Main Article Content


The vast majority of businesses of today are supported or conducted online. Marketing offers are one of the most effective methods that can be used to support the created virtual environments. In the past, these offers were offered to every person who visited an e-commerce website. After that, online stores chose to analyze visitor information in near real time because they knew they needed to target the right audience with their marketing efforts. The goal is to get in touch with the most relevant users by phone or email to suggest deals that are likely to get them to return to the website and make a good purchase. We propose a real-time online shopper behavior prediction system that can anticipate a visitor's intended purchase right after they visit a website. We investigate CLNB and rely on session and visitor data to accomplish this. With Dependent Samples and Matched Pairs, Pairs Inferences Ratio about Two Means. When there is a connection between the samples, there are dependent samples. Matched pairs from random samples make up the data. We want to consolidate such systems by trying to keep as many potential visitors as possible. In this context, we propose a method for identifying customers who are likely to make a purchase as soon as they connect to an online store. When the values chosen for one sample are used to determine the values in the second sample, a sampling method is dependent. In addition, we use oversampling to boost each classifier's performance and scalability. to offer more generous deals to visitors who didn't make a good first purchase but showed a strong desire to make a purchase after a specific click stream. SVM ensemble with PIR outperforms the other techniques in terms of accuracy and F1 Score, as shown by the findings. The project's objectives include. It is necessary to conduct an analysis of the user who purchased the particular item, the link they viewed, and the relation the user just viewed, purchased, or both. To locate the product recommendation provided by the link,

Article Details

How to Cite
V. Kavipriya, P. Aravind Gokul, S. Gowtham, & K. Mithun. (2023). Recommendations in E-Commerce. International Journal of Intellectual Advancements and Research in Engineering Computations, 11(2), 35–38. Retrieved from