Product Recommendation (4th step of Customer Analytics)
Customer Relation Management classroom project
Product Recommendation (4th step of Customer Analytics)
Customer Relation Management classroom project
If you are interested in articles related to my experience, please feel free to contact me: linkedin.com/in/nattapong-thanngam
This article is part of a series about Customer Analytics_._ (Part 1: Customer Profiling with Descriptive Analytics with SQL),(Part 2: Customer Segmentation with Clustering), (Part 3: Market Basket Analysis), and (Part 4: Product Recommendation)
After finish 3 steps, we will combine all analyses for Product recommendations that use a set of algorithms to show relevant products to your visitors. They do this by using data like location, gender, and more specific information like purchase intent.
- From part 1, I used Pivot table result to assign status to each customer.
My assumption:
- day 1 = 1 Jan 2017 (assume).
- New = Start shopping in this month (Dec.18)
- Repeat = Used to shopping in Last month + Shopping in this month
- Reactivated = Not shopping in last month but shopping in this month
- Churn1 = Not shopping in last 4 months (Sep.18 — Dec.18)
- Churn2 = Not shopping longer than 4 months
(1) Assign status to each customer (Image by Author)
- From part 2, we assign Member_level to each customer (Silver, Gold, Platinum)
(2) Assign member_level to each customer (Image by Author)
- From part 3, we will know Top 3 favorite item of each user. For Product recomendation of each user, I filter top 10 favorite item of each user and match with product recommendation.
(3) Top 3 favorite item of each user (Image by Author)
(4) Product recomendation of each user from Market Basket Analysis (Image by Author)
- Join all data together.
(5) List of recommendation product for each user (Image by Author)
- Moreover, another simple but powerful list is top 10 best seller
(6) Top 10 best seller (Image by Author)
- Popular 1st purchasing item of new customer is the powerful list to acquire new customer.
(7) Top 10 item for new customer (Image by Author)
- The recommendation lists are shown in figure 5, 6 and 7. I think we cannot say which list is the best one. It depends on Consumer Behavior, Marketing strategy, Timing, etc. We should work with the marketing team, test and compare the result.
- Moreover, no need to use only 1 method. For example,
- Masket basket analysis and individual favorite item for Platinum (Increase customer satisfaction)
- Big discount coupon for Churn-customer (Increase reactivate rate)
- Top 10 item for new customer for new target group (Easy)
Please feel free to contact me, I am willing to share and exchange on topics related to Data Science and Supply Chain.
Facebook: facebook.com/nattapong.thanngam
Linkedin: linkedin.com/in/nattapong-thanngam