Enabling customer centricity, upstream decisioning, and retention at the enterprise- level through Customer Experience Score (CES)

Situation

• One of the UK & Europe’s largest Entertainment & Media companies with a 15M+ customer base experienced an annual customer-initiated churn rate of > 10%

• A large proportion of customer retention initiatives were discount-driven, leading to a $1B+ financial overhead annually

• The client’s Customer Retention team wanted to develop a hyper-personalized metric for every customer to enable:
  Avoid being pressed into rolling out deep offers for churn retention at renewal through customer-centricity and nurturing of value-based relationships

  Upstream decisioning through churn detection 2-4 months in future

• The solution needed to be scalable and enable a near real-time refresh of scores, reporting and treatments for the entire customer base
  
  

Our Approach

Principles

Working closely with multiple client teams, Fractal developed a solution to:

• Define a value-based relationship and move away from price discounts, and offer-based retention

• Provide an in-depth understanding of drivers of customer experience to help design customer-centric strategies

• Design an easy-to-implement relationship score metric (0-100) to provide holistic view of customers’ relationship with the business

Development

• AI: Ensembled AI framework with superior performance and ability to leverage:

• Static information like demographics, pricing, billing

• Dynamic journeys, such as a sequence of past transactions/interactions

• Engineering: Harmonized customer view (Customer 360) at weekly level, from 25+ raw data sources

• Design: ‘Simple to measure’ metric, model explainability, and business actions

Testing & Operationalization

• Results validated on OOS & OOT samples and against existing baseline models

• End-to-end automation on the cloud and incremental execution on a weekly basis

• Integration with marketing platform (through the on-premise database) to ensure regular automated feeds of customer responses, lists ,and drivers

Insights

• 40% of drivers discovered by the model were completely new/unrelated to offers and provided incremental intelligence about:

• DTV and broadband product holdingsBillings/Pricing, marketing outreach

• Engineered 800+ granular features to identify early signals of poor experience and churn-risk behavior across 150+ customer segments

• Established the hypothesis that experience is defined not only by the current state but by the overall journey the customer has been through with the organization

• 
  

Impact ​

Estimated annual impact

• Call reduction: 7-10% reduction in the total annual volume of cancellation calls

• Churn reduction: 5-6% reduction in the total annual volume of churn

Innovation

• First customer management solution on the cloud for the organization resulting in accelerated migration from on-premise data and technology platforms

• Simultaneously captured dynamic and static behavioral patterns

• Self-learning models enabled adjustment over time to account for the change in customer behavior

• Process automation, parallelized data processing, and modeling resulted in efficiencies at scale and delivered a time reduction of 20X compared to traditional frameworks

CES is a dynamic indicator of the experience customer is having with the business throughout the relationship

Customer 360 is a single row per customer capturing a holistic view of the relationship

More than 40% of drivers of Customer Experience were unrelated to End of Offer/Contract and helped discover insights not known earlier to client

CES successfully differentiated the high and low risk of churn

AI/ML framework on the cloud was based on three key components to drive customer-centricity

Ensembled deep learning model was built to capture both historical journeys and current behavior to identify at-risk customers

Ensembled deep learning model was built to capture both historical journeys and current behavior to identify at-risk customers