multiple-testing / Deflated Sharpe analysis on 160 BTC rules (DSR = 0.70, fail).
Multi-agent evolutionary strategy discovery with quality-diversity and NSGA-III search, evaluated against WRDS CRSP equities and Yahoo Finance futures data.
Agentic multi-strategy hedge fund: PatchTST forecasts, 4-agent LangGraph debate, CPCV-OOS + DSR validation, HRP with Ledoit-Wolf shrinkage. 10-year OOS Sharpe=0.766.
Torch-free honest-statistics kernel (Deflated Sharpe, PBO, Diebold-Mariano, HAC, purged walk-forward) — the single source of truth behind a 19-project ML+Finance portfolio
策略照妖鏡 — 客戶端誠實回測驗證器。上傳你的回測報酬,一整套學界統計檢定告訴你這個 edge 是真的還是過擬合。Pyodide 瀏覽器內跑,資料不上傳。
Prove a trading backtest is real without revealing the strategy. Zero-knowledge (STARK) verification of backtest honesty: enforce the Deflated Sharpe Ratio, committed trial ledger, in-circuit. Reproduce a live credential to the digit.
Add a description, image, and links to the deflated-sharpe-ratio topic page so that developers can more easily learn about it.
To associate your repository with the deflated-sharpe-ratio topic, visit your repo's landing page and select "manage topics."