Skip to main content

Task 2: Explore datasets

Let's explore the dataset to understand each column.

  1. In the DATASETS page, observe the two datasets we will use for this tutorial.
  2. Click the consumer_complaint_resolution_train.csv dataset and select the DETAILS option.
  3. Let’s take a quick overview of the columns of the training dataset:

  • The dataset consists of 18 columns which are as follows: Dataset 1 a. Date received - Date when the complaint was received
    b. Product - Type of product identified in the complaint, e.g., “Student loan”
    c. Sub-product - Type of sub-product identified in the complain
    d. Issue - The issue raised in the complaint, e.g., “Struggling to repay your loan.”
    e. Sub-issue - The sub-issue, e.g., “Problem lowering your monthly payments.”
    f. Consumer complaint narrative - This is a consumer-submitted description of “what happened”.
    g. Company public response - The response to a consumer’s complaint. It can be from a pre-set list of options, e.g., “Company believes the complaint is the result of an isolated error”

  • Continue scrolling to the right of the page to view the rest of the columns of the dataset: Dataset 2 h. Company - For which the complaint is about
    i. State - Derived from the consumer’s mailing address
    j. ZIP Code - Derived from the consumer’s mailing address
    k. Tags - Provides additional context about the complaint. These tags help in categorizing complaints based on the demographics of the complainant
    l. Consumer consent provided - Flag to specify whether the consumer allowed the publishing of their complaint description
    m. Submitted via - E.g., “Web” or “Phone.”
    n. Date sent to the company - The date the complaint was sent to the company Dataset 3 o. Company response to consumer - Records how the company addressed each consumer complaint
    p. Timely response - Flag specifying if the response was timely
    q. Consumer disputed - Flag specifying if the consumer disputed the resolution
    r. Complaint ID - Identifier for each complaint

  1. Return to the Datasets page.

Now that you understand each column of the dataset, in Task 3, we will learn how to set up the experiment from scratch.

Feedback