Autocorrelation Price Forecasting for Long-Only Take-Profit Trades
Summary
This strategy uses autocorrelation to flag cyclical behavior in closing prices, then applies a linear regression to recent returns to estimate a future price move. When the estimated gain exceeds a configurable threshold and no trade is open, it enters a long position and places a limit take-profit at the forecast price. Order quantity is calculated from a chosen percentage of initial capital. The described implementation is long-only and has no stop-loss.
The document supplies example parameters and backtesting assumptions, but it reports no measured returns, drawdowns, or validation results. Its forecast depends on detected cycles and the regression estimate; these may not persist or predict future prices reliably. Without a stop-loss, a falling market or inaccurate forecast can leave losses open, and the position sizing and backtest assumptions should be assessed against realistic costs and risk limits before use.
Key ideas
- Autocorrelation is used to identify recurring behavior in closing prices.
- A regression on recent returns supplies the move used to estimate a future price.
- A long trade opens only when forecast gain exceeds a threshold and no trade is open.
- The exit is a limit take-profit tied to the forecast, with no stop-loss.
- The document provides strategy settings and an example use case but no reported performance results.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.