Bosch is a large manufacturing corporation that relies on high quality products to both gain and retain customers. The Bosch data science team was looking for a way to predict when parts on their product assembly lines would fail during production – these kinds of mishaps can cause costly product recalls and an overall drop in customer satisfaction. In addition, Bosch needed a way to communicate effectively across a global data science team to create this predictive models more rapidly and with the right stakeholders at hand.
Bosch’s data scientists had already developed proprietary predictive maintenance models in house, but needed a way to manage these models and push them into production in a more seamless fashion. Previously, these models were created by disparate data science teams, with no way of searching and auditing past work. Since different types of data are necessary to predict part failure, Bosch also needed a way to connect to and blend data from their database and Hadoop environments.
The Chorus Workflow Editor enabled Bosch’s data scientists to implement their existing models in a fully managed and central environment. Alpine’s Extensions SDK optimized their data transformation workflows to process large amount of complex manufacturing data faster. The project management features within Chorus made it easy to track the progress of models being created and pushed into production as well as bring the right stakeholders from across the business into the data science process.