C5i Case Studies Multivariate profiling to understand utility customers by level of engagement

Edit This Case Study Record

	Multivariate profiling to understand utility customers by level of engagement C5i

Multivariate profiling to understand utility customers by level of engagement

C5i

Technology Category	Analytics & Modeling - Big Data Analytics Analytics & Modeling - Predictive Analytics
Applicable Industries	Utilities
Applicable Functions	Business Operation Sales & Marketing
Services	Data Science Services
Challenge	The client, a large US public utility, was looking to develop an engagement scoring system for profiling highly engaged residential customers as input to product/service marketing efforts. The challenge was to measure engagement based on the number and importance of interactions by the customer with the utility on four different dimensions. The goal was to establish a distinct segment of most engaged customers for targeted marketing of new product offers and ways to increase interaction with and convert less engaged customers. Read More
About Customer	The customer in this case study is a large public utility company based in the United States. The company operates in the utilities industry, providing essential services to residential customers. The company was looking to better understand its customers and their level of engagement with the company's services. The goal was to identify highly engaged customers and use this information to inform their product and service marketing efforts. The company was also interested in finding ways to increase interaction with less engaged customers and convert them into more engaged customers. Read More
Solution	Blueocean Market Intelligence developed a framework to measure engagement based on the number and importance of interactions by the customer with the utility on four different dimensions. Engagement scores were first developed for each dimension based on several parameters, and then an overall engagement score was computed using weights developed through an analytic hierarchy process. Third-party data was used to profile the groups of customers based on demographic, attitudinal and behavioral variables, as well as customer transaction data available from the client. Finally, a profile-based predictive model was built using a decision tree approach to predict which customers were likely to have a high propensity of engagement with the utility, based on demographic, attitudinal, behavioural and historical transactional data. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Big Data Analytics

Analytics & Modeling - Predictive Analytics

Applicable Industries

Utilities

Applicable Functions

Business Operation

Sales & Marketing

Services

Data Science Services

Challenge

The client, a large US public utility, was looking to develop an engagement scoring system for profiling highly engaged residential customers as input to product/service marketing efforts. The challenge was to measure engagement based on the number and importance of interactions by the customer with the utility on four different dimensions. The goal was to establish a distinct segment of most engaged customers for targeted marketing of new product offers and ways to increase interaction with and convert less engaged customers.

About Customer

The customer in this case study is a large public utility company based in the United States. The company operates in the utilities industry, providing essential services to residential customers. The company was looking to better understand its customers and their level of engagement with the company's services. The goal was to identify highly engaged customers and use this information to inform their product and service marketing efforts. The company was also interested in finding ways to increase interaction with less engaged customers and convert them into more engaged customers.

Solution

Blueocean Market Intelligence developed a framework to measure engagement based on the number and importance of interactions by the customer with the utility on four different dimensions. Engagement scores were first developed for each dimension based on several parameters, and then an overall engagement score was computed using weights developed through an analytic hierarchy process. Third-party data was used to profile the groups of customers based on demographic, attitudinal and behavioral variables, as well as customer transaction data available from the client. Finally, a profile-based predictive model was built using a decision tree approach to predict which customers were likely to have a high propensity of engagement with the utility, based on demographic, attitudinal, behavioural and historical transactional data.

Impact #1	Five groups of customers were identified based on their level of engagement with the utility.
Impact #2	Established top three rules to predict high engagement levels using existing customer data.
Impact #3	Identified characteristics of most engaged customers who are most likely to be open to new product offers.

Impact #1

Five groups of customers were identified based on their level of engagement with the utility.

Impact #2

Established top three rules to predict high engagement levels using existing customer data.

Impact #3

Identified characteristics of most engaged customers who are most likely to be open to new product offers.

Download PDF Version

Overview

Multivariate profiling to understand utility customers by level of engagement

Operational Impact