Data Mining Assisted Purchase Prediction

Abstract

With the revolution from physical businesses to shopping online, predicting client behavior in e-commerce is becoming increasingly important. It can increase customer satisfaction and sales, resulting in higher conversion, by enabling a more individualized shopping process. Today, most users want to save their time using and they prefer to shop using the platform provided for e-commerce. Millions of transaction records are available in the databases of such websites using which, a customer shops something. Using the transaction to find something can be helpful for the organization or merchants. Using the available databases or datasets, to find some useful pattern can increase the business, to check out the customer satisfaction level, to check the customer behavior about the product, etc. Some of the useful information can be to find out which item will be purchased by the customer in the next visit, or which new items can be purchased by the customer in the next visit. Using this information, an organization or Shops can control the quantity and increase the maximum purchased items, improving the quality of products for the customers. For this purpose, we use supervised learning techniques for prediction. Because most of the data which we will use will be labeled. Many researchers used supervised methods but some of the researchers also used unsupervised methods too. We created a supervised model for predicting the basket items. Due to the large dataset, it was very difficult to extract the features and it takes a lot of time. We have performed feature engineering, to choose the best ones. After the training model, our model shows better performance than the previous results.