Case
Assume that you are employed to help a credit card company to detect potential fraud cases so that the customers are ensured that they won’t be charged for the items they did not purchase. You are given a dataset containing the transactions between people, the information that they are fraud or not, and you are asked to differentiate between them. This is the case we are going to deal with. Our ultimate intent is to tackle this situation by building classification models to classify and distinguish fraud transactions.
Why Classification? Classification is the process of predicting discrete variables (binary, Yes/no, etc.). Given the case, it will be more optimistic to deploy a classification model rather than any others.
Steps Involved
- Importing the required packages into our python environment.
- Importing the data
- Processing the data to our needs and Exploratory Data Analysis
- Feature Selection and Data Split
- Building six types of classification models
- Evaluating the created classification models using the evaluation metrics
We are using python for this project because it is really effortless to make use of a bunch of methods, has an extensive amount of packages for machine learning, and can be learned easily. In recent days, the job market for python is seamlessly higher than any other programming language and companies like Netflix are using python for data science and many other applications. With that, let’s dive into the coding part.
#python #machine-learning #data-science
