Article Preview
TopCustomer-segmentation marketing strategies play an important role in improving market competitiveness, reducing marketing costs, enhancing marketing effectiveness, and strengthening customer-relationship management. By segmenting customer groups, enterprises can better meet customer needs, achieve sustained growth, and achieve sustainable competitive advantages. To better leverage customer-segmentation marketing strategies, many scholars have analyzed and studied relevant sales data. Scholars such as Sokol and Holý (2021) have utilized data clustering analysis techniques to analyze customer behavior and value in the retail industry. This study obtained information on shopping proximity, frequency, and purchasing power by segmenting customers and applied data-clustering analysis to a chain pharmacy. The results indicate that this method can bring more customer needs to the attention of merchants.
Nikaein and Abedin (2021) constructed a data-mining method based on a radio frequency machine learning model for enhancing the efficiency of marketing and reducing costs during the marketing process and applied it to the pharmaceutical industry. The results indicate that this model can help sales managers more effectively plan for each customer, improve visit efficiency, and lower costs.
To reduce customer churn in potential customer orders, Fitriani and Febrianto (2021) compared data-mining methods such as naive Bayes, random forests, and SVM. They used these to obtain data-feature information about potential customers to eliminate the problem of category imbalance in the marketing process of banks. The results indicate that random forests have high mining ability, with a maximum accuracy of 92.61%.