Effective fault control mechanism for a huge device manufacturer in US and thus improving productivity in device operation.
A device manufacturer, with 200+ customers worldwide, has millions of mobile devices across all continents. They wanted to predict the devices at high chance of failure and proactively replace them to reduce downtime for their customers.
The client has sensors on each device which collects data from each device every hour. The data accumulated runs into billions of records. Our consultants built a machine learning algorithm to predict the device failure with an accuracy of more than 80%.
As a result, downtime was reduced by 20% and thus, leading to increased productivity for their clients.