Model efficacy

The main goal of model building in machine learning is generalization, which is how well the model will perform its intended objective. Generalization means how the model would perform on new unseen data, typically data in production. To estimate the generalization of a model, we need to test its performance based on unseen data. The mechanism to do it varies, depending upon the task at hand.

Classification

In this section, we will discuss the common ways to evaluate the efficacy of a classification model.

Confusion matrix

One of the most common and basic ways of evaluating a model's performance is by creating a confusion matrix and computing various metrics such as accuracy, precision, recall, and so on. We will start with an example for two class classifiers to understand the concepts, and then extend it to problems involving more than two classes.

The confusion matrix is as follows:

Classifier		Predicted
Classifier				Negative	Positive
Actual	Negative	A	B ...

Tech Concepts

Programming languages

Tech Tools

Unlimited access to the largest independent learning library in tech of over 8,000 expert-authored tech books and videos.

Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.

50+ new titles added per month and exclusive early access to books as they are being written.

Learning Apache Mahout

By : Chandramani Tiwary

Learning Apache Mahout

By: Chandramani Tiwary

Overview of this book

Model efficacy

Classification

Confusion matrix

Learning Apache Mahout

By : Chandramani Tiwary

Learning Apache Mahout

By: Chandramani Tiwary

Overview of this book

Model efficacy

Classification

Confusion matrix

Confirmation

Buy this book with your credits?

Submit Your Feedback

Create a Free Account To Continue Reading

Sign in to activate your 7-day free access