Business Problem
One of the most important problems in e-commerce is the correct calculation of the points given to the products after the sale.
The solution to this problem means more customer satisfaction for the e-commerce site, product prominence for sellers and a smooth shopping experience for buyers.
Another problem is the correct ranking of the comments given to the products. Since the prominence of misleading reviews will directly affect the sales of the product, it will cause both financial loss and customer loss.
In solving these 2 basic problems, e-commerce sites and sellers will increase their sales while customers will complete their purchasing journey smoothly.
Dataset Info
amazon_review.csv
Total Features: 12
Total Row: 4915
| Feature | Definition |
|---|---|
| reviewerID | User ID |
| asin | Product Id |
| reviewerName | User Name |
| helpful | Earnings from purchased products |
| reviewText | Useful review rating |
| overall | Product rating |
| summary | Review Summary |
| unixReviewTime | Review Time (UNIX) |
| reviewTime | Review Time |
| day_diff | Number of days since review |
| helpful_yes | Number of times the review was found helpful |
| total_vote | Number of votes for review |
Requirements
matplotlib==3.5.2
pandas==1.4.3
scipy==1.7.3
Files
01-user-time-weighted-product-score.ipynb - User & Time Weighted Product Score Calculation Notebook
02.1-sorting-udemy-courses.ipynb - Sorting Udemy Courses Notebook
02.2-sorting-imdb-movies.ipynb - Sorting IMDB Movies Notebook
03-sorting-reviews.ipynb - Sorting Reviews Notebook
04-amazon-rating-product-sorting-reviews.ipynb - Rating Product & Sorting Reviews in Amazon