TSPP: A Unified Benchmarking Tool for Time-series Forecasting

TL;DR

A unified benchmarking framework is proposed that exposes the crucial modelling and machine learning decisions involved in developing time series forecasting models and demonstrates that carefully implemented deep learning models with minimal effort can rival gradient-boosting decision trees requiring extensive feature engineering and expert knowledge.

Abstract

While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment of machine learning solutions in real-world settings necessitates standardization throughout the entire pipeline. This need is particularly acute in time series forecasting, where diverse settings impede meaningful comparisons between various methods. To bridge this gap, we propose a unified benchmarking framework that exposes the crucial modelling and machine learning decisions involved in developing time series forecasting models. This framework fosters seamless integration of models and datasets, aiding both practitioners and researchers in their development efforts. We benchmark recently proposed models within this framework, demonstrating that carefully implemented deep learning models with minimal effort can rival gradient-boosting decision trees requiring extensive feature engineering and expert knowledge.

Figures (2)

• Figure 1: An overview of the pipeline standardization considered to guide model development and comparison. The framework is comprised of three main components, data, training, inference, which a tuner has access to for adequate exploration to ensure reliable model training.
• Figure 2: A flowchart of the framework, where orange shows components that can be changed by a hyperparameter optimizatoin algorithm.