Graph Neural Networks for Model Recommendation using Time Series Data

TL;DR

This paper introduces a Graph Neural Network-based architecture to recommend suitable models for time series forecasting, demonstrating superior performance over existing methods across multiple datasets.

Contribution

The paper proposes a novel GNN-based approach for model recommendation in time series forecasting, outperforming state-of-the-art techniques including meta-learning.

Findings

GNN-based method outperforms baseline models

Approach validated on three datasets

Superior to over sixteen competing techniques

Abstract

Time series prediction aims to predict future values to help stakeholders make proper strategic decisions. This problem is relevant in all industries and areas, ranging from financial data to demand to forecast. However, it remains challenging for practitioners to select the appropriate model to use for forecasting tasks. With this in mind, we present a model architecture based on Graph Neural Networks to provide model recommendations for time series forecasting. We validate our approach on three relevant datasets and compare it against more than sixteen techniques. Our study shows that the proposed method performs better than target baselines and state of the art, including meta-learning. The results show the relevancy and suitability of GNN as methods for model recommendations in time series forecasting.