Model building using raw ecommerce data

HI, I have a user-level log data of browsing behavior (Timestamp, UserId and website section visited) and the final conversion data too (Timestamp, UserID, Products Purchased in the transaction, Overall Cart Value). Based on this data you are required to build features and model on these characteristics of users to calculate a score/rank for conversion probability of that user. These scores will eventually decide the bidding logic used for each user. I want a detailed explanation & python file on the below points. a. Feature Engineering (Variable Imputation) b. Model Selection Criteria (Basis of choosing the final Technique) c. Measurement Criteria (Comparison of Various Models) d. Scope for improvement 2. A summary file (MS Word format) stating a. Problem Statement b. Approach Taken c. Interpretation of Results d. Minimal but effective Storyboarding Note: I am looking for a detailed python file with all the visualization and final output storytelling. Looking for someone too complete this project in simple understandable codes in Machine Learning within a day at a budget of 3k. and do not expect any further data apart from the attachments Please do not bid if you are not matching the timeline or budget.