How a Seasoned Digital Mobility Provider cut down on Operational and Maintenance Costs

How a Seasoned Digital Mobility Provider cut down on Operational and Maintenance Costs

How a Seasoned Digital Mobility Provider cut down on Operational and Maintenance Costs


An established digital mobility service provider wanted to utilize predictive maintenance and continuous SOH monitoring to reduce unexpected breakdowns and downtime. Datakrew introduced an advanced AI/ML integrated solution to forecast potential issues to enable timely intervention.

Client Profile

Our client is a leading digital mobility solutions and services provider with almost 40 years of industry experience. They operate and maintain a wide and diverse fleet, and connect customers, drivers, and vehicles to deliver technology-enabled solutions that are safe, reliable, inclusive, and sustainable.


Our client’s pre-existing battery management system lacked the sophistication to accurately predict the State of Health of the batteries. This resulted in sub-optimal battery performance and frequent replacements, affecting the overall efficiency of their fleet. Additionally, the customer faced challenges in understanding how different usage patterns impacted the State of Health of their vehicle batteries.
The absence of predictive maintenance capabilities meant that the customer often dealt with unexpected vehicle downtimes and maintenance issues, which led to higher operational costs and reduced fleet availability.
notion image


Our EV Intelligence & Analytics solution includes a predictive maintenance module that utilizes Artificial Intelligence and Machine Learning to forecast potential maintenance issues before they occur. This feature helped in scheduling maintenance activities proactively, thus reducing unexpected downtimes.
Our sophisticated SOH Prediction Technology leveraged historical data, real-time analytics, and a multiphysics simulation model to provide accurate predictions about the battery's health and lifespan. Our solution also provided recommendations based on identifying usage patterns that negatively impacted battery health.


The predictive maintenance system lead to a significant reduction in unexpected vehicle downtimes, enhancing fleet availability and operational efficiency.
Accurate SOH predictions enabled the client to make informed decisions about battery maintenance and replacement, ensuring optimal performance and reducing overall operational costs.
With better predictive maintenance and SOH insights, the client’s fleet reliability improved, leading to increased satisfaction among their end-users and a stronger reputation in the market.


  • Increased End-User satisfaction
  • Reduced Unexpected Downtime
  • Considerably lowered Operational and Maintenance Costs