An Empirical Evaluation of DeepAR for Univariate Time Series Forecasting

• Type: Article in International Conference Proceedings Book
• Date: 2024

Authors

Gomes, RU (Author) Other; Carlos Soares (Author) FEUP; reis, lp (Author) FEUP

Conference proceedings International

Title: Progress in Artificial Intelligence - 23rd EPIA Conference on Artificial Intelligence, EPIA 2024, Viana do Castelo, Portugal, September 3-6, 2024, Proceedings, Part III

Pages: 188-199

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

Viana do Castelo, 3 September 2024 through 6 September 2024

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-017-CQ4

DOI: 10.1007/978-3-031-73503-5_16

Abstract (EN): DeepAR is a popular probabilistic time series forecasting algorithm. According to the authors, DeepAR is particularly suitable to build global models using hundreds of related time series. For this reason, it is a common expectation that DeepAR obtains poor results in univariate forecasting [10]. However, there are no empirical studies that clearly support this. Here, we compare the performance of DeepAR with standard forecasting models to assess its performance regarding 1 step-ahead forecasts. We use 100 time series from the M4 competition to compare univariate DeepAR with univariate LSTM and SARIMAX models, both for point and quantile forecasts. Results show that DeepAR obtains good results, which contradicts common perception. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 11