backtesting-frameworks
建構穩健的交易策略回測系統，處理前視偏誤、存活者偏誤和交易成本
中文翻譯
---
name: backtesting-frameworks
description: 為交易策略建構穩健的回測系統，正確處理前視偏誤（look-ahead bias）、存活者偏誤（survivorship bias）和交易成本。在開發交易演算法、驗證策略，或建構回測基礎設施時使用。
---
# 回測框架
建構穩健、可上線等級的回測系統，避開常見的陷阱，產出可靠的策略績效估計。
## 何時使用這個 Skill
- 開發交易策略的回測
- 建構回測基礎設施
- 驗證策略績效
- 避開常見的回測偏誤
- 實作 walk-forward 分析
- 比較不同的策略方案
## 核心概念
### 1. 回測偏誤
| 偏誤 | 說明 | 緩解方式 |
| ---------------- | ------------------------- | ----------------------- |
| **Look-ahead** | 使用未來的資訊 | Point-in-time 資料 |
| **Survivorship** | 只在存活下來的標的上測試 | 納入已下市的證券 |
| **Overfitting** | 對歷史資料做曲線擬合 | 樣本外測試 |
| **Selection** | 只挑好看的策略 | 預先註冊 |
| **Transaction** | 忽略交易成本 | 真實的成本模型 |
### 2. 正確的回測結構
```
Historical Data
│
▼
┌─────────────────────────────────────────┐
│ Training Set │
│ (Strategy Development & Optimization) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ Validation Set │
│ (Parameter Selection, No Peeking) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ Test Set │
│ (Final Performance Evaluation) │
└─────────────────────────────────────────┘
```
### 3. Walk-Forward 分析
```
Window 1: [Train──────][Test]
Window 2: [Train──────][Test]
Window 3: [Train──────][Test]
Window 4: [Train──────][Test]
─────▶ Time
```
## 詳細的實作範例與模式
詳細的章節（從 `## Implementation Patterns` 開始）放在 `references/details.md`。上面的導覽摘要不夠用時，再讀那個檔案。
## 最佳實務
### 該做的
- **用 point-in-time 資料** - 避免前視偏誤
- **納入交易成本** - 要有貼近真實的估計
- **做樣本外測試** - 一定要保留資料
- **用 walk-forward** - 不要只做 train/test
- **蒙地卡羅分析** - 了解不確定性
### 不該做的
- **不要過度擬合** - 限制參數數量
- **不要忽略存活者偏誤** - 要納入已下市的標的
- **不要隨便使用調整過的資料** - 要了解做了哪些調整
- **不要用完整歷史資料做最佳化** - 要保留測試集
- **不要忽略容量** - 市場衝擊很重要英文原文
---
name: backtesting-frameworks
description: Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
---
# Backtesting Frameworks
Build robust, production-grade backtesting systems that avoid common pitfalls and produce reliable strategy performance estimates.
## When to Use This Skill
- Developing trading strategy backtests
- Building backtesting infrastructure
- Validating strategy performance
- Avoiding common backtesting biases
- Implementing walk-forward analysis
- Comparing strategy alternatives
## Core Concepts
### 1. Backtesting Biases
| Bias | Description | Mitigation |
| ---------------- | ------------------------- | ----------------------- |
| **Look-ahead** | Using future information | Point-in-time data |
| **Survivorship** | Only testing on survivors | Use delisted securities |
| **Overfitting** | Curve-fitting to history | Out-of-sample testing |
| **Selection** | Cherry-picking strategies | Pre-registration |
| **Transaction** | Ignoring trading costs | Realistic cost models |
### 2. Proper Backtest Structure
```
Historical Data
│
▼
┌─────────────────────────────────────────┐
│ Training Set │
│ (Strategy Development & Optimization) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ Validation Set │
│ (Parameter Selection, No Peeking) │
└─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────┐
│ Test Set │
│ (Final Performance Evaluation) │
└─────────────────────────────────────────┘
```
### 3. Walk-Forward Analysis
```
Window 1: [Train──────][Test]
Window 2: [Train──────][Test]
Window 3: [Train──────][Test]
Window 4: [Train──────][Test]
─────▶ Time
```
## Detailed worked examples and patterns
Detailed sections (starting with `## Implementation Patterns`) live in `references/details.md`. Read that file when the navigation summary above is insufficient.
## Best Practices
### Do's
- **Use point-in-time data** - Avoid look-ahead bias
- **Include transaction costs** - Realistic estimates
- **Test out-of-sample** - Always reserve data
- **Use walk-forward** - Not just train/test
- **Monte Carlo analysis** - Understand uncertainty
### Don'ts
- **Don't overfit** - Limit parameters
- **Don't ignore survivorship** - Include delisted
- **Don't use adjusted data carelessly** - Understand adjustments
- **Don't optimize on full history** - Reserve test set
- **Don't ignore capacity** - Market impact matters