The performance of machine learning models can decline over time - due to changes in data, business processes, or simply data loss or failures. To avoid the negative impact on business performance, it is crucial to detect such situations and take timely action - for example, by retraining the model. Due to this, monitoring of services based on machine learning needs to include additional metrics related to the model and data quality. In the course of the tutorial, Emeli Dral will demonstrate how the quality of a model can change over time, and how one can track and analyze the changes using open source tools.
Emeli Dral is a Co-founder and CTO at Evidently AI, a startup developing open-source tools to analyze and monitor the performance of machine learning models. Earlier, she co-founded an industrial AI startup and served as the Chief Data Scientist at Yandex Data Factory. She led over 50 applied ML projects for various industries - from banking to manufacturing. Emeli is a data science lecturer at GSOM SpBU and Harbour. Space University. She is a co-author of the Machine Learning and Data Analysis curriculum at Coursera with over 100,000 students. She also co-founded Data Mining in Action, the largest open data science course in Russia.