C5i Case Studies Improved direct response program participation and reduced marketing costs with predictive modeling

Edit This Case Study Record

	Improved direct response program participation and reduced marketing costs with predictive modeling C5i

Improved direct response program participation and reduced marketing costs with predictive modeling

C5i

Technology Category	Analytics & Modeling - Predictive Analytics
Applicable Industries	Utilities
Applicable Functions	Sales & Marketing
Use Cases	Predictive Replenishment
Services	Data Science Services
Challenge	The client, a large US public utility, was facing a challenge in understanding the key drivers that influence the propensity to enroll in their program. They wanted to identify which residential customers are the best prospects for the program and optimize campaign costs by targeting the best subset of prospective customers. The traditional response rate of program participation was 4%, and the client wanted to increase this rate while decreasing mailing costs. Read More
About Customer	The customer is a large public utility company based in the United States. The company is part of the utilities industry and provides essential services to the public. The company was looking to improve its direct response program participation and reduce marketing costs. They wanted to understand the key drivers that influence the propensity to enroll in the program and identify the best residential customers for the program. The company was also interested in optimizing campaign costs by targeting the best subset of prospective customers. Read More
Solution	Blueocean Market Intelligence developed a predictive model using historical billing and usage data for customers over a two-year period and data from a satisfaction survey in the same time frame. Historical data analysis was used to understand what usage patterns would help to predict program participation. Historical and customer demographic information was captured to predict program participation and identify differences between program participants and non-participants. Blueocean Market Intelligence also conducted secondary research and evaluated social media conversations to obtain additional context on what customers think about the rate plan. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Applicable Industries

Utilities

Applicable Functions

Sales & Marketing

Use Cases

Predictive Replenishment

Services

Data Science Services

Challenge

The client, a large US public utility, was facing a challenge in understanding the key drivers that influence the propensity to enroll in their program. They wanted to identify which residential customers are the best prospects for the program and optimize campaign costs by targeting the best subset of prospective customers. The traditional response rate of program participation was 4%, and the client wanted to increase this rate while decreasing mailing costs.

About Customer

The customer is a large public utility company based in the United States. The company is part of the utilities industry and provides essential services to the public. The company was looking to improve its direct response program participation and reduce marketing costs. They wanted to understand the key drivers that influence the propensity to enroll in the program and identify the best residential customers for the program. The company was also interested in optimizing campaign costs by targeting the best subset of prospective customers.

Solution

Blueocean Market Intelligence developed a predictive model using historical billing and usage data for customers over a two-year period and data from a satisfaction survey in the same time frame. Historical data analysis was used to understand what usage patterns would help to predict program participation. Historical and customer demographic information was captured to predict program participation and identify differences between program participants and non-participants. Blueocean Market Intelligence also conducted secondary research and evaluated social media conversations to obtain additional context on what customers think about the rate plan.

Impact #1	Developed a robust and scientific framework to decrease mailing costs.
Impact #2	Increased the campaign response rate by targeting only the best prospective customers for select rate plans.
Impact #3	Established a target profile of the best prospective customers.

Impact #1

Developed a robust and scientific framework to decrease mailing costs.

Impact #2

Increased the campaign response rate by targeting only the best prospective customers for select rate plans.

Impact #3

Established a target profile of the best prospective customers.

Benefit #1	Response rate more than doubled with 50% implied savings from higher conversion ratio of enrollment/contacts.
Benefit #2	The predictive model scored the customer base on higher propensity to participate in the program resulting in 60% accuracy of participation likelihood.

Benefit #1

Response rate more than doubled with 50% implied savings from higher conversion ratio of enrollment/contacts.

Benefit #2

The predictive model scored the customer base on higher propensity to participate in the program resulting in 60% accuracy of participation likelihood.

Download PDF Version

Overview

Improved direct response program participation and reduced marketing costs with predictive modeling

Operational Impact

Quantitative Benefit