Outlining Our Data Set and Business Problem

Hey - Nick here! This page is a free excerpt from my $199 course Python for Finance, which is 50% off for the next 50 students.

If you want the full course, click here to sign up.

Over the next several sections of this course, you will build an artificial neural network from scratch.

This tutorial will first outline how you can download the data set, what the data set contains, and what business problem we will use the data set to solve.

Table of Contents

You can skip to a specific section of this deep learning tutorial using the table of contents below:

How To Download The Data Set

Click here to download the data set associated with the artificial neural networks section of this course.

What Our Data Set Contains

Once the data set is downloaded, you can open it up using spreadsheet software such as Microsoft Excel.

It will look like this:

Our example data set

This data set has several columns, including:

  • RowNumber
  • CustomerId
  • Surname
  • CreditScore
  • Geography
  • Gender
  • Age
  • Tenure
  • Balance
  • NumOfProduct
  • HasCrCard
  • IsActiveMember
  • EstimatedSalary
  • Exited

This data set comes from a hypothetical financial institution. It is fairly large and has approximately 10,000 entires.

Due to its size and high dimensionality, this data set can be harnessed by deep learning techniques to solve a number of fascinating business problems.

We explore one of these problems in the next section of this tutorial.

The Business Problem We Are Trying To Solve

Churn is the business term used to describe the event of a customer ending its relationship with a business.

The hypothetical bank that has issued our data set has experienced higher-than-normal churn lately. You have been hired to analyze this data set and especially its churn. More specifically, the bank would like you to identify the customers in the database that have the highest risk of churning.

Final Thoughts

This tutorial outlined the data set we will use to build our first artificial neural network.

Here is a brief summary of the information discussed in this article:

  • How to download the data set we'll use to build our artificial neural network
  • What the data set contains
  • The business problem (churn) that our model hopes to address