Fraud-Insurance-claim--detection

---

Financial frauds are associated with sophisticated urban areas. But when it comes to insurance frauds, rural India has taken the lead due to various reasons. While baby steps like a fraudster database is being taken, such malpractices may not be contained without strict punishments under penal code

Insurers have identified at least 80 districts across the country which have excelled in fraudulent claims over the past decade. They have identified rings that operate with the efficiency of a corporation with well-trained men and women who collect data with the efficiency of a 21st century start-up.

A combination of poor due diligence in writing policies by insurance companies and the organisational efficiencies of criminals in identifying those who are on deathbed and in enlisting do.

---

Objective

The traditional approach for fraud detection is based on developing heuristics around fraud indicators. Based on these heuristics, a decision on fraud would be made in one of two ways.

• In certain scenarios rules would be framed that would define if the case needs to be sent for investigation.
• In other cases, a checklist would be prepared with scores for the various indicators of fraud. An aggregation of these scores along with the value of the claim would determine if the case needs to be sent for investigation.

Libraries used :

  * pandas
  * numpy
  * matplotlib
  * plotly
  * cufflinks

Algorithms Used

The Algorithms used are :

* decision tree
* kNN
* kMeans clustering
* RandomForestClassifier

Hence, Machine Learning can saves Million of $ Dollars.

Developed by : Kanishk sharma