Approaches to Customer Types Classification Method in the Supermarket

Abstract

The development of the retail industry in the economy is very rapid so it provides good economic growth, one of the retailers is supermarkets, in supermarkets consumers can buy goods directly, so consumers must be served well. The problem is how supermarkets can continue to increase their sales results, because there is a lot of competition from supermarket competitors, so the marketing team when creating events or promotions must be right on target so that loyalty for member or non-member customers can be measured, which will be used as the right marketing strategy and can increase customer satisfaction when the customer is satisfied with the services, products and promotional activities at the supermarket, the customer will continue to make purchases and will increase the results of achieving good sales. Based on this problem, how will this research apply the classification method, so that when we can make predictions from supermarket sales data for member and non-member customers, there will be a lot of insight for the marketing team, so that marketing activities are right on target for member or non-member customers. This research uses machine learning methods for data classification, using the Support Vector Machine (SVM) and Naïve Bayes algorithms. The results of this research are from the Support Vector Machine (SVM) algorithm. Accuracy is 0.493 while using the Naïve Bayes algorithm is 0.535. From the results of this research, the use of the Naïve Bayes algorithm is better than SVM so that it can approach the prediction of member and non-member customer classification in supermarket data in this research.

Keywords

• supermarkets
• customer types
• classification
• svm
• naïve bayes