Case Study
How we helped our client achieve cost-savings and minimize downtime through an approach that could determine the condition of each individual service equipment in real-time.
Machines often form the backbone of businesses, and machinery breakdowns are inevitably costly. In response to the challenge, companies have explored a variety of strategies and tools – even preventive maintenance programs – to increase machine uptime. But mostly these tools only generate a wealth of data which is not often aggregated, unified, analyzed, or acted upon.
The real challenge for our client, a large ATM manufacturer, was to determine the actual condition of each individual in-service equipment to predict when maintenance should be performed? When Infosys was asked to provide a solution, we leveraged our Insights-as-a-Service offering to curate information from machines – like the one that must be maintained – from across a wider landscape. For example, we curated four million failure ticket records from over 8,500 ATMs to develop, train, and test a machine learning model for predicting ATM failure in North America.
The result?
99%
machine availability guaranteed
18%
reduction in costs of unwarranted preventive maintenance and repair
14.3%
increase in operational efficiency
60
milliseconds is the time our algorithms take to predict machine fault with 80% accuracy
