Research And Implementation Of Automobile Parts Sales Forecasting System Supporting Industrial Chain Collaboration Platform

With the rapid development of China's economy and automobile industry, China has gradually become the world's largest automobile production and consumption country, and then makes the continuous expansion of the scale of automotive service.The auto parts play a pivotal role in the after-sales service of the entire automotive industry. However, with the gradual maturity of the after-sales service industries,more and more auto companies focus on the demand of auto parts. The accurate forecast of the demand for auto parts and the parts timely supply of the autos both have played a more and more critical role in terms of improving the quality of service.At the same time, with the development of forecasting technology, regression analysis,GM(1, N) gray model and BP neural network are becoming more and more popular ,and then these models are gradually introduced into the auto parts management.Relying on the automobile industry chain collaboration platform, in combination with the auto parts forecast and auto parts sales to provide features that benefit the forecasting of auto parts demand, which has become an important way to improve the service efficiency of automobile after-sales service enterprises.At present, the traditional automobile manufacturers have adopted the business unit to submit the parts plan,and then using these plans to predict the demand for the parts during the three guarantees period. However, the demand of amount of parts in every business unit is often determined by experience, which usually yield error. And while auto factory only makes a simple "addition" on the submission of parts plan,causing more mistakes.To solve this problem, firstly the auto parts forecasting model of auto parts sales management is studied in this thesis, and the auto parts demand forecasting solution is designed. In this solution, the auto parts sales history, auto sales history, parts failure rate and so on are all included in the parts forecasting factors,so that the factory and the business units can accurately forecast the auto parts demand, in order to satisfy the demand of customers and to improve quality of service and enhance business capabilities.Secondly, a variety of prediction algorithms are studied in this thesis in order to improve the forecasting accuracy of the auto parts demand. The auto parts sales history, auto sales history, parts failure rate and other variables are used in combination with regression analysis, GM(1, N) gray model and BP neural network for modeling and analyzing on auto parts demand.Finally, an auto parts sales forecasting system by using C# language, based on three-tier structure of B/S mode are designed and implemented in this thesis.