Data Mining Technology and Its Role in Discovering Financial Fraud (Published)
The basis of any business – the customer database, which provides information about the client relationship with the company. The increasing complexity of organizational processes and rapidly changing business environment led to strong growth in domestic corporate data companies. In this regard, the increasing interest from the point of view of fraud risk assessments are beginning to provide tools such as data mining (Forensic Data Analytics – FDA), which allows you to narrow sample of suspicious transactions while minimizing the volume of checks. For example, in the field of communication in the database stores information about the conclusion of agreements for the use of services, the time of termination of the contract, a region rate, etc. The analysis revealed 7 out of 31 dentists who deliberately overstate the value of work performed by the insurance.
K-means algorithm using the algorithm of k-means as 4 clusters formed:
- Cluster 1: specialized work using expensive additional procedures, the average age of the client – 25, the average cost of services – $ 715;
- Cluster 2: minor works without the use of additional procedures, the average age of the client – 21, the average cost of services – $ 286;
- Cluster 3: Significant work using expensive additional procedures, the average age of the client – 38, the average cost of services – $ 819;
- Cluster 4: Significant work with cheap additional procedures, the average age of the client – 27, the average cost of services – $ 551.
Keywords: Cluster Algorithms, Data Miner., Data mining, Financial Fraud, K-Means Algorithm