Amazon Customer Reviews

Avatar
Posted on Aug 4, 2019

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 ID1158
Age18 ~ 85, integer
TitleText
Review Text
Rating1 ~ 5 ,Categorical
Recommended IND0 or 1, Categorical
Positive Feedback Countinteger
Division Name3 values
Department Name5 values
Class Name17 values

Phase I

To help Entrepreneurs who are planning on opening a women's clothing store on Amazon.  Questions to be answered:

  1. Should I consider Amazon platform for the coming store?
  2. What kind of clothing should I sell ?
  3. What sizes should I sell ?
  4. 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)

  1. What are the topics of positive reviews  ?
  2. What are the focus of complaints ?
  3. What should I do to improve customers' experience?
  4. What should I do to drive the growth of customers group?

About Author

Avatar

Lan Mond

Recently certified as Data Scientist and Masters in Electrical Engineering alongside with rich international business experience in helping companies to gather and analyze data to make more informed decisions regionally and globally to achieve their business goals while...
View all posts by Lan Mond >

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

2019 airbnb alumni Alumni Interview Alumni Spotlight alumni story Alumnus API artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Big Data bootcamp Bootcamp Prep Bundles California Cancer Research capstone Career citibike clustering Coding Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Industry Experts Job JP Morgan Chase Kaggle lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Open Data painter pandas Portfolio Development prediction Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest recommendation recommendation system regression Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Tableau Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping What to expect word cloud word2vec XGBoost yelp