Forecasting the FTSE 100 with Linear Regression on Index Constituents

Summary

The article describes an MQL5 forecasting model for the FTSE 100 that uses the index and ten large constituent stocks as inputs. It standardizes the historical input series with means and standard deviations, then fits multiple linear regression to predict the index close twenty steps ahead. The author notes that linear regression can extrapolate beyond observed input groupings, unlike the decision-tree behavior described in the article, and outlines a planned Expert Advisor that uses the forecast in trading and portfolio routines.

The text includes implementation fragments and references forward and backtesting figures, but the supplied material gives no numerical performance results or enough detail to assess the tests. It also leaves important questions about time alignment, validation, transaction costs, and how the model output translates into reliable trades. The approach is therefore a modeling example, not evidence that constituent-based forecasts produce an enduring edge or a well-controlled portfolio.

Key ideas

• The model uses standardized prices for the FTSE 100 and ten constituent stocks as predictors.
• Multiple linear regression is fitted to forecast the index close twenty steps ahead.
• The article distinguishes regression extrapolation from the group-average predictions associated with decision trees.
• The MQL5 implementation is connected to an Expert Advisor and portfolio routines.
• The provided text does not give numerical test results or establish predictive trading value.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.