People often look at the average user rating of a product before buying it online
Let's take an average. For example 4.764925.
This is a preferable, important indicator. But we may be missing the latest trend in products. Positive or negative trends in the presentation or use of the product may lose their impact.
This project involves a study on how to calculate the most accurate score for a product by making various evaluations on the scores given to a product
For example, if a product received very high ratings in its first three months, it may have the same weight as others and thus miss the recent trend of liking it more or liking it less.
|Rating||Course Rating Score|
|Progress||Course Completion Rate|
|Questions Asked||How many questions asked|
|Questions Answered||How many of the questions he asked were answered|
pandas==1.4.3 scikit_learn==1.1.2 scipy==1.7.3
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