In this video, we will outline some commonly used algorithms for building a classification model. After this video, you will be able to describe the goal of a classification algorithm and name some common algorithms for classification. Recall that a classification task is to predict the category from the input variables. A classification model processes the input data it receives and provides an output. Since classification is a supervised task, a target or desired output is provided for each sample. The goal is to get the model outputs to match the targets as much as possible. A classification model adjusts its parameters to get its outputs to match the targets. To adjust a model's parameters, a learning algorithm is applied. This occurs in a training phase when the model is constructed. There are many algorithms to build a classification model. In this course, we will cover the algorithms listed here, kNN or k Nearest Neighbors, decision tree, and naive Bayes. kNN stands for k Nearest Neighbors. This technique relies on the notion that samples with similar characteristics, that is samples with similar values for input, likely belong to the same class. So classification of a sample is dependent on the target values of the neighboring points. Another classification technique is referred to as decision tree. A decision tree is a classification model that uses a treelike structure to represent multiple decision paths. Traversing each path leads to a different way to classify an input sample. A naive Bayes model uses a probabilistic approach to classification. Baye's Theorem is used to capture the relationship between the input data and the output class. Simply put, the Baye's Theorem compares the probability of an event in the presence of another event. We see here the probability of A if B is present. For example, probability of having a fire if the weather is hot. You can imagine event B depending on more than one variable. For example, weather is hot and windy. We will cover kNN, decision tree and naive Bayes in detail in the next few lectures. There are many other classification techniques, but we will focus on these since they are fundamental algorithms that are commonly used and form the basis of other algorithms for classification.