English

MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation

Machine Learning 2022-09-09 v2 Artificial Intelligence

Abstract

Multi-horizon probabilistic time series forecasting has wide applicability to real-world tasks such as demand forecasting. Recent work in neural time-series forecasting mainly focus on the use of Seq2Seq architectures. For example, MQTransformer - an improvement of MQCNN - has shown the state-of-the-art performance in probabilistic demand forecasting. In this paper, we consider incorporating cross-entity information to enhance model performance by adding a cross-entity attention mechanism along with a retrieval mechanism to select which entities to attend over. We demonstrate how our new neural architecture, MQRetNN, leverages the encoded contexts from a pretrained baseline model on the entire population to improve forecasting accuracy. Using MQCNN as the baseline model (due to computational constraints, we do not use MQTransformer), we first show on a small demand forecasting dataset that it is possible to achieve ~3% improvement in test loss by adding a cross-entity attention mechanism where each entity attends to all others in the population. We then evaluate the model with our proposed retrieval methods - as a means of approximating an attention over a large population - on a large-scale demand forecasting application with over 2 million products and observe ~1% performance gain over the MQCNN baseline.

Keywords

Cite

@article{arxiv.2207.10517,
  title  = {MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation},
  author = {Sitan Yang and Carson Eisenach and Dhruv Madeka},
  journal= {arXiv preprint arXiv:2207.10517},
  year   = {2022}
}

Comments

Accepted at KDD2022 Workshop on Mining and Learning from Time Series

R2 v1 2026-06-25T01:07:10.812Z