Skip to content

Customer segmentation using SQL, Python, feature engineering, and machine learning for optimizing TravelTide's rewards program

Notifications You must be signed in to change notification settings

DanMenegaz/TravelTide-CustomerSegmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 

Repository files navigation

Travel Tides Project

This repository contains code and insights from the Travel Tides project.

TravelTide - Customer Rewards Program Optimization

Executive Summary:

TravelTide aims to enhance its customer rewards program by segmenting customers based on behavior and affinity for discounts. The goal is to personalize marketing efforts, optimize customer retention strategies, and offer targeted perks that resonate with each customer segment.

Objectives:

  • Analyze customer behavior using key metrics related to discount usage, average discount size, and overall spending.
  • Segment customers into distinct groups based on their behaviors to identify high-value segments.
  • Tailor rewards specifically designed for each segment to increase engagement and loyalty.

Methodology:

We used a combination of SQL for data extraction, Python for data processing, and machine learning for customer segmentation. Key steps included:

  • Metric Calculation: Metrics like discount flight proportion, average flight discount, and total hotel spending were calculated.
  • Bargain Index: An aggregate index to identify customers with high sensitivity to discounts.
  • K-Means Clustering: Applied to segment customers into distinct groups based on behavior and preferences.

Key Findings:

  • High Bargain Segment: Customers in this group are highly responsive to discounts and show a higher average Customer Lifetime Value (CLTV).
  • Diverse Segments: Additional segments like Frequent Travelers, Occasional Travelers, and Budget-Conscious Travelers were identified.
  • Behavioral Insights: Each segment has unique spending and travel patterns, providing opportunities for targeted marketing and rewards.

Google Colab Notebook

Access the Google Colab notebook for this project here.

Loom Video

Watch the walkthrough video here.

Recommendations/Targeted Marketing:

  • High Bargain Segment: Offer exclusive discounts, early sales access, and bonus reward points.

  • Frequent Travelers: Provide loyalty benefits such as free upgrades and priority boarding.

  • Occasional Travelers: Introduce flexible booking, travel insurance perks, and referral bonuses.

  • Budget-Conscious Travelers: Focus on budget-friendly deals and rewards for cost-saving behaviors.

  • Rewards Program Refinement: Align rewards program perks with the behavioral patterns of each segment.

  • CRM Integration: Use segmentation results to inform personalized marketing and customer relationship strategies.

Conclusion:

By understanding and segmenting the customer base, TravelTide can offer relevant perks and improve customer retention. Tailoring rewards to the needs of each segment enhances engagement and drives long-term revenue growth.

About

Customer segmentation using SQL, Python, feature engineering, and machine learning for optimizing TravelTide's rewards program

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published