Livestream sales prediction based on an interpretable deep-learning model

• Published in: Scientific reports Vol. 14; no. 1; pp. 20594 - 13
• Main Authors: Wang, Lijun, Zhang, Xian
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 04.09.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1046; 639/705/117; Attention mechanism; Deep learning; Electronic commerce; Humanities and Social Sciences; Interpretability analysis; multidisciplinary; Predictions; Sales prediction; Science; Science (multidisciplinary); Streaming media; Deep learning; Sales prediction; Attention mechanism; Interpretability analysis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-71379-2

Although live streaming is indispensable, live-streaming e-business requires accurate and timely sales-volume prediction to ensure a healthy supply–demand balance for companies. Practically, because various factors can significantly impact sales results, the development of a powerful, interpretable model is crucial for accurate sales prediction. In this study, we propose SaleNet, a deep-learning model designed for sales-volume prediction. Our model achieved correct prediction results on our private, real operating data. The mean absolute percentage error (MAPE) of our model’s performance fell as low as 11.47% for a + 1.5-days forecast. Even for a 1-week forecast (+ 6 days), the MAPE was only 19.79%, meeting actual business needs and practical requirements. Notably, our model demonstrated robust interpretability, as evidenced by the feature contribution results which are consistent with prevailing research findings and industry expertise. Our findings provided a theoretical foundation for predicting shopping behavior in live-broadcast e-commerce and offered valuable insights for designing live-broadcast content and optimizing the user experience.