Improving Accuracy Without Losing Interpretability: A ML Approach for Time Series Forecasting

TL;DR

This paper introduces the W-R hybrid algorithm that combines decomposition and machine learning to enhance time series forecasting accuracy while maintaining interpretability, validated through extensive experiments and real-world applications.

Contribution

The paper proposes the W-R algorithm, a novel hybrid method that replaces additive models with weighted combinations and modifies all components simultaneously, improving accuracy without sacrificing interpretability.

Findings

W-R outperforms existing benchmarks in accuracy.

8.76% improvement on JD.com sales forecasts.

77.99% improvement on electricity load dataset.

Abstract

In time series forecasting, decomposition-based algorithms break aggregate data into meaningful components and are therefore appreciated for their particular advantages in interpretability. Recent algorithms often combine machine learning (hereafter ML) methodology with decomposition to improve prediction accuracy. However, incorporating ML is generally considered to sacrifice interpretability inevitably. In addition, existing hybrid algorithms usually rely on theoretical models with statistical assumptions and focus only on the accuracy of aggregate predictions, and thus suffer from accuracy problems, especially in component estimates. In response to the above issues, this research explores the possibility of improving accuracy without losing interpretability in time series forecasting. We first quantitatively define interpretability for data-driven forecasts and systematically review the existing forecasting algorithms from the perspective of interpretability. Accordingly, we propose the W-R algorithm, a hybrid algorithm that combines decomposition and ML from a novel perspective. Specifically, the W-R algorithm replaces the standard additive combination function with a weighted variant and uses ML to modify the estimates of all components simultaneously. We mathematically analyze the theoretical basis of the algorithm and validate its performance through extensive numerical experiments. In general, the W-R algorithm outperforms all decomposition-based and ML benchmarks. Based on P50_QL, the algorithm relatively improves by 8.76% in accuracy on the practical sales forecasts of JD.com and 77.99% on a public dataset of electricity loads. This research offers an innovative perspective to combine the statistical and ML algorithms, and JD.com has implemented the W-R algorithm to make accurate sales predictions and guide its marketing activities.