The Private Healthcare Insurance sector: A victim of fraud

Regardless of the jurisdiction research has repeatedly highlighted that the ‘public’ see the insurance sector as an acceptable business to defraud. This article builds on this work but is different in that we draw on primary research, of which there is little, into the private healthcare insurance sector as a victim of fraud. We start by highlighting the types and volumes of fraud that the insurance sector encounters. This is followed with an examination of policing private insurance fraud in a neo-liberal context where individuals and organisations are responsible for risks. Then, we consider if the private healthcare insurance sector is precipitating and participating in its own victimisation. The methods used in this research to secure data are then explained. Finally we analyse how the key elements of the data might point to the private healthcare insurance sector potentially precipitating and participating in its own victimisation.

Phenomenon of Causal Fraud Health Insurance in Hospitals: Theory of gear fraud

Objective: To describe and explore the experiences of hospital employees with the causes of fraud in the health insurance program at the hospitals. Design And Setting: This research was carried out at government hospitals in the Southeast Sulawesi Province in collaboration with BPJS Health, namely the Bahteramas Regional General Hospital and the Kendari City Regional General Hospital. Triangulation was carried out at BPJS Health, the Center for Health Insurance Financing at the Ministry of Health and the Center for Health Policy and Management at Gadjah Mada University, Yogyakarta. This research was conducted for one year, namely January 2020 to February 2021qualitative method with a phenomenological approach. Data collection methods were carried out through in-depth interviews, focus group discussions, and document studies. The number of participants in this study was 44 people consisting of doctors in charge of services, nurses, midwives, and case-mix team including coders who met the inclusion criteria. Data analysis used the Moustakas method. Result: The causes of health insurance fraud in hospitals financial motives (the desire to get money or material or economic or welfare benefits, get high service services and low employee salaries), behavioral motives (low integrity, lifestyle and employee habits of committing fraud0, and social motives (kinship, humanitarian factors, avoiding conflict, social position, and the existence of pressure), internal controls (a weak monitoring system, poorly enforced regulations, unclear regulations and limited hospitals providing services, no monitoring and evaluation, and there are no sanctions for fraud perpetrators), revenue targets (hospitals income and increasing the number of claims), leadership (leadership style or weak leadership in the hospitals and the absence of transparency), incentive systems (poor distribution of incentives and the absence of transparency of services from hospitals management), National Health Insurance (NHI) regulations (dynamic regulations and the availability of the National Guidelines for Medical Services has not been fulfilled and there is no standard for readmission and fragmentation), the NHI financing system (inconvenience of the financing system and the adequacy of the INA-CBGs tariff calculation), and the BPJS Health system (inconvenience of the BPJS Health system and the BPJS Health system which makes it difficult). Conclusions: The causes of health insurance fraud in hospitals can be explained by the gear fraud theory that Internal factors are the main cause and external factors predispose to health insurance fraud in hospitals. These internal and external factors interact with each other like the working mechanism of a gear. Understanding the theory of gear fraud will help formulate fraud prevention efforts in health insurance programs in hospitals that are more comprehensive and focus on eliminating the causes of fraud.

Research on automobile insurance fraud identification based on fuzzy association rules

With the development of automobile insurance industry, how to identify automobile insurance fraud from massive data becomes particularly important. The purpose of this paper is to improve automobile insurance fraud management and explore the application of data mining technology in automobile insurance fraud identification. To this aim, an Apriori algorithm based on simulated annealing genetic fuzzy C-means (SAGFCM-Apriori) have been proposed. The SAGFCM-Apriori algorithm combines fuzzy theory with association rule mining, expanding the application scope of the Apriori algorithm. Considering that the clustering center of the traditional fuzzy C-means (FCM) algorithm is easy to fall into local optimal, the simulated annealing genetic (SAG) algorithm is used to optimize it. The SAG algorithm optimized FCM (SAGFCM) is used to generate fuzzy membership degrees and introduces fuzzy data into the Apriori algorithm. The Apriori algorithm is improved by reducing the rule mining time when acquiring rules. The results of empirical studies on several data sets demonstrate that the optimization of FCM by SAG can effectively avoid the local optimal problem, improve the accuracy of clustering, and enable SAGFCM-Apriori to obtain better fuzzy data during data preprocessing. Moreover, the proposed algorithm can reduce the mining time of association rules and improve mining efficiency. Finally, the SAGFCM-Apriori algorithm is applied to the scene of automobile insurance fraud identification, and the automobile insurance fraud data is mined to obtain fuzzy association rules that can identify fraud claims.

Insurance Fraud in Korea, Its Seriousness, and Policy Implications

Several characteristics of insurance fraud including its chronic nature justifies the need for identifying feasible proposals which can be expected to bring about significant impacts. Recent statistics show that insurance fraud is now consistently on the increase. However, insurance fraud is highly fragmented and each offence is not significant enough to elicit active interest among the public or interventions from the police. Three problems have been identified and diagnosed. These were a lack of awareness, an absence of a national leadership and also limited attention directed to insurance fraud by the investigating authorities. Based on these, three recommendations have been suggested. (1) Embarking on and developing a national initiative by central government, (2) Taking a dynamic concentration approach to send deterrent threats to potential fraudsters, and (3) Using big data technologies to detect clandestine activities by organised groups.

An Effective Data Sampling Procedure for Imbalanced Data Learning on Health Insurance Fraud Detection

Fraud detection has received considerable attention from many academic research and industries worldwide due to its increasing popularity. Insurance datasets are enormous, with skewed distributions and high dimensionality. Skewed class distribution and its volume are considered significant problems while analyzing insurance datasets, as these issues increase the misclassification rates. Although sampling approaches, such as random oversampling and SMOTE can help balance the data, they can also increase the computational complexity and lead to a deterioration of model's performance. So, more sophisticated techniques are needed to balance the skewed classes efficiently. This research focuses on optimizing the learner for fraud detection by applying a Fused Resampling and Cleaning Ensemble (FusedRCE) for effective sampling in health insurance fraud detection. We hypothesized that meticulous oversampling followed with a guided data cleaning would improve the prediction performance and learner's understanding of the minority fraudulent classes compared to other sampling techniques. The proposed model works in three steps. As a first step, PCA is applied to extract the necessary features and reduce the dimensions in the data. In the second step, a hybrid combination of k-means clustering and SMOTE oversampling is used to resample the imbalanced data. Oversampling introduces lots of noise in the data. A thorough cleaning is performed on the balanced data to remove the noisy samples generated during oversampling using the Tomek Link algorithm in the third step. Tomek Link algorithm clears the boundary between minority and majority class samples and makes the data more precise and freer from noise. The resultant dataset is used by four different classification algorithms: Logistic Regression, Decision Tree Classifier, k-Nearest Neighbors, and Neural Networks using repeated 5-fold cross-validation. Compared to other classifiers, Neural Networks with FusedRCE had the highest average prediction rate of 98.9%. The results were also measured using parameters such as F1 score, Precision, Recall and AUC values. The results obtained show that the proposed method performed significantly better than any other fraud detection approach in health insurance by predicting more fraudulent data with greater accuracy and a 3x increase in speed during training.

Fourteen years of manifestations and factors of health insurance fraud, 2006–2020: a scoping review

Background Healthcare fraud entails great financial and human losses; however, there is no consensus regarding its definition, nor is there an inventory of its manifestations and factors. The objective is to identify the definition, manifestations and factors that influence health insurance fraud (HIF). Methods A scoping review on health insurance fraud published between 2006 and 2020 was conducted in ACM, EconPapers, PubMed, ScienceDirect, Scopus, Springer and WoS. Results Sixty-seven studies were included, from which we identified 6 definitions, 22 manifestations (13 by the medical provider, 7 by the beneficiary and, 2 by the insurance company) and 47 factors (6 macroenvironmental, 15 mesoenvironmental, 20 microenvironmental, and 6 combined) associated with health insurance fraud. We recognized the elements of fraud and its dependence on the legal framework and health coverage. From this analysis, we propose the following definition: “Health insurance fraud is an act of deception or intentional misrepresentation to obtain illegal benefits concerning the coverage provided by a health insurance company”. Among the most relevant manifestations perpetuated by the provider are phantom billing, falsification of documents, and overutilization of services; the subscribers are identity fraud, misrepresentation of coverage and alteration of documents; and those perpetrated by the insurance company are false declarations of benefits and falsification of reimbursements. Of the 47 factors, 25 showed an experimental influence, including three in the macroenvironment: culture, regulations, and geography; five in the mesoenvironment: characteristics of provider, management policy, reputation, professional role and auditing; 12 in the microenvironment: sex, race, condition of insurance, language, treatments, chronic disease, future risk of disease, medications, morale, inequity, coinsurance, and the decisions of the claims-adjusters; and five combined factors: the relationships between beneficiary-provider, provider-insurance company, beneficiary-insurance company, managers and guānxi. Conclusions The multifactorial nature of HIF and the characteristics of its manifestations depend on its definition; Identifying the influence of the factors will support subsequent attempts to combat HIF.