Amazon Customer Reviews
Background
More and more companies turn to social media to understand their customers, in order to improve their products and services, or to make business decisions. This is a two_phase_project which aimed to conduct a study on Amazon women's clothing business.
- Phase I : Analysis on review counts cross different features (Numeric)
- Phase II: NLP analysis on review contents(Text)
Dataset
The Women’s Clothing E-Commerce Reviews dataset was used for this project. This reviews included in the dataset were written by real customers but all anonymized for privacy reason.
The dataset contains 23318 observations and 11 features:
| Clothing ID | 1158 |
| Age | 18 ~ 85, integer |
| Title | Text |
| Review | Text |
| Rating | 1 ~ 5 ,Categorical |
| Recommended IND | 0 or 1, Categorical |
| Positive Feedback Count | integer |
| Division Name | 3 values |
| Department Name | 5 values |
| Class Name | 17 values |
Phase I
To help Entrepreneurs who are planning on opening a women's clothing store on Amazon. Questions to be answered:
- Should I consider Amazon platform for the coming store?
- What kind of clothing should I sell ?
- What sizes should I sell ?
- Who should I sell to?
In order to answer the above questions based on customer reviews, we make two assumptions:
- the probability of a customer writing a review after making a purchase is the same cross all age groups
- the profit ratio is the same cross all clothing ID
- the Entrepreneur has unlimited access to any inventory
1) Overall Review
The above graph reveals that more than 55% of the customers rated 5.
Amazon is the largest online retail store in the world and carries a large satisfied customer body. It should be considered for the planning online store.
2) Age distribution
The above graph is the review count over age. It reveals that the most customers who left reviews on purchased products fell into the age range of 32 to 45. In addition, they are also the group who gave most positive reviews on their purchased products. Therefore,
- 32 to 45 age group is the most satisfied group in the range of customers.
- With the standing assumption, it is reasonable to conclude that 33 to 45 age group is the most active purchase force
3) Review Count over Department
Tops clearly received the most reviews follows by Dresses and Bottoms. With the standing assumption, we conclude that Tops, Dresses and Bottoms are the top selling clothing.
3) Review Count vs Division
General division received the most reviews. With the standing assumption, General size Tops should be the first inventory to consider.
4) Review Count by Class
The Dresses, Knits and Blouses received the most reviews.
5) Top 30 Most Reviewed Clothing ID
6) Top 5 Most Reviewed in 5 Rating Classes
Further investigation on Clothing ID: 1094, 1081, 1078, 872, 862 is strongly recommended to an Entrepreneur. With the findings of their success should be extremely helpful for the start of the planning new store.
Phase II (to be continued)
- What are the topics of positive reviews ?
- What are the focus of complaints ?
- What should I do to improve customers' experience?
- What should I do to drive the growth of customers group?
The skills the authors demonstrated here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.
About Author
