Cloud-based Machine Learning Solution Drives 2.3% Revenue Uplift for FinTech Unicorn

Summary

A global InsurTech was looking to improve the performance of device protection sales at cell phone retailers across Indonesia. The company connects insurers with customers via businesses, and this case study focuses on the travel efficiency and effectiveness of sales ambassadors. These individuals visit cell phone stores to deliver staff training on the insurance benefits, supporting the in-store sales process. Amdocs Cloud Studio was engaged to devise a data-driven solution to improve travel planning using cloud-based data analytics platform Databricks.

• Amdocs Cloud Studio data scientists designed and implemented a sophisticated MLOps workflow to optimize and automate route planning.
• Time sales ambassadors spend in non-productive travel has been reduced by 3.5%.
• Optimization of cell phone store visits has resulted in a 2.3% revenue increase. 

Challenge

Automated Route Planning was a Non-trivial Data Challenge 
The sales team’s manual approach to route planning meant travel was inefficient and costly, with decisions about the frequency and prioritization of store visits made subjectively. A data-driven solution was needed to reduce travel time, strategically prioritize stores, and ensure optimal coverage of stores to drive an uplift in sales revenue.

Addressing this challenge demanded more than a simple route optimization algorithm. The 100-plus sales team works across the Indonesian archipelago, so the solution had to account for multiple start points and destinations as well as traffic patterns in various towns and cities and the opening times of different stores. In addition, some stores were more strategically important than others. Many required several visits in a given monthly schedule, which needed to be spaced out effectively.

With so many varied factors, the development and implementation of automated route planning was a non-trivial challenge. Since in-house cloud and data experts are focused on the company’s core digital ecosystem, external assistance was required for this AI-driven sales optimization project.

Amdocs Cloud Studio was engaged to support the transition from subjective travel planning to an objective, data-driven approach. This involved designing an ML model then deploying it on the InsurTech’s AWS-hosted unified analytics platform, Databricks. Our goal was to provide automated, optimized travel schedules for each individual sales ambassador, taking into account the many variables noted above.  

Solution

End-to-end ML Model Deployed on Databricks using MLOps 
Amdocs Cloud Studio’s expert data scientists devised a sophisticated ML algorithm for deployment on Databricks using MLOps practices.

The algorithm covers all variables associated with the sales team’s route planning. Minimizing travel time and maximizing the time spent productively in cell phone stores involves a two-step process. Firstly, a ‘store importance’ value calculation prioritizes which stores a sales ambassador should visit in a given month, and how many times. Then, a ‘route optimization’ calculation determines the order in which they should be visited, given store opening hours, travel distance, traffic congestion, travel time (via a maps API), start and destination points, salesperson working hours, and home location.  

The algorithm’s complexity made it very compute-intensive, so Amdocs Cloud Studio’s data scientists creatively optimized it for efficiency and to reduce cloud costs. Leveraging core aspects of Databricks’ functionality in the MLOps workflow has enabled scalability and further cost optimization. Governance and security are also enhanced through integration into the MLOps processes.

Finally, we established best practice MLOps methodologies for deployment on Databricks, which the InsurTech now uses for all ML use cases.