Case Study
A Leading Transportation Agency Implements AI/ML to Enable Predictive Analytics
The solution modernizes forecasting around fare revenues and fleet maintenance.
Overview
The client is a leading governmental agency providing transportation services to millions of commuters in major cities and provinces. They are responsible for operating the various subway, bus, commuter rail, and other transportation solutions.
Challenge
The client was looking to enable real-time decisions on fleet scheduling and disseminating that information to the public. Additionally, they were looking to modernize their forecasting around fare revenues and fleet maintenance. They also wanted to standardize their AI/ML stack.
Solution
We were chosen as a partner for our strong credentials in Azure and our relationship with Microsoft. Ness worked closely with Microsoft to design and implement a greenfield Azure ML platform environment. The environment was delivered through Terraform Infrastructure-as-Code components, secured end-to-end with the native Azure service. Ness also created a comprehensive AI Operating Model based on 11 feature lenses and an associated AI Maturity Model.
Result
The client retired the bespoke AI/ML frameworks and infrastructure, resulting in significant cost savings. Our solution implemented AI/ML-based predictive fare estimation and fleet scheduling and provided 100% improvement in the current maturity level.