WEBINAR REPLAY 

Concept Drift: Monitoring Model Quality in Streaming ML Applications

With Emre Velipasaoglu, Principal Data Scientist at Lightbend, Inc.

About This Webinar

Most machine learning algorithms are designed to work with stationary data. Yet, real-life streaming data is rarely stationary. Machine learned models built on data observed within a fixed time period usually suffer loss of prediction quality due to what is known as concept drift.

The most common method to deal with concept drift is periodically retraining the models with new data. The length of the period is usually determined based on cost of retraining. The changes in the input data and the quality of predictions are not monitored, and the cost of inaccurate predictions is not included in these calculations.

A better alternative is monitoring the model quality by testing the inputs and predictions for changes over time, and using change points in retraining decisions. There has been significant development in this area within the last two decades.

In this webinar, Emre will review the successful methods of machine learned model quality monitoring.



WEBINAR REPLAY 

Concept Drift: Monitoring Model Quality in Streaming ML Applications

With Emre Velipasaoglu, Principal Data Scientist at Lightbend, Inc. and

About This Webinar

Most machine learning algorithms are designed to work with stationary data. Yet, real-life streaming data is rarely stationary. Machine learned models built on data observed within a fixed time period usually suffer loss of prediction quality due to what is known as concept drift.

The most common method to deal with concept drift is periodically retraining the models with new data. The length of the period is usually determined based on cost of retraining. The changes in the input data and the quality of predictions are not monitored, and the cost of inaccurate predictions is not included in these calculations.

A better alternative is monitoring the model quality by testing the inputs and predictions for changes over time, and using change points in retraining decisions. There has been significant development in this area within the last two decades.

In this webinar, Emre will review the successful methods of machine learned model quality monitoring.



SUBSCRIBE

SHARE

About Presenter

Emre Velipasaoglu, Principal Data Scientist at Lightbend, Inc.

Emre Velipasaoglu is a Principal Data Scientist at Lightbend. He has worked in various labs and start-ups as a researcher, scientist, engineer and manager for over 20 years, including several years at Yahoo! Labs as a senior scientist, where Emre and his team built the machine learning ranking models for Yahoo! Search. His expertise spans machine learning, information retrieval, natural language processing and signal processing. He holds a Ph.D. in Electrical and Computer Engineering from Purdue University.

About Presenters

Emre Velipasaoglu, Principal Data Scientist at Lightbend, Inc.

Emre Velipasaoglu is a Principal Data Scientist at Lightbend. He has worked in various labs and start-ups as a researcher, scientist, engineer and manager for over 20 years, including several years at Yahoo! Labs as a senior scientist, where Emre and his team built the machine learning ranking models for Yahoo! Search. His expertise spans machine learning, information retrieval, natural language processing and signal processing. He holds a Ph.D. in Electrical and Computer Engineering from Purdue University.

About Lightbend

Lightbend (Twitter: @Lightbend) provides the leading Reactive application development platform for building distributed systems. Based on a message-driven runtime, these distributed systems, which include microservices and streaming fast data applications, can effortlessly scale on multi-core and cloud architectures. Many of the most admired brands around the globe are transforming their businesses with our platform, engaging billions of users every day through software that is changing the world. For more information on Lightbend, visit: lightbend.com