🔗 View code on Github
Description
Assuming I work as a data scientist at a bank and I’ve been tasked with predicting what the probability is that a customer at the end of the month can’t pay their credit card bills and that, Therefore, that our bank can be advanced by putting considerable limits, I undertook this new project.
In this case I used the AWS SageMaker Studio tool, as the SageMaker Studio interface allows to carry out machine learning algorithms.
In this way, it allowed me to carry out the creation, training and even deployment of the model. By using these SageMaker productivity tools from Amazon, I understood that we can automatically create environments by configuring model parameters, inputs, outputs, the artificial intelligence artifact in one place.
In this project I applied the theory about gradient boosting and trees using the XGBoost how to create, build, train and deploy a model based on gradient boosting technology and that I carry out regression tasks, prediction, the probability that those customers will not be able to meet their bills by the end of the month.