Predicting Up-sell

A South African insurance company predicted customers with higher affinity to buy again.


rows of data

4 days

time to value


prediction accuracy


revenue growth


“Love the flexibility and how fast our junior data scientists can build models and run experiments.”

- Head of Data Science

A large insurance company based out of South Africa that provides various types of insurance plans to millions of users, was struggling to expand revenue on existing accounts.

The Data team was looking to build predictive models for customer up-sell and cross-sell. However, they had limited bandwidth to do data science in-house. That's when they decided to turn to Obviously AI.

The Solution

They conducted extensive market research and chose Obviously AI’s predictive analytics platform for their needs. 

The BI team used Obviously AI’s platform to train a model that helped predict which customers are likely to be upsold. The company just didn't settle there, they conducted several acid tests running over 100 models, in a span of couple of days. Then picked one that best matched their use case.

The Results

Obviously AI allowed the existing Data team to build the AI model within 4 days, versus 6 months it would require to do model building manually, and at a significantly lower cost.

Most notably, the company empowered their non-technical employees to make predictions using state of the art AI predictive analytics models, without the need to rely on a data science team all the time.

See how no-code machine learning can transform your business. Book a demo now!

Get Started Now

See how no code machine learning can transform your business and change how you make decisions.