Description of the problem

Lending Club strives to connect borrowers with investors through our online marketplace.

The goal is to predict the interest rates that Lending Club should use, based on previous borrowers data they have. Whether or not a client will repay a loan or have difficulty is a critical business need. In this project, we are going to see some models that the machine learning community can develop to help organizations like Lending Club.

What you will build

• A simple Flask app to deploy the machine learning model

What you will learn

• Module 4: How to deploy your machine learning app as a REST web service.

The web service is primarily written using the Flask framework in python with a bit of HTML and CSS.

• pandas
• numpy
• matplotlib
• seaborn
• scipy
• Sklearn
• Pickle
• Flask
• wtforms

Once you have finalized the model, pickle each model separately and save it. Also, we need to pickle some important metrics from the data, like the max and min values and the different features and their categories.

These will be required to convert the categorical user inputs to numerical and normalise the the features so that they can be fed to the model.

Running the app from QuSandbox.

• Go to the running Tasks page on QuSandbox.
• Click on the green launch button.
• A pop-up will appear.
• Click in the Launch button again and you will be redirected to the app.

This is your app home page.

Fill in the required details. You can select which of the 3 models that we have created you want to use for prediction. Hit Submit.

You will get the predicted interest rate for the given user profile.