The Research Of Data Mining And Models Based On Grey System Theory

As a course of extracting valuable implied information and knowledge from huge amount of data,Data Mining has been widely used in society,economy, production,and all areas of our life.But there are limitations in Data Mining that the amount of data must be large enough to identify the anticipant relationships.As a new method to research problems that have less data,poor information and uncertainty,Grey System Theory can make up for the shortcomings of Data Mining.Although Grey System Theory itself has many defects,many technologies in the area of Data Mining can overcome these problems.Therefore,we can combine Grey System Theory and Data Mining Technologies together.They complement each other and then we can build system and models based on Data Mining and Grey System Theory.Based on this thinking,researchers have proposed several combined models of grey neural network.But these models are only the simple combinations of Grey System Theory and Artificial Neural Network and can only do forecast on a series of data,they can't be used to forecast on a number of related sequences.So this paper integrates the mutual relationships between several sequences and the deviation relationship between the prediction value and the actual value forecasted by the GM(1,1) model into the BP Neural Network Model and builds the Grey Neural Network Multi-series Prediction Model.And this paper forecasts the stock price using the current combined model of Grey Neural Network and the Grey Neural Network Multi-series Prediction Model that we have built and verifies the feasibility and superiority of the Grey Neural Network Multi-series Prediction Model.