Skip to content

In insurance domain retention of customer is very important. Thus feedback mail sent to customers. In order to find retention rate it is very important to do the sentimental analysis on feedbacks. Here we are using multiple NLP libraries for doing the sentimental analysis and building a classification model.

Notifications You must be signed in to change notification settings

Mahesh3394/Claims-Feedback-Analysis

Repository files navigation

Claims-Feedback-Analysis

we can predict feedback given by customer as positive or negative.

Introduction:

As we know insurance becomes a important part of life after covid surge. Due to which insurance market grows exponentially. Also there are new market players entering in sector makes it is very competitive for old market players. As a role of service industry it is primary goal of every insurance company to look after customers reviews and feedbacks. As those positive feedbacks may result into further recommendation of insurance and ultimately result in growth of company. So it is very important to analyze feedbacks from customers.

Business problem.

We are provided with a dataset which contains feedback submitted by customers after settlement of claims. A record contains both categorical and continuous features. The target feature is promoter or detractor.

This is clearly a classification problem where target is numerical value and we have to predict class label by using given features. Also we already have target value in train data set so we can do supervised learning and train model on given data set.

As we can afford to take time to predict loss, there is no requirement of very low latency.

About

In insurance domain retention of customer is very important. Thus feedback mail sent to customers. In order to find retention rate it is very important to do the sentimental analysis on feedbacks. Here we are using multiple NLP libraries for doing the sentimental analysis and building a classification model.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published