• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Insurance Fraud Analytics Using Data Science and Machine Learning Tools

Student: Sorokina Anastasiia

Supervisor: Yuliya Mironkina

Faculty: Faculty of Economic Sciences

Educational Programme: Economics and Statistics (Bachelor)

Year of Graduation: 2020

The current study is dedicated to insurance fraud detection. According to most conservative estimations, fraudulent insurance claims constitutes 80 billion dollars annually across all lines of insurance. This results in losses to a company and drives the average level of insurance premiums up. Traditional methods such as “red flags” or business rules prove to be ineffective in the face of the data volume being collected and sophisticated nature of fraudulent scenarios in a whole. Today those are being replaced by advanced artificial intelligence algorithms and machine learning methods which are able to facilitate investigation time and improve the results. The present paper aims to research machine learning models for fraud detection and evaluate their performance on a life insurance dataset. Apart from that, the benefits of text mining for fraud detection are demonstrated by implementing topic modelling technique on the corpus of insurance claims’ descriptions. The obtained results show that incorporation of unstructured data into analysis improves the binary classification models’ performance. The authors conclude that integrated approach is preferable to be implemented by companies for insurance fraud detection.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses