Customer Intelligence Predictive Models: Customer Attrition, Loyalty Scoring and Next Best Offer

The purpose of this project is to develop three predictive models for Temenos’ Customer Intelligence offering including: (1) Customer Attrition; (2) Loyalty Scoring; and, (3) Next Best Offer. Customer attrition, also called “churn”, or “defection”, is a major business issue for organizations to address. It is crucial to maintain and grow customer relationships in order to sustain profitable growth. There are many ways to measure customer loyalty which are predominantly market research based such as the Net Promoter Score, satisfaction and likelihood to repurchase. However, it is getting increasingly difficult to get representative samples of the entire customer base. Data modeling can provide insight into loyalty based on actual customer behavior instead of perception alone.Next best offer (NBO) models predict the next product, service or offer that a customer is likely to buy or use given the customer’s previous purchase history. NBO models are effective in cross-selling and when used along with campaign response data to improve response rates. The approach is to develop individual propensity-to-buy predictive analytics models for each product or offering. These models are then combined to create a set of best next offers for each customer. Integrating these data-driven models into the business intelligence software will let the financial institution to take proactive actions, determine selling opportunities within the existing customer base and put more efforts into the purchase and serving of the most profitable customers.

Faculty Supervisor:

Drs. Yulia R. Gel & Mary E. Thompson


Vyacheslav Lyubchich


Temenos Software Canada


Statistics / Actuarial sciences


Information and communications technologies


University of Waterloo



Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects