Introduction to Classification Models

Ever wonder what classification models do? In this quick introduction, we talk about what classifications models are, as well as what they are used for in machine learning. In machine learning there are many different types of models, all with different types of outcomes. When it comes to classification or statistical classification, the model is trying to identify two or more determined classes, i.e. Apples and Bananas, and classify them accordingly. Usually, these models have been trained using a training set.

Welcome to this short introduction to classification models. What are
classification models? In machine learning there are many different models
all with different types of outcomes. Classification models are machine
learning models that predict a class type outcome. In other words a
classification model predicts any kind of category or class such as apples and bananas.
A classification model uses attributes of a person or any kind of
entity to predict the entities class, for example Class A might be apples and
Class B might be bananas. The attributes of apples and bananas could be their
shape their dimensions and their color. These data points could be used to
predict the class outcome of it likely being an apple or a banana
differentiating apples from bananas based on their own unique attributes
this means the model learns that certain attributes belong to a certain
categories or classes for example if it’s colored yellow is six to eight
inches long one to two inches wide and it’s crescent-shaped then these
attributes are more likely to belong to a banana than an apple.
The model makes a prediction that given these attributes the fruit is likely to be a banana
similarly if it purrs has fur and whiskers and is found in every corner of
the internet then it’s likely a cat; if a croaks, has feathers and wings, and is found
on farms, it is likely a rooster. A classification model learns that these
attributes belong to a certain categorical outcome in a supervised way
where it directly maps the data points to a class label.
The class label can be binary such as positive or negative, whether a disease is present or not,
whether the customer is a returning customer or not, or whether the job
applicant was a success or fail or the class label could be multiple classes
such as easy, intermediate, and advanced level in a game, or all types of fruits from
peaches, oranges, and kiwi, not only apples and bananas
some key algorithms used in classification models include decision trees,
naïve bayes, support vector machines, and neural networks, which you can learn
about these in future videos. They all take different approaches to predicting
a class outcome. And that quickly sums up classification models for you! Thanks for
watching, give us a like if you found this useful, or you can check out our
other videos at Data Science Dojo Tutorials.

Learn more about Classification Models:
Introduction to the Confusion Matrix
Precision, Recall and F1 in Classification
One Versus One vs. One Versus All in Classification

Complete Series:
Data Science in Minutes

More Data Science Material:
[Video] One vs. One versus One vs. All
[Video] Data Attributes: Data Mining Fundamentals
[Blog] A Comprehensive Tutorial on Classification Using Decision Trees


Rebecca Merrett
About The Author
- Rebecca holds a bachelor’s degree of information and media from the University of Technology Sydney and a post graduate diploma in mathematics and statistics from the University of Southern Queensland. She has a background in technical writing for games dev and has written for tech publications.


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>