What is the difference between event-driven and vectorized backtesting in this skill?

Event-driven models simulate realistic trade execution bar-by-bar (ideal for complex logic), while vectorized models use array operations for significantly faster processing of simple strategies.

Can this skill calculate risk-adjusted performance metrics?

Yes, it includes built-in patterns for calculating Sharpe ratios, annual volatility, maximum drawdown, win rates, and total returns.

How does this skill help avoid backtesting biases?

It provides specific implementation patterns for point-in-time data handling to prevent look-ahead bias and utilizes patterns for including delisted securities to mitigate survivorship bias.

Does it support strategy optimization?

It includes implementation patterns for walk-forward optimization, which helps validate strategy parameters across rolling historical windows to prevent curve-fitting and overfitting.

Quantitative Backtesting Frameworks

Name: Quantitative Backtesting Frameworks
Author: Tahir-yamin

byTahir-yamin

•

データサイエンスとML

Builds robust, production-grade backtesting systems for trading strategies with specialized handling of biases and transaction costs.

概要

This skill provides specialized guidance and implementation patterns for developing reliable trading strategy backtests using Claude Code. It focuses on eliminating common pitfalls like look-ahead and survivorship bias while offering both high-performance vectorized backtesters for speed and event-driven architectures for realistic simulation. Ideal for quantitative researchers and financial engineers, it enables rigorous strategy validation through walk-forward analysis, realistic slippage modeling, and comprehensive performance metric calculation to ensure historical results translate to live trading performance.

主な機能

Implements event-driven architectures for realistic trade execution simulation
Mitigates common biases including look-ahead, survivorship, and overfitting
3 GitHub stars
Calculates essential risk metrics like Sharpe ratio, max drawdown, and win rate
Automates walk-forward optimization and out-of-sample testing
Provides high-speed vectorized backtesting patterns for rapid strategy iteration

ユースケース

Developing custom backtesting infrastructure with realistic transaction cost models
Optimizing strategy parameters using robust walk-forward analysis techniques
Validating algorithmic trading strategies against historical market data

概要

主な機能

Implements event-driven architectures for realistic trade execution simulation
Mitigates common biases including look-ahead, survivorship, and overfitting
3 GitHub stars
Calculates essential risk metrics like Sharpe ratio, max drawdown, and win rate
Automates walk-forward optimization and out-of-sample testing
Provides high-speed vectorized backtesting patterns for rapid strategy iteration

ユースケース

Developing custom backtesting infrastructure with realistic transaction cost models
Optimizing strategy parameters using robust walk-forward analysis techniques
Validating algorithmic trading strategies against historical market data