AUTOMATIC SALES FORECASTING SYSTEM BASED ON DATA CRAWLING AND MANAGER'S INPUT

摘要

According to the present invention, in addition to existing multi variant is based on statistics and artificial intelligent analysis, news goes on business, weather and sport, searches for trend, public holidays, memorial day, procedure qualification, economic indicator, statistical data, SNS message, billboard, internet, which is replied, to be promoted related classification and is used to forecast prediction of the sale as adeditive attribute data by creeping. Data set is generated by pretreatment, generates the algorithm by prediction model, and is calculated sales forecast value and carried out sales forecast information corresponding to due date forecast to provide such as table, chart or numerical value. Inputting as workshop director influences futuresell element, such as in the feedback sale result, promotes other events, the significant fact, data set and has forecast that the sales forecast for increasing accuracy can be improved in model. ;The 2015 of copyright KIPO submissions