Analysis of Laptop Purchase History to Determine Key Factors Using Logistic Regression

Abstract

E-Commerce is a new concept commonly described as the process of buying and selling goods or services over the World Wide Web or the exchange of products, services, and information through information networks, including the internet. Tokopedia, one of the largest e-commerce platforms in Indonesia, markets many products, including electronics. This study analyzes laptop data from Tokopedia. The vast history of purchase data and customer data in Tokopedia's database offers various ways to process it. One approach is using logistic regression models. The logistic regression results on the three features (price_cat, memory_size, and merk_cat) indicate that all three can be used to create logistic regression equations to determine laptop purchase probability. However, the regression calculations show that the r^2 value for price_cat is the highest at 0.82, indicating that price_cat significantly influences the probability of purchasing a laptop.