tesa SE is a global adhesive manufacturing company. In their highly automated tape production process it's needed to observe quality and effiency abnormal events with very short latency to avoid high costs.

Utilizing Snowflake's Machine Learning capabilities, Tesa SE is monitoring various KPI's that indicate the correct production process.

Tesa's newest innovative usecase aims to decrease waste during the production process using anomaly detection methodologies, which are trained on Snowflake, and used for inference on-edge for optimal latency.

The machine learning model pipeline components are built and served leveraging Snowflake features such as Snowflake CLI, Snowpark Pandas and other Snowflake capabilities to streamline the overarching ML process.

Modern data engineering leverages Python to build robust, scalable, end-to-end workflows. In this talk, we will cover how Snowflake offers you a flexible development environment for developing Python data pipelines, performing transformation at scale, orchestrating and deploying your pipelines at scale. Topics we’ll cover include: – Ingest: Data source APIs, Snowflake file-to-read and ingest data of any format when files arrive, with sources outside Snowflake – Develop: Packaging (artifact repo), Python runtimes, IDE (Notebook, vscode) – Transform: Snowpark pandas, UDFs, UDAFs – Deploy: Tasks, Notebook scheduling