Online Consumer Alignment using Supervised Machine Learning Technique

As we all know, online businesses are growing in popularity by the day, and the need for websites to attract more clients and provide them with the best possible service should be ensured for all. In this regard, we have come up with a concept for client categorization. Customers who buy items frequently online will be in the platinum group, followed by consumers who buy products occasionally online, who will be in the gold group, and finally, customers who buy products extremely seldom online, who will be in the silver group. We used the data evolution method to collect data from a Google Form in this study. We have set an age limit to ensure that everyone gets the information they need. We have also included a few key professions so that you may learn from those experts and their important info. There were 531 responders in all, with 57 percent of females and 43 percent of males. We assemble data leveling with the guidance of e-commerce business experts to identify customers as Silver, Gold, or Platinum depending on the frequency of their purchases, shopping intervals, and expenses. After labeling data, Machine learning approaches are established for data analysis. Random Forest Classifier (RFC), Nave Bayes Classifier (NBC), Logistic Regression (LR), Instance Based-K, Logistic Model Tree, J-48, J-Rip, and PART those models are developed to classify the online consumer. For classification, the random forest classifier (RFC) technique performs very well with 94.34% accuracy.