Momentum and Trend Following

Under development

This lesson is part of the course scaffold and is being actively written. The learning objectives and outline below define its final scope.

Learning objectives

By the end of this lesson you will be able to:

• State time-series momentum as a testable hypothesis and implement a sign-of-past-return system on real futures or equity index data.
• Implement moving-average and channel trend filters and breakout entries, and compare their trade profiles (hit rate, skew, average holding period).
• Map performance across a grid of lookback lengths and distinguish a robust parameter region from a curve-fit point.
• Summarize the leading behavioral and risk-based explanations for momentum persistence and their implications for when the effect should weaken.

Outline

1. The momentum hypothesis — the evidence across assets and decades
2. Time-series momentum — sign-of-past-return systems and their implementation
3. Trend filters — moving averages, crossovers, and channel filters
4. Breakout systems — Donchian-style entries, exits, and stop placement
5. Lookback selection — parameter surfaces, robustness vs overfitting
6. The trade profile — hit rate, payoff skew, and drawdown character of trend systems
7. Why momentum persists — behavioral and risk-based explanations

Prerequisites

• Part III — Time Series