Measurement Problems

• Rating Product & Sorting Reviews (Amazon)
• Comparison of Conversion of Bidding Methods with A/B Test

Rating Product & Sorting Reviews in Amazon

GitHub Repository:

Business Problem
One of the most important problems in e-commerce is the correct calculation of the points given to the products after sales.

The GitHub Repository to this problem means providing greater customer satisfaction for the e-commerce site, prominence of the product for the sellers and a seamless shopping experience for the buyers.

Another problem is the correct ordering of the comments given to the products. Since misleading comments will directly affect the sale of the product, it will cause both financial loss and loss of customers.

In the GitHub Repository of these 2 basic problems, e-commerce site and sellers will increase their sales, while customers will complete their purchasing journey without any problems.

Dataset Story
This dataset, which includes Amazon product data, includes product categories and various metadata.

The product with the most reviews in the electronics category has user ratings and reviews.

Variables

• reviewerID: User ID
• asin: Product Id
• reviewerName: User Name
• helpful: Useful rating degree
• reviewText: Useful review rating
• overall: Product rating
• summary: Review summary
• unixReviewTime: Review time
• reviewTime: Review Time
• day_diff: Number of days since review
• helpful_yes: Number of times the review was found useful
• total_vote: Number of votes for review

Requirements

• pandas==1.5.1
• scipy==1.11.4

Comparison of Conversion of Bidding Methods with A/B Test

GitHub Repository:

Business Problem

Facebook recently introduced a new bidding type, 'average bidding', as an alternative to the existing 'maximum bidding' type of bidding.

One of our customers website decided to test this new feature and wants to do an A/B test to see if average bidding brings more conversions than maximum bidding.

A/B testing has been going on for 1 month and website now expects you to analyze the results of this A/B test. The ultimate measure of success for the website is 'Purchase'. Therefore, the focus should be on the 'Purchase' metric for statistical testing.

Dataset Story
In this dataset, which includes the website information of a company, there is information such as the number of advertisements that users see and click, as well as earnings information from here. There are two separate datasets, the Control and Test group. These datasets are in separate sheets of the ab_testing.xlsx excel. Maximum Bidding was applied to the control group and Average Bidding was applied to the test group.

Variables

• impression: Number of ad views
• Click: Number of clicks on the displayed ad
• Purchase: The number of products purchased after the ads clicked
• Earning: Earnings after purchased products

Requirements

• pandas==1.5.1
• scipy==1.11.4