Acceso usuarios
Xin Wang, Raja Zuraidah Binti Raja Mohd Rasi
This study focuses on the application of deep learning based consumer demand prediction algorithms in the C2M (consumer to manufacturer) supply chain model. As consumer demand for personalized products increases, accurately predicting consumer demand becomes crucial. Traditional prediction methods are limited by data processing capabilities and model complexity, making it difficult to cope with large-scale, high-dimensional consumer data. Deep learning provides new solutions for consumer demand prediction through its powerful feature extraction and pattern recognition capabilities. This study reviews existing literature and empirical analysis to explore the advantages and limitations of deep learning models in consumer demand forecasting, and evaluates the performance of different models in the C2M supply chain. The research results show that deep learning models have higher accuracy and flexibility in predicting consumer demand, and can handle complex nonlinear relationships. However, the performance of the model is affected by various factors such as data quality, model parameters, and training strategies, and further optimization and adjustment are needed. This study provides useful reference and inspiration for consumer demand prediction algorithms based on deep learning in the C2M supply chain, and supports further development in this field.
