This is a backtesting demo in Python. Different moving average prices are used to make buy and sell decisions. A Jupyter notebook version is for serial mode. while py version is for multiprocessing. A version for GPU has been tried, but not successful.
Exploratory index-rebalancing data collection and backtesting research with Python, notebooks, and historical S&P materials.
Notebooks on crypto EDA, strategy backtesting, RSI and ML-based stock price prediction.
Repository for pair trading research using python
Analyze historical market data using Jupyter Notebooks
Panel time-series forecasting notebooks (daily sales across stores × items). Clean validation (holdout + rolling-origin backtest), strong statistical baselines (SARIMAX/TBATS/ARIMA), and automated models (AutoTS), with optional Prophet/Darts/NeuralProphet. Primary metric: SMAPE.
Companion notebook for the post “Algo Backtests Are Lying to You.”
Cross-sectional research study of vanilla technical indicator strategies across Indian equities using Python and Jupyter notebooks.
Research notebooks for MASI downside-risk modeling, VaR/ES backtesting, GARCH benchmarks, and hybrid LSTM risk forecasting.
Mean reversion signal backtests and analysis with a Jupyter notebook and CSV signal data.
A modular quantitative trading environment for designing, backtesting, and simulating strategies (Mean Reversion, Momentum, Pairs Trading) in real-time. Features an event-driven backtesting engine, statistical research notebooks, a FastAPI backend, a dynamic frontend dashboard, and full Docker containerization.
2026 - 2025 - Multi-Broker Algorithmic Trading Platform - Juypter Notebook Learning
面向中国本科生与研究生的金融数据科学教材（含可在线运行的 notebook）
Alpha 因子挖掘系统 v3.0 — 模块化自动化因子挖掘平台 (表达式/遗传编程/深度学习三模式, A股+美股, CLI+Streamlit+Notebook)
Is your backtest overfit? CSCV/PBO, Deflated Sharpe Ratio and MinBTL implemented and verified in executed Jupyter notebooks
End-to-end quant research pipeline for 10 commodities — technical indicators, VADER news sentiment, 5 backtested rule-based strategies, and an XGBoost price-prediction model with simulated buy/sell execution and out-of-sample PnL tracking. Built in a single Jupyter notebook.
End-to-end Python platform for portfolio construction, optimization, and risk budgeting, featuring state-of-the-art models (Markowitz, Black–Litterman, HRP, CVaR), robust covariance estimators, transaction cost modeling, scenario analysis, and walk-forward backtesting. Includes a professional Streamlit UI, REST API, and research-grade notebooks.
Khóa học Quant Trading tiếng Việt: 14 module + 14 notebook + backtesting/ML + dữ liệu thật. Chạy được, tái lập, offline-first.
Equity and options research notebooks: risk analytics, Black-Scholes pricing with numerically verified Greeks, walk-forward signal evaluation, and backtests that report negative results.
Point-in-time A-share factor research with M2 timing and ROE stock selection, including bias controls, transaction costs, reproducible notebooks, and tests.
To associate your repository with the backtesting topic, visit your repo's landing page and select "manage topics."