Magnetic

Tampa Bay, FL www.magnetic.com
   
 
   
 

About Magnetic Engineering

At Magnetic, the Internet is our passion. As an established Digital Agency focused on Web Site Design & Internet Marketing company located in Tampa, Florida, we specialize in helping our clients transform the way the Internet works for their businesses. We build award-winning web sites and top-quality Internet solutions for both small and large businesses across a wide variety of industries. We also offer expertise in search engine optimization, web hosting, systems integration, and other Internet-related technologies.

Unknown author on

Information Theoretic Metrics for Multi-Class Predictor Evaluation

The most common metrics used to evaluate a classifier are accuracy, precision, recall and F1 score.

These metrics are widely used in machine learning, information retrieval, and text analysis (e.g., text categorization).Each of these metrics is imperfect in some way (captures only one aspect of predictor performance and can be fooled by a weird data set).None of them can be used to compare predictors across different datasets.

In this talk we present an information-theoretic performance metric which does not suffer from the aforementioned flaws and can be used in both classification (binary and multi-class) and categorization (each example can be placed in several categories) settings.
The code to compute the metric is available under the Apache open-source license:
https://github.com/Magnetic/proficiency-metric

This video was recorded at the NYC Machine Learning meetup at Pivotal Labs.

Join Us