Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality
In this study, we address a demanding time series forecasting problem that deals simultaneously with the following: (1) intermittent time series, (2) multi-step ahead forecasting, (3) time series with multiple seasonal periods, and (4) performance measures for model selection across multiple time se...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2022-09-01
|
| Series: | Data Science and Management |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666764922000273 |
| _version_ | 1828032409134694400 |
|---|---|
| author | Martim Sousa Ana Maria Tomé José Moreira |
| author_facet | Martim Sousa Ana Maria Tomé José Moreira |
| author_sort | Martim Sousa |
| collection | DOAJ |
| description | In this study, we address a demanding time series forecasting problem that deals simultaneously with the following: (1) intermittent time series, (2) multi-step ahead forecasting, (3) time series with multiple seasonal periods, and (4) performance measures for model selection across multiple time series. Current literature deals with these types of problems separately, and no study has dealt with all these characteristics simultaneously. To fill this knowledge gap, we begin by reviewing all the necessary existing literature relevant to this case study with the goal of proposing a framework capable of achieving adequate forecast accuracy for such a complex problem. Several adaptions and innovations have been conducted, which are marked as contributions to the literature. Specifically, we proposed a weighted average forecast combination of many cutting-edge models based on their out-of-sample performance. To gather strong evidence that our ensemble model works in practice, we undertook a large-scale study across 98 time series, rigorously assessed with unbiased performance measures, where a week seasonal naïve was set as a benchmark. The results demonstrate that the proposed ensemble model achieves eye-catching forecasting accuracy. |
| first_indexed | 2024-04-10T15:04:58Z |
| format | Article |
| id | doaj.art-16767e5e15d24a9cb874fcf368aa6eaa |
| institution | Directory Open Access Journal |
| issn | 2666-7649 |
| language | English |
| last_indexed | 2024-04-10T15:04:58Z |
| publishDate | 2022-09-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Data Science and Management |
| spelling | doaj.art-16767e5e15d24a9cb874fcf368aa6eaa2023-02-15T04:28:55ZengKeAi Communications Co. Ltd.Data Science and Management2666-76492022-09-0153137148Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonalityMartim Sousa0Ana Maria Tomé1José Moreira2Corresponding author.; IEETA/DETI, University of Aveiro, Aveiro, 3810-193, PortugalIEETA/DETI, University of Aveiro, Aveiro, 3810-193, PortugalIEETA/DETI, University of Aveiro, Aveiro, 3810-193, PortugalIn this study, we address a demanding time series forecasting problem that deals simultaneously with the following: (1) intermittent time series, (2) multi-step ahead forecasting, (3) time series with multiple seasonal periods, and (4) performance measures for model selection across multiple time series. Current literature deals with these types of problems separately, and no study has dealt with all these characteristics simultaneously. To fill this knowledge gap, we begin by reviewing all the necessary existing literature relevant to this case study with the goal of proposing a framework capable of achieving adequate forecast accuracy for such a complex problem. Several adaptions and innovations have been conducted, which are marked as contributions to the literature. Specifically, we proposed a weighted average forecast combination of many cutting-edge models based on their out-of-sample performance. To gather strong evidence that our ensemble model works in practice, we undertook a large-scale study across 98 time series, rigorously assessed with unbiased performance measures, where a week seasonal naïve was set as a benchmark. The results demonstrate that the proposed ensemble model achieves eye-catching forecasting accuracy.http://www.sciencedirect.com/science/article/pii/S2666764922000273Multi-step ahead forecastingScale-independent performance measuresNeural networksTBATSWeighted average ensembleProphet |
| spellingShingle | Martim Sousa Ana Maria Tomé José Moreira Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality Data Science and Management Multi-step ahead forecasting Scale-independent performance measures Neural networks TBATS Weighted average ensemble Prophet |
| title | Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| title_full | Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| title_fullStr | Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| title_full_unstemmed | Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| title_short | Long-term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| title_sort | long term forecasting of hourly retail customer flow on intermittent time series with multiple seasonality |
| topic | Multi-step ahead forecasting Scale-independent performance measures Neural networks TBATS Weighted average ensemble Prophet |
| url | http://www.sciencedirect.com/science/article/pii/S2666764922000273 |
| work_keys_str_mv | AT martimsousa longtermforecastingofhourlyretailcustomerflowonintermittenttimeserieswithmultipleseasonality AT anamariatome longtermforecastingofhourlyretailcustomerflowonintermittenttimeserieswithmultipleseasonality AT josemoreira longtermforecastingofhourlyretailcustomerflowonintermittenttimeserieswithmultipleseasonality |