Data Description : This dataset is made up of various feature vectors from 12,330 sessions. Details of this dataset: To avoid any tendency to a particular campaign, special day, user profile, or time, it was created so that each session would belong to a different user throughout the course of a year. 84,5% of the 12 330 sessions in the dataset were negative class samples that did not result in shopping, while the remaining were positive class samples that did.
The main objective of this project is to analyze the dataset, visualize it using various libraries (such as Matplotlib, Seaborn, and Bokeh), and model it to create a machine learning classification system that can predict an online shopper's intention (to buy or not to buy), based on the values of the given features, using libraries like Scikit-Learn through the use of multiple algorithms and comparing between them. The model will then be converted into a Django API so that it may be appropriately shown through it.