Skip to content

Using government dataset to make predictions about finance related complains by customers using ML, NLP application built with airflow

License

Notifications You must be signed in to change notification settings

natek-1/finance_complaint_analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

finance_complaint_analysis

Problem Statement

Complaints can give us insights into problems people are experiencing in the marketplace and help us to undestand the reason and do necessary modification in exisiting financial product if required.

##Solution Proposed By understanding existing complaints registered against financial products we can create an ML model that can help us to identify newly registered complaints whether they are problematic or not and accordingly company can take quick action to resolve the issue, and satisfy the customer's need.

The problem is to identify registered complaint will be disputed by customer or not.

Tech Stack Used

Python PySpark PySpark ML Airflow as Scheduler MongoDB

Infrastructure Required.

GCP Compute Engine S3 Bucket Artifact Registry

Dashboarding

Grafana Prometheus Node Exporter Promtail Loki

About

Using government dataset to make predictions about finance related complains by customers using ML, NLP application built with airflow

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published