{"id":182,"date":"2020-08-07T08:00:26","date_gmt":"2020-08-07T08:00:26","guid":{"rendered":"https:\/\/data-science.gotoauthority.com\/2020\/08\/07\/six-popular-classification-evaluation-metrics-in-machine-learning\/"},"modified":"2020-08-07T08:00:26","modified_gmt":"2020-08-07T08:00:26","slug":"six-popular-classification-evaluation-metrics-in-machine-learning","status":"publish","type":"post","link":"https:\/\/wealthrevelation.com\/data-science\/2020\/08\/07\/six-popular-classification-evaluation-metrics-in-machine-learning\/","title":{"rendered":"Six Popular Classification Evaluation Metrics In Machine Learning"},"content":{"rendered":"
\n
\"Evaluation\"Evaluation<\/span><\/div>\n
\n

Evaluation metrics are the most important topic in machine learning and deep learning model building. These metrics help in determining how good<\/strong> the model is trained. We are having different evaluation metrics for a different set of machine learning algorithms.<\/p>\n

For evaluating classification models we use classification evaluation metrics, whereas for regression kind of models we use the regression evaluation metrics.<\/p>\n

There are a number of model evaluation metrics that are available for both supervised and unsupervised learning<\/a> techniques.<\/p>\n

In this article, we will focus on what kind of model evaluation metrics are used in \u00a0quantifying the performance of the models built with supervised learning algorithms. <\/p>\n

In particular, we learn about different classification evaluation<\/strong> metrics.<\/p>\n

Before we go further let\u2019s list down the topics we are going to learn in this article.<\/p>\n<\/div>\n

\n

Supervised and Unsupervised Learning Algorithms<\/h2>\n

Supervised Learning Algorithms<\/h3>\n

Supervised Learning algorithms are only applicable to the dataset which has features as well as labels<\/strong>. For the given combination of feature, the expected target is called as label.<\/p>\n

For example, If we know the shape and color of the fruit. We can strongly say what fruit it could be. Here shape and color<\/strong> are the features and fruit type is target (label).<\/p>\n

Supervised learning algorithms further classified as two different<\/strong> categories.<\/p>\n