Architecture and algorithms of a CSCW-based sales forecasting system

The sales forecasting is an important task that it maintains a good relationship with customers in the modem enterprise resource planning system and the supply chain management system. This article designs a distributional and layered cooperative sales forecasting system based on CSCW and analyzes cooperative architecture of this system. We use the neural network theory to get the local level sales forecasting, make the company strategy according to the data fusion theory, implement the high level sales forecasting, and infer a suitable forecasting algorithm for this system. The theoretical analysis and the experimental result show that the design of this system and the forecasting algorithm can substitute the traditional central sales forecasting one and get the accurate result.