Scoring customer leads at nib

nib is a health and medical insurance provider in Australia with approximately 1,500 employees and over 1.6 million members

Business challenge

  • The nib website provides an online quote service that enables potential members to browse insurance products 
  • nib wanted to determine the likelihood that a person using the quote service would purchase an insurance product, and provide this information to the sales team for follow-up
  • nib’s data science team were seeking support to deploy the model, integrate with downstream systems, and ensure performance was optimised for production

Success critera

  • Optimise the speed and accuracy of the existing model to ensure it was ready for production use
  • Engineer an end-to-end pipeline to deploy the model to production and enable future model enhancements to be released quickly and without risk 
  • Integrate the output of the model with Tealium (nib’s member data hub) to enable the sales team to focus on a refined subset of potential members who are most likely to buy
  • Empower the nib data science team to maintain and administer the service after hand-over 

Solution

  • Eliiza’s data scientists were able to optimise the model for performance in production without compromising accuracy
  • Amazon SageMaker was selected for this project as it enabled integration with all other AWS services and external platforms (Tealium, Snowflake and Databricks)
  • Eliiza’s machine-learning engineers containerised and deployed the model in nib’s AWS environment through the use of SageMaker. This provided nib with an automated, end-to-end pipeline making future  model enhancements easy and low-risk to deploy 
https://eliiza.com.au/wp-content/themes/salient/css/fonts/svg/basic_webpage_img_txt.svg

Individuals engage with nib online quote service

https://eliiza.com.au/wp-content/themes/salient/css/fonts/svg/ecommerce_graph2.svg

Data related to
sales conversion captured

https://eliiza.com.au/wp-content/themes/salient/css/fonts/svg/basic_elaboration_cloud_refresh.svg

Model runs predictions on Amazon SageMaker

https://eliiza.com.au/wp-content/themes/salient/css/fonts/svg/basic_todolist_pen.svg

Individuals are scored by the model, based on likelihood to join

https://eliiza.com.au/wp-content/themes/salient/css/fonts/svg/basic_headset.svg

nib sales team focus on certain individuals, as suggested by the model

Outcomes

  • In 4 weeks Eliiza optimised and deployed nib’s customer leads model using SageMaker
  • Eliiza worked with the nib data science team to upskill them on the model deployment process and tooling enabling them to run and optimise the service
  • Provided the nib data science team with training and documentation so they could maintain and administer the service after hand-over

Contact Us

We’re always keen to start conversations on how AI can help solve real-world problems, or opportunities for technology to impact people in a positive way.

Contact Eliiza