Case Study: KONUX improves traceability and data consistency with Valohai

Ensuring Traceability and Eliminating Data Inconsistency

KONUX, a company that combines Industrial IoT and machine learning for railway maintenance, faced challenges with traceability and data inconsistency across their data science projects. With multiple long-running projects and a team encouraged to work independently, it was difficult to quickly find the latest datasets and models, hampering efficiency and collaboration. The human element in data collection also led to inconsistencies, making it hard to establish a reliable ground truth for their predictive maintenance models.

Utilizing Valohai's datasets feature, KONUX automated the programmatic creation of new dataset versions within their pipelines, eliminating manual errors and ensuring data consistency. This solution provided the team with a single source of truth, making it easy to find and use the latest datasets and models, which fostered collaboration and streamlined operations. As a result, KONUX is now prepared to scale their data collection by at least ten times without needing manual intervention.

KONUX

Andres Hernandez

Lead Data Scientist