• Harsh Salvi
• Nemil Shah
• Tilak Satra
• Mitchell D’Silva

The burgeoning growth of the internet these days has resulted in a spurt in online business. Online E-commerce websites seek to convert the potential visitors on the websites to buyers of the goods and services. The behavior of the customers browsing online is used to predict the intent of an online buyer dynamically. The anonymous nature of these e-commerce transactions presents a greater risk for the industry with regard to increasing sales, enhancing customer experience, etc. as it becomes difficult to access the customer's browsing patterns. Such patterns can show customer's needs, expectations, and dislikes. The user's aim can be predicted early in the browsing session based on the moments tracked by the task performed by the user on the website. There are various dynamic predictive models such as Naive Bayes, Random Forest, XGBoost, KNN, Logistic Regression that are used for predicting user's intent before they would leave the website. The performance of these models has been examined.

Online shopper intent prediction, intention prediction, logistic regression, KNN, Random Forest, Naive Bayes, XGBoost

"Comparison of Techniques to predict Shopper's Intent", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.183-185, December-2019, Available :http://www.jetir.org/papers/JETIR1908180.pdf

"Comparison of Techniques to predict Shopper's Intent", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp183-185, December-2019, Available at : http://www.jetir.org/papers/JETIR1908180.pdf