A Machine Learning-based Approach for Medical Insurance Anomaly Detection by Predicting Indirect Outpatients' Claim Price

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Sharifi Garmdareh Mahdi; SOLEIMANI NEYSIANI BEHZAD; Zahiri Nogorani Mohammad; Bahramizadegan Mehdi

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2023 | Issue:9

Download Full-Text

View:

Download:

Information Seminar Paper

Title

A Machine Learning-based Approach for Medical Insurance Anomaly Detection by Predicting Indirect Outpatients' Claim Price

Author(s)

Sharifi Garmdareh Mahdi | SOLEIMANI NEYSIANI BEHZAD | Zahiri Nogorani Mohammad | Bahramizadegan Mehdi

Keywords

Regression

Fraud Detection

Deep Learning

Machine Learning

Medical Insurance

Anomaly Detection

Decision Tree

Abstract

About 10% of insurance claims are fraudulent according to published reports. Insurance companies can take a very robust approach to detect anomalies using Machine Learning techniques. This study proposes a new model based on Regression-based Machine Learning algorithms to predict the Total Price of a patient's claim based on the history of other patients, and then compare the estimated amount with the actual amount to obtain their price difference. The abnormal or fraud costs will be predicted in claims based on a threshold for the absolute price difference. A dataset of 99, 440 records of RASA web portal is gathered for evaluation. Deep Learning has the best mean absolute error (MAE) in the training phase, but the Decision Tree has the best MAE in the testing phase. So, the Decision Tree is used for Anomaly Detection, which can detect about 17% of records as abnormal with at least a 30% deviation. Expert human assessors check the results and approve more than 50% of reported anomalies.

Cites

No record.

References

No record.

Cite

APA: Copy

Sharifi Garmdareh, Mahdi, SOLEIMANI NEYSIANI, BEHZAD, Zahiri Nogorani, Mohammad, & Bahramizadegan, Mehdi. (). . . SID. https://sid.ir/paper/1046847/en

Vancouver: Copy

Sharifi Garmdareh Mahdi, SOLEIMANI NEYSIANI BEHZAD, Zahiri Nogorani Mohammad, Bahramizadegan Mehdi. . . Available from: https://sid.ir/paper/1046847/en

IEEE: Copy

Mahdi Sharifi Garmdareh, BEHZAD SOLEIMANI NEYSIANI, Mohammad Zahiri Nogorani, and Mehdi Bahramizadegan, “,” presented at the . , [Online]. Available: https://sid.ir/paper/1046847/en

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans

No record.

Recommended Workshops