Case study Esure


Data fragmentation is the biggest problem for companies. Businesses today have online and offline data, and it happens that they do not have it connected. Companies want it to personalize and optimize the process, which fulfills them with all the most important corporate key performance indicators: higher sales and conversion rates, higher retention rates, lower churn rates, and greater customer satisfaction.

Business case

The reaching of all these KPIs resulted from more than 10 months of our ongoing cooperation with UK-based insurance company Esure. We joined their team with 10 data engineers and consultants and successfully deployed the solution for all their data and use cases by setting up the secure Databrics data platform on Amazon web services.


Esure has more than 3 million clients and collects both online and offline data. Online data are presented by activity on the website, third-party data, conversion funnel data, and the data connected with the ads displayed to the customer. To the offline data belong customer data (age, gender, etc.), insurance contract data, marketing communication (email), call center data, financial crime data (fraud), data from internal models (customer value, optimal price, etc.), claims, operational data.

The data in Esure have been stored on different platforms like Excel, database in Oracle, Salesforce, Adobe Analytics, SAS, and others. Thence the data science analytics was not applicable for these data. Additionally, basic insufficient reporting and analysis were done in a low-performance SAS system.


DataSentics, as the data machine learning partner, delivered the solution on the new easy-to-use modern cloud platform Databricks. This cloud data architecture was built for the client base to support and enable the use of the data science cases.

The first step was to merge the primary or raw data and clean them up—the second step led to stratifying all data into bronze, silver, and gold data.

Scheme: the Bronze layer contains raw data, the Silver layer contains filtered data, the Gold layer contains business data ready for reporting.

All raw data have been imported to Amazon Web Services cloud. Data stored in the Gold layer are now prepared to report customer retention, report the conversion funnel passage, and prepare data to calculate the customer's optimal discount.

Using of A/B testing reusable framework by DataSentics

A/B testing of the script for the call center helps exclude other influences and exactly shows the test results. It is automatic, reusable, and intended for business use. For the company Esure, A/B testing fulfills their needs to determine if the new team has better results than the previous one or if the new script is better than the old one.


  • Replaced SAS (data analytics) and Oracle (data warehouse) with a single data platform based on Databricks and AWS, the internal platform's onboarding.
  • Built datamarts for data models to optimize acquisition, improve retention, prevent churn, analyze claims and frauds.
  • Applied our AI A/B testing framework to improve the effectiveness of the call-center agents.
  • Speeded up the project by 30% thanks to our development framework.
  • Created transparent business-oriented data catalog and documentation.