Algorithmic Quant
Explore quantitative trading strategies, backtesting frameworks, and factor models — from moving-average systems to machine-learning stock selection, codifying trading decisions with data.
6 articles
Trend-Following Strategy Backtesting Framework Based on Three-Stage Data Isolation and Walk-Forward Rolling Validation
Backtesting framework documentation (specifically designed for trend-following trading strategies)
The Complete Guide to 10 Python AI Libraries: Every Stage of a Quant Trading Workflow
A one-stop guide to the positioning of 10 core Python AI libraries in quantitative trading: NumPy for numerical computing, pandas for financial time series, scikit-learn for traditional ML, XGBoost/LightGBM as the workhorses for tabular data, PyTorch for research-oriented deep learning, TensorFlow/Keras for production deployment, and Jupyter as the research environment—plus practical use cases for statsmodels, spaCy, Transformers, backtrader, vectorbt, ccxt, MetaTrader5, and TA-Lib. Includes typical installation combinations and a decision tree.
How to Draw Support and Resistance Levels: A Complete Guide from Basics to Application
Support and resistance form the foundation of all technical analysis. This article teaches you how to correctly identify, draw, and apply support and resistance levels, avoid common drawing mistakes, and build systematic rules by combining quantitative trading concepts.
MT5 Complete Guide: Charts, Order Placement, TSL, Alerts, and Troubleshooting
From MT5 installation and interface navigation to order types, TSL trailing stop loss, chart drawing tools, price alerts, and common troubleshooting—an essential MT5 guide for gold intraday traders.
ICT Order Block Signal Engine Complete Tutorial: From Theory to 10 Enhancements, From Backtesting to Live Alignment
A complete tutorial on implementing ICT Order Block trading theory using vectorized Python, paired with 10 enhancements that go beyond the original PineScript (bidirectional OB, mitigation tracking, ATR-based dynamic SL, volume confirmation, Displacement, FVG, EMA trend filter, session filter, freshness scoring, zone scoring). Covers the Brain + Hands hybrid architecture, the full StrategyConfig parameter set, and the consistency guarantees between BacktestEngine and LiveEngine.
Introduction to Factor Investing: Data-Driven Secrets to Outperforming the Market
An overview of the core concepts behind multi-factor models, covering factors such as value, momentum, and quality, and how data-driven stock selection works.