A quantitative trading strategy backtester with an interactive dashboard. Enables users to implement, test, and visualise trading strategies using historical market data, featuring customisable parameters and key performance metrics. Developed with Python and Polars.

Production multi-agent trading platform with rigorous walk-forward validation. TSMOM momentum (1.097 Sharpe) + GEX regime filtering. Interactive CLI, autonomous trade lifecycle, daily scheduler. Alpaca integration. Built on Microsoft AutoGen. Research-driven approach with statistical validation. Educational - not financial advice.

Kiploks Engine is an open-source TypeScript engine for deterministic backtest and walk-forward analysis (WFA) of algorithmic trading strategies, published as @kiploks/engine-* packages under Apache 2.0.

Rigorous ML framework for alpha generation research. Demonstrates that apparent alpha from public market data is primarily overfitting. Key finding: IC flips from +0.036 to -0.084 when regularization is increased 100x.

Motor de decisión ML para trading cuantitativo con validación walk-forward anti-leakage, triple-barrier labeling, XGBoost + Optuna, risk management para cuentas micro, human-in-the-loop y paper trading. Sistema completo Python 3.11+ de producción para NAS100 M5 con gating de modelos, costos realistas y kill switch.

Hybrid stacking system: [MLP, VAE, LTSM XGBoost, LightGBM, CatBoost, RandomForest] -> LogReg

systematic trading strategies developed and validated using walk-forward analysis. The code is modular and structured for production backtesting.

ML investigation into whether public data can generate profitable betting signals on European football markets

Time series forecasting project predicting PM2.5 air quality using Linear Regression, AR, and ARMA models — from MongoDB data wrangling to model evaluation and visualization.

Quantum Geometry and Topological Regime Detection in Financial Markets

Time series and machine learning modeling to analyze and predict Seattle’s weather patterns using climate variables like precipitation, temperature, and wind.

Production-grade ML signal intelligence engine for quantitative trading. Powers real-time XGBoost inference across 100 S&P 500 tickers, 4-agent decision governance, algorithmic drift detection with automatic exposure scaling, and geopolitical risk overlay via live news APIs.

A leakage-controlled research framework for evaluating structured and semantic news signals in time-series asset return prediction using walk-forward validation.

This project focuses on forecasting US inflation trends using historical data. Since economic data is often erratic, this notebook explores the transformation of non-stationary series into stationary ones to build reliable predictive models.

Systematic ML options strategy using walk-forward XGBoost ensembles on 14 years of CBOE data | Sharpe 2.17 | Python, DuckDB, IBKR API

Time series forecasting of telecom revenue using Auto-ARIMA and walk-forward validation.

AI-native quantitative trading system — autonomous research, ML-driven signals, risk-gated execution, and self-improving strategy loops. Powered by Claude Code + MCP.