Design of a sports culture data fusion system based on a data mining algorithm

Abstract

The sports industry is an important component of social life and the national economy. With the advent of the era of big data, promoting the decision-making and scientific construction of the sports and cultural goods industry is conducive to the transformation and upgrading of the sports industry. In view of the shortcomings of the current sports stationery industry consumption data system, this paper combines K-means spatial clustering, fusion decision tree, naive Bayes, and other data mining algorithms and data warehouse technologies to the sports stationery industry. The consumption data system is the research object, and the analysis of geospatial feature clustering, customer segmentation, and consumption preference prediction of sports stationery industry consumption is carried out. The data mining–based sports cultural product industry data fusion system model is constructed, and the architecture, technology path, and function realization of the model are clarified. The actual case analysis and performance test results show that the realized sports cultural goods consumption data fusion system can provide a scientific reference model and basis for the modern sports stationery industry to use data mining and other new technologies to establish a decision-making information system.