A generalized financial time series forecasting model based on automatic feature engineering using genetic algorithms and support vector machine

TL;DR

This paper introduces a novel approach combining genetic algorithms and support vector machines to optimize feature extraction in financial time series forecasting, enhancing prediction accuracy and trading performance.

Contribution

It presents an embedded genetic algorithm for automatic time window optimization tailored to each technical indicator, improving forecasting models over traditional methods.

Findings

Optimized time windows improve trading returns.

The model generalizes well across different stock data.

Enhanced prediction accuracy compared to default settings.

Abstract

We propose the genetic algorithm for time window optimization, which is an embedded genetic algorithm (GA), to optimize the time window (TW) of the attributes using feature selection and support vector machine. This GA is evolved using the results of a trading simulation, and it determines the best TW for each technical indicator. An appropriate evaluation was conducted using a walk-forward trading simulation, and the trained model was verified to be generalizable for forecasting other stock data. The results show that using the GA to determine the TW can improve the rate of return, leading to better prediction models than those resulting from using the default TW.