Optimal starting point for time series forecasting

TL;DR

This paper introduces OSP-TSP, a method to identify the optimal starting point in time series data, improving forecasting accuracy especially when data have structural breaks or concept drifts, by leveraging machine learning models.

Contribution

The paper proposes a novel approach to select the optimal starting point for time series forecasting, enhancing existing models' performance in the presence of data irregularities.

Findings

OSP-TSP outperforms using the complete dataset in predictions.

Combining OSP-TSP with existing models yields better accuracy.

Empirical results on M4 and real datasets validate effectiveness.

Abstract

Recent advances on time series forecasting mainly focus on improving the forecasting models themselves. However, when the time series data suffer from potential structural breaks or concept drifts, the forecasting performance might be significantly reduced. In this paper, we introduce a novel approach called Optimal Starting Point Time Series Forecast (OSP-TSP) for optimal forecasting, which can be combined with existing time series forecasting models. By adjusting the sequence length via leveraging the XGBoost and LightGBM models, the proposed approach can determine the optimal starting point (OSP) of the time series and then enhance the prediction performances of the base forecasting models. To illustrate the effectiveness of the proposed approach, comprehensive empirical analysis have been conducted on the M4 dataset and other real world datasets. Empirical results indicate that predictions based on the OSP-TSP approach consistently outperform those using the complete time series dataset. Moreover, comparison results reveals that combining our approach with existing forecasting models can achieve better prediction accuracy, which also reflect the advantages of the proposed approach.