For a financial company, customer complaints carry a lot of importance, as they are often an indicator of the shortcomings in their products and services. If these complaints are resolved efficiently in time, they can bring down customer dissatisfaction to a minimum and retain them with stronger loyalty. This also gives them an idea of how to continuously improve their services to attract more customers.
These customer complaints are unstructured text data; so, traditionally, companies need to allocate the task of evaluating and assigning each ticket to the relevant department to multiple support employees. This becomes tedious as the company grows and has a large customer base.
In this case study, you will be working as an NLP engineer for a financial company that wants to automate its customer support tickets system. As a financial company, the firm has many products and services such as credit cards, banking and mortgages/loans.
You need to build a model that is able to classify customer complaints based on the products/services. By doing so, you can segregate these tickets into their relevant categories and, therefore, help in the quick resolution of the issue.
Apply topic modeling to map each ticket to one of the following categories based on their products/services :
-
Credit card / Prepaid card
-
Bank account services
-
Theft/Dispute reporting
-
Mortgages/loans
-
Others
After mapping, use the labelled data to train a supervised model. Using this trained model, you can classify any new customer complaint support ticket into its relevant department.
The data set given to you is in the .json format and contains 78,313 customer complaints with 22 features. You need to convert this to a dataframe in order to process the given complaints.