Apriori Algorithm in K-Means Clustering of Consumer Purchases

abstract–People live in an era of big data, where internet users generate a large amount of data through interactions between people, platforms, and different platforms. These pieces of information affect users. Based on this, this article constructs an integrated model of consumer shopping behavior based on large sample data and planning behavior theory, and uses SPSS software to perform cluster analysis on the sample data. It extracts data related rules through the Apriori algorithm to explore the consumption characteristics of consumers during the shopping process and the influencing factors when they exist. It can be seen that as the number of records increases, the running time of the Apriori algorithm remains between $0-2000 \mathrm{~ms}$, with a relatively small increase. Research has found that the improvement in the association rules between economic income, occupation, and consumption amount is greater than $8 \%$, and there is a strong correlation between the two and consumption amount.