A GACP and GTMCP company
Maximize Revenues on your Customer Loyalty
Program using Predictive Analytics
A GACP and GTMCP company
?
Q & A wwwBefore we begin...
A GACP and GTMCP company
Your Speakers
@parikh_shachi
Technical Analyst @tatvic Loves js and data analysis
@kushan_s
Web Analyst @tatvic Loves R, Pandas, ML
A GACP and GTMCP company
Agenda
• Background and Economics of Customer Loyalty • Defining the Business Question
• A Primer on Predictive Analytics • Defining the data sources
• Logistic Regression • Model Accuracy
A GACP and GTMCP company
Customer Retention – Why should you Care?
• Customer Acquisition Costs are on the rise • Repeat Customers
– Create higher value (both in AOV & Revenue) – Evangelize your brand
– Have Lower Service Costs
“Retailers can achieve tremendous revenue gains by shifting their marketing budgets to better target these customer segments”
http://www.practicalecommerce.com/articles/63459-Seek-Repeat-Customers-to-Drive-A Ghttp://www.practicalecommerce.com/articles/63459-Seek-Repeat-Customers-to-Drive-ACP and GTMCP company
A GACP and GTMCP company
Contribution to Revenue
750 (repeat) customers drive 40% of the total RevenueA GACP and GTMCP company
Contribution to Revenue
If 5% of these customers become repeat buyers after Discount Targeting, what are the implications for revenue?
A GACP and GTMCP company
Conventional Approach to Customer Loyalty
• Send Discount Coupons to all Customers either via email or some other medium
• Problems
– Non Targeted Campaign hence suffers from Low Conversion Rate
A GACP and GTMCP company
Revenue Leakage: What If Analysis
Size of Email List 100,000
Click Through Rate of Email List 5%
Visits 5000
Conversion Rate 2.5%
Transactions 125
Average Order Value $250
Discount Provided 20%
A GACP and GTMCP company
Revenue Leakage: What If Analysis
Size of Email List 100,000
Click Through Rate of Email List 5%
Visits 5000
Conversion Rate 2.5%
Transactions 125
Average Order Value $250
Discount Provided 20%
Discount $50
Persuadables
(Customers Who bought after discount was provided)
75 Sure Things
(Customers who would have bought anyway)
50
A GACP and GTMCP company
Summing up
Target your
Loyalty Campaign to this segment
A GACP and GTMCP company
Business Question for Predictive Analytics
• Predicting Customers who would make a repeat purchase within 2 months of their initial purchase
• Outcome/Response Variable: Whether the customer would make a repeat purchase within 60 days
• Using Data of Past Customers who have made purchases on the site
A GACP and GTMCP company
Until Now
• Repeat Customers are valuable and we need more of them • Sending out discount coupons to all customers w/out
segmentation leads to a loss in your Revenue
• Use a Predictive Model to find out those customers who would not make a return purchase without a discount coupon
A GACP and GTMCP company
Data Sources and Features
Google Analytics Data
Transaction Date Product Category Item Quantity
Shipping Cost Incurred Medium
CRM Data
Is Newsletter Subscriber?
Discount Coupon Redeemed? Account Creation Date
Customer ID
A GACP and GTMCP company
An Aside: Extracting Google Analytics Data into R
User performing data extraction Google OAuth2 Authorization Server Google Analytics API
Access Token Request
A GACP and GTMCP company
An Aside: Extracting Google Analytics Data into R
User performing data extraction Google OAuth2 Authorization Server Google Analytics API
Access Token Response Access Token Request
A GACP and GTMCP company
An Aside: Extracting Google Analytics Data into R
User performing data extraction Google OAuth2 Authorization Server Google Analytics API
Access Token Response
Call API for list of profiles Access Token Request
A GACP and GTMCP company
An Aside: Extracting Google Analytics Data into R
User performing data extraction Google OAuth2 Authorization Server Google Analytics API
Access Token Response
Call API for list of profiles
Call API for query Access Token Request
A GACP and GTMCP company
Intuition behind Supervised Learning
A GACP and GTMCP company
Supervised Learning
Generates a function that maps inputs (labeled data) to desired outputs (e.g. Image Classification)
Training Data Machine Learning Algorithm Labels
Supervised Learning Model
Variables
Labels are right answers from historical data
e.g. Image of Car/Bike Input Data: Contains Images of Bike and Car
A GACP and GTMCP company
Supervised Learning
Generates a function that maps inputs (labeled data) to desired outputs (e.g. Image Classification)
Training Data Machine Learning Algorithm Test Data Predictive Model Predicted Outcome labels Labels
Supervised Learning Model
Variables
Labels are right answers from historical data
e.g. Image of Car/Bike Input Data: Contains Images of Bike and Car
A GACP and GTMCP company
Logistic Regression Model
• Algorithm used to predict categorical labels • In our problem Categorical Labels are
– 0 : Did not carry out repeat purchase
– 1 : Carried out Repeat Purchase within 60 days
• Using the algorithm we predict the probability of a Customer ID belonging to either class
A GACP and GTMCP company
Checking Model Accuracy
• Split Data Randomly into Train and Test
• Fit glm model on Train Data
• Predict labels for unseen Test Data
20 % Test Data
A GACP and GTMCP company
Model Accuracy
Confusion Matrix Predicted Labels (Predicted by running Model on Test Set)Actual Labels (From Test Set)
Not a Repeat Purchaser Repeat Purchaser Not a Repeat Purchaser 5271 4
Repeat Purchaser 1209 1
Labels
• 0 : Customer didn’t make a repeat purchase in 60 days • 1 : Customer made a repeat purchase in 60 days.
A GACP and GTMCP company
Model Accuracy
Confusion Matrix Predicted Labels (Predicted by running Model on Test Set)Actual Labels (From Test Set)
Not a Repeat Purchaser Repeat Purchaser Not a Repeat Purchaser 5271 4
Repeat Purchaser 1209 1
Accuracy = (Number of Correctly Predicted Labels) / Total Number of Labels = (5271 + 1) / (5271 + 4 + 1209 + 1)
A GACP and GTMCP company
Improving Model Accuracy
• Adding New Features to the model
– Difference b/w Account Creation Date and Transaction Date
– Checking for Transactions occurring during Weekend (based on Date) – Adding Days To Transaction, Location, Device Type as Features from
Google Analytics
• Trying out additional models
– Random Forests – Gradient Boosting
A GACP and GTMCP company
A GACP and GTMCP company
Next Webinar
How to Perform Churn Analysis for your Mobile Application
Key Takeaways • Predict the Segment of
Mobile App Users who would uninstall your app
• Remain Inactive and Churn over a period of Time
Register Now:
www.tatvic.com/webinar March 19th 11:00 AM PDT