Variational Autoencoder-Based Framework for Retail Sales Prediction
Accurate retail sales prediction is crucial for supporting the intelligent operations and management of a retail sales organization. For example, intelligent inventory replenishment based on forecasted sales can help reduce inventory backlog and turnover periods, improving operational efficiency. Th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10758624/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536157796532224 |
|---|---|
| author | Fuyu Li Lei Wang Bo Jin |
| author_facet | Fuyu Li Lei Wang Bo Jin |
| author_sort | Fuyu Li |
| collection | DOAJ |
| description | Accurate retail sales prediction is crucial for supporting the intelligent operations and management of a retail sales organization. For example, intelligent inventory replenishment based on forecasted sales can help reduce inventory backlog and turnover periods, improving operational efficiency. This paper presents a variational autoencoder (VAE)-based framework for retail sales prediction, with three unique contributions. First, the framework leverages the clustering properties of the VAE in latent space to enhance feature learning. The data clustering module integrates correlation information across different samples to effectively extract both local and global features.Second, we design a restructured VAE to capture high-level local and global features essential for sales prediction. The use of multiple self-adaptive priors and corresponding posteriors diversifies the posterior space, facilitating effective learning of characteristic distributions across samples. This approach enhances the extraction of useful features from the original data. Finally, to mitigate abnormal prediction outcomes, we incorporate prior knowledge to adjust predictions that may be affected by the model’s limited fitting capacity or insufficient training data in certain cases. Extensive experiments conducted in collaboration with a national retail chain in China demonstrate that our method outperforms state-of-the-art baseline methods and is practical for various operational and management tasks. |
| format | Article |
| id | doaj-art-19f44838a59d4737abab7aad2f79adca |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-19f44838a59d4737abab7aad2f79adca2025-01-15T00:01:20ZengIEEEIEEE Access2169-35362024-01-011219639119640210.1109/ACCESS.2024.350265710758624Variational Autoencoder-Based Framework for Retail Sales PredictionFuyu Li0Lei Wang1https://orcid.org/0009-0004-0639-8870Bo Jin2https://orcid.org/0000-0002-4094-7499Dalian University of Foreign Languages, Dalian, ChinaDalian University of Technology, Dalian, ChinaDalian University of Technology, Dalian, ChinaAccurate retail sales prediction is crucial for supporting the intelligent operations and management of a retail sales organization. For example, intelligent inventory replenishment based on forecasted sales can help reduce inventory backlog and turnover periods, improving operational efficiency. This paper presents a variational autoencoder (VAE)-based framework for retail sales prediction, with three unique contributions. First, the framework leverages the clustering properties of the VAE in latent space to enhance feature learning. The data clustering module integrates correlation information across different samples to effectively extract both local and global features.Second, we design a restructured VAE to capture high-level local and global features essential for sales prediction. The use of multiple self-adaptive priors and corresponding posteriors diversifies the posterior space, facilitating effective learning of characteristic distributions across samples. This approach enhances the extraction of useful features from the original data. Finally, to mitigate abnormal prediction outcomes, we incorporate prior knowledge to adjust predictions that may be affected by the model’s limited fitting capacity or insufficient training data in certain cases. Extensive experiments conducted in collaboration with a national retail chain in China demonstrate that our method outperforms state-of-the-art baseline methods and is practical for various operational and management tasks.https://ieeexplore.ieee.org/document/10758624/Abnormal predictions calibratingregression taskretail sales predictionvariational autoencoder |
| spellingShingle | Fuyu Li Lei Wang Bo Jin Variational Autoencoder-Based Framework for Retail Sales Prediction IEEE Access Abnormal predictions calibrating regression task retail sales prediction variational autoencoder |
| title | Variational Autoencoder-Based Framework for Retail Sales Prediction |
| title_full | Variational Autoencoder-Based Framework for Retail Sales Prediction |
| title_fullStr | Variational Autoencoder-Based Framework for Retail Sales Prediction |
| title_full_unstemmed | Variational Autoencoder-Based Framework for Retail Sales Prediction |
| title_short | Variational Autoencoder-Based Framework for Retail Sales Prediction |
| title_sort | variational autoencoder based framework for retail sales prediction |
| topic | Abnormal predictions calibrating regression task retail sales prediction variational autoencoder |
| url | https://ieeexplore.ieee.org/document/10758624/ |
| work_keys_str_mv | AT fuyuli variationalautoencoderbasedframeworkforretailsalesprediction AT leiwang variationalautoencoderbasedframeworkforretailsalesprediction AT bojin variationalautoencoderbasedframeworkforretailsalesprediction |