{"slug":"epiroc-uses-azure-machine-learning-to-predict-steel-quality-and-cut-customer-returns-by-30-percent","url":"https://findausecase.com/use-cases/epiroc-uses-azure-machine-learning-to-predict-steel-quality-and-cut-customer-returns-by-30-percent","title":"Epiroc uses Azure Machine Learning to predict steel quality and cut customer returns by 30 percent","description":"Swedish equipment manufacturer Epiroc built an ESML AI Factory on Microsoft Azure Machine Learning and Azure Data Factory to create machine learning models for its steel heat-treatment process, predicting steel density, hardness and flexibility for rock drilling tools under various conditions. Epiroc reports the predictive models reduced customer rejections and product returns by 30 percent, and the company now runs eleven analytical teams' use cases in the shared AI factory.","company":"Epiroc","industry":"Manufacturing","country":"Sweden","aiCapabilities":["Predictive Analytics","Machine Learning"],"technology":["Azure Machine Learning","Azure Data Factory","Azure Databricks","Power BI","Microsoft Intelligent Data Platform"],"deployment":"Public Cloud","problemStatement":"Epiroc's manufacturing facilities around the world were not able to easily share data and best practices for consistency in steel quality. The company was collecting massive amounts of data at its locations but had no straightforward way to fully utilize it, creating inefficiencies and redundancies that sometimes impacted quality, resulting in customer equipment returns.","solutionApproach":"Epiroc created an ESML AI Factory on Microsoft Azure, using Azure Machine Learning, Azure Data Factory and Azure Databricks. Using ESML, an open-source solution accelerator created by Microsoft Sweden, and with help from Microsoft Cloud Partner Program member Molnbolaget, Epiroc quickly established the AI factory with secure private networking; the entire process took just 60 hours. The team also created machine learning models specifically for the heat treatment process with an end-to-end pipeline to the AI factory, all in just six weeks. The models predict steel density, hardness and flexibility for rock drilling tools under various conditions. Epiroc also had help from Microsoft Cloud Partner Program member Sogeti in running automation in AI governance.","businessValue":"Epiroc has reduced customer rejections and product returns by 30 percent, saving time and money. The company currently runs eleven analytical teams' use cases in the Epiroc worldwide ESML AI Factory utilizing Azure Machine Learning, with more planned in the coming year.","evidence":{"band":"high"},"sourceUrl":"https://www.microsoft.com/en/customers/story/1653030140221000726-epiroc-manufacturing-azure-machine-learning","dates":{"publishedAt":"2026-08-21T09:05:46.745Z","publishedAtSource":"pipeline","updatedAt":"2026-08-26T10:51:00.460Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/epiroc-uses-azure-machine-learning-to-predict-steel-quality-and-cut-customer-returns-by-30-percent. Bulk republication requires permission."}