Executive Summary

An insurance provider offering auto, health, and life insurance to individual and business customers. Rapid growth led to a significant customer churn challenge.

To address this, we developed a data-driven churn prediction and retention solution using Databricks. The system consolidated fragmented data, predicted at-risk customers, and enabled personalized retention strategies, reducing churn by 20% and enhancing customer engagement.

About Client

The client is an insurance provider specializing in auto, health, and life insurance, serving both individual and business customers. With a strong market presence and a growing customer base, the company is committed to delivering high-quality insurance solutions tailored to diverse needs. However, rapid expansion brought challenges, including customer churn and fragmented data systems, which impacted their ability to retain clients effectively. Recognizing the importance of customer loyalty in a competitive industry, the company sought an innovative, data-driven approach to enhance customer engagement and reduce churn.

Problem Statement

The firm faced three critical challenges:

High Churn Rate

A significant percentage of customers were leaving, impacting revenue.

Data Silos

Customer data was fragmented across transactional systems, support logs, and usage records, hindering analysis.

Generic Retention Strategies

The lack of data insights made retention efforts broad and ineffective.

Solution Overview

We implemented a churn prediction system leveraging Databricks for data integration and machine learning. The solution:

Consolidated and transformed fragmented data.
Built a predictive model to identify at-risk customers.
Designed targeted retention strategies to enhance loyalty and engagement.

Key Components of the Solution

#1. Data Consolidation & Transformation

Challenge: Customer data was siloed across multiple systems.
Solution: Databricks unified transaction data, support logs, and customer activity into a single environment.
Tools: Databricks
Steps:

Extracted and cleaned data to remove duplicates and handle missing values.
Engineered key features like premium payment frequency, claim activity, and support queries.

#2. Churn Prediction Model

Challenge: Identifying customers likely to leave.
Solution: A Random Forest classifier was developed using Databricks MLlib to predict churn based on historical patterns.
Tools: Databricks, MLlib.
Steps:

Trained the model on consolidated data with features like premium payment history, policy type, and claim frequency.
Achieved high accuracy through iterative testing and optimization.

#3. Targeted Retention Strategies

Challenge: Retention efforts lacked personalization.
Solution: High-risk customers were targeted with personalized offers like premium discounts, extended coverage, and loyalty rewards.
Tools: Databricks, Tableau.
Steps:

Visualized churn risk using interactive Tableau dashboards.
Tracked the effectiveness of retention campaigns in real time.

Results

26% Reduction in Churn

Within six months of implementing the churn prediction and retention system, the company successfully reduced customer churn by 20%, resulting in an estimated annual revenue retention of $3.5 million.

35% Increase in Customer Engagement

Personalized retention strategies, such as premium discounts and loyalty rewards, led to a 35% boost in customer engagement metrics, including higher renewal rates and increased interaction with the company’s support and service channels.

15% Higher Retention Campaign ROI

The targeted retention campaigns achieved a 15% improvement in ROI compared to previous broad-based strategies, saving approximately $500,000 in marketing & retention costs annually.

Actionable Insights Delivered to 5+ Departments

The interactive Tableau dashboards provided actionable insights across five key departments, including marketing, customer service, and sales, empowering teams to make data-driven decisions and improve operations.

Tech Stack & Tools

Data Ingestion

Azure Data Factory (ADF) for automated ETL processes.

Optimization

Google OR-Tools for solving the Vehicle Routing Problem (VRP).

Visualization

Power BI for route visualization and monitoring.

Team Composition

Data Engineer : 2
Data Scientist : 2
Business Analyst : 1
Tableau Specialist : 1

Testimonials

Our Slam Book

Tony Lehtimaki

DIRECTOR - AMEOS

Spain

Very professional, accurate and efficient team despite all the changes I had them do. I look forward to working with them again.

Antoine de Bausset

CEO - BEESPOKE

France

They are great at what they do. Very easy to communicate with and they came through faster than I hoped. They delivered everything I wanted and more! I will certainly use them again!

Vivek Singh

MARKETING & SALES HEAD - VARMORA

Gujarat

I really liked their attention to detail and their sheer will to do the job at hand as good as possible beyond professional boundaries.

Nimesh Patel

DIRECTOR - COVERTEK CERAMICA

Gujarat

Excellent work, and on time with all goals. Communication was very easy, and knowledge of work was excellent. Will be working with them on upcoming projects. I highly recommend.

Craig Zappa

DIRECTOR - ENA PARAMUS

United States

"I would like to recommend their name to one and all. No doubt" their web app development services cater to all needs.

Neil Lockwood

CO-FOUNDER - ESR

Australia

Aglowid is doing a great job in the field of web app development. I am truly satisfied with their quality of service.

Daphne Christoforidou

CEO - ELEMENTIA

United States

Their team of experts jotted down every need of mine and turned them into a high performing web application within no time. Just superb!

Customer Churn Prediction and Retention for an Insurance Firm

Industry

Insurance

Project Type

Location

Timeline

Team Size