# Metrics

This category groups posts on metrics used in machine learning. Each post focuses on a specific metric. The emphasis is on understanding how these tools actually work at a technical level. Here you will learn how to use machine learning metrics so that you can properly assess, and interpret, your models performance.

## A Simple Introduction to Cross Entropy Loss

Cross Entropy serves as a loss function, in the context of machine learning classification problems. Learn all about the Cross Entropy Loss here.

## Median Absolute Error

Mean Squared Error What is the Median Absolute Error? The Median Absolute Error is a metric that can be used to quantify a regression models performance. This measure is slightly more difficult to interpret for a non-technical audience. However, the main benefit of using this quantity is its strong resilience to outliers. This is in

## How to Measure Information Gain in Decision Trees

Can Decision Trees Handle Missing Values? For classification problems, information gain in Decision Trees is measured using the Shannon Entropy. The amount of entropy can be calculated for any given node in the tree, along with its two child nodes. The difference between the amount of entropy in the parent node, and the weighted average

## Precision@k and Recall@k Made Easy with 1 Python Example

Understanding Backpropagation For those who prefer a video presentation, you can see me work through the material in this post here: https://youtu.be/WEJcETfWwOo What are Precision@k and Recall@K ? Precision@k and Recall@k are metrics used to evaluate a recommender model. These quantities attempt to measure how effective a recommender is at providing relevant suggestions to users. The

## Explaining the Gini Impurity with Examples in Python

Can Decision Trees Handle Missing Values? This article will cover the Gini Impurity: what it is and how it is used. To make this discussion more concrete, we will then work through the implementation, and use, of the Gini Impurity in Python. What is the Gini Impurity? The Gini Impurity is a loss function that

## A Complete Introduction to Cross Validation in Machine Learning

How Neural Networks Learn, with 1 Complete Example This post will discuss various Cross Validation techniques. Cross Validation is a testing methodology used to quantify how well a predictive machine learning model performs. Simple illustrative examples will be used, along with coding examples in Python. What is Cross Validation? A natural question to ask, when building

## 6 Methods to Measure Performance of a Classification Model

Neural Networks Explained Simply In this post, we will cover how to measure performance of a classification model. The methods discussed will involve both quantifiable metrics, and plotting techniques. How do we Measure Performance of a Classification Model? Classification is one of the most common tasks in machine learning. This is the case where the

## Coefficient of Determination

Mean Absolute Error Introduction The Coefficient of Determination is a metric for evaluating the goodness of fit for a linear regression model. This quantity is often defined as:    (1) where is the sum of squared errors, and is the sum of squared total variance. Let’s define these, along with the sum of squared regression

## Mean Squared Error

Mean Squared Error Introduction In this post we’ll cover the Mean Squared Error (MSE), arguably one of the most popular error metrics for regression analysis. The MSE is expressed as:    (1) where are the model output and are the true values. The summation is performed over individual data points available in our sample. The advantage

## Bias and Variance

Mean Squared Error Introduction Machine learning models are developed primarily to produce good predictions for some desired quantity. What we want is a model that can generalise well the patterns in our data in order to make reasonable predictions. Two important measures of how well a model generalises are bias and variance: Bias is the tendency