Search results

The purpose of this paper is to survey the automobile insurance fraud detection literature in the past 31 years (1990–2021) and present a research agenda that addresses the challenges and opportunities artificial intelligence and machine learning bring to car insurance fraud detection.

Content analysis methodology is used to analyze 46 peer-reviewed academic papers from 31 journals plus eight conference proceedings to identify their research themes and detect trends and changes in the automobile insurance fraud detection literature according to content characteristics.

This study found that automobile insurance fraud detection is going through a transformation, where traditional statistics-based detection methods are replaced by data mining- and artificial intelligence-based approaches. In this study, it was also noticed that cost-sensitive and hybrid approaches are the up-and-coming avenues for further research.

This paper’s findings not only highlight the rise and benefits of data mining- and artificial intelligence-based automobile insurance fraud detection but also highlight the deficiencies observable in this field such as the lack of cost-sensitive approaches or the absence of reliable data sets.

This paper offers greater insight into how artificial intelligence and data mining challenges traditional automobile insurance fraud detection models and addresses the need to develop new cost-sensitive fraud detection methods that identify new real-world data sets.

In the current global economy, the survival of an insurance company depends on its ability to respond to the customer demands. One of the demands of customers is efficient settlement of insurance claims. All insurance companies face the conflicting goals of authenticating claims and settling claims quickly. The use of human adjusters in claim settlement process leaves room for subjective judgment and the use of discretion while finalizing a claim. It has been observed that the opportunity exists for claim adjustors to settle insurance claims in favor of the claimants simply by colluding with the claimant and sacrificing the monetary interest of the insurers. The increasing cost of human experts for authentication (fraud detection) has led many companies to develop technological solutions such as expert systems to assist in the authentication of processed claims.

We have used fuzzy math in combination with the expert systems technology to design this model system.

We develop a fuzzy logic based expert system that can identify and evaluate whether elements of fraud are involved in insurance claims settlement.

We could not obtain real life data from any one of the insurance companies even after various attempts in Canada. Canadian Privacy Legislation does not permit these organizations to share them with any one.

This expert system can help decide if settled claims are genuine or if an element of fraud might exist which needs substantive testing by an auditor. The proposed methodology has been illustrated with an example that tends to model insurance claims in general.

The model designed in this paper is original and carries a substantial value to internal/external auditing professional who has access to these data to train the inference engine.

Insurance fraud as a global economic problem threatens the financial strength of insurers and threatens the survival of the insurance institution. The purpose of this paper is to explore the magnitude of the problem including the industry's and regulatory authority's responses in tackling the menace in Nigeria. The paper is motivated by the recent effort on the part of the Nigerian regulatory authority to strengthen the sector through consolidation. Such renewed vigour on part of Nigeria is geared towards fighting all forms of economic crimes in both public and private sectors in post‐military years.

The paper reviews the literature on the existing fraud control mechanisms, i.e. insurance contract design and auditing and the perception of fraud by customers in the insurance market. A survey is conducted by interview method to explore the size of the problem and the effectiveness of the approach the industry and its regulator are adopting to control it.

The paper's findings suggest a lukewarm or no serious attitude on the part of the regulatory authority and the insurance companies in appreciating the enormity of the problem now and in the future. This stems from lack of clear‐cut sanctions for offenders and mechanism for enforcement.

The paper reveals the paucity of research of such a topical issue in developing economies and suggests the need for urgent stakeholders' summit that will discuss effects of insurance fraud on the industry with a view to identifying specific roles and responsibilities of each stakeholder group in tackling the problem. This should also be complimented with the establishment of insurance fraud bureau that would promote public awareness campaign on the evil effect of fraud on the economy.

The purpose of this paper is to review the management of consumer insurance fraud in the US property‐casualty market, attending to definition, prevalence, insurer and regulatory responses, and outcomes. A social marketing campaign is offered as a partial, long‐term solution.

This paper explicates the difficulties associated with defining and measuring consumer insurance fraud, then models the system of factors now in place in redress.

Little agreement was found for a common definition of consumer insurance fraud and this was explained in part due to the decentralization of insurance regulation, competitive factors, and inconsistency in claims processing. The paper concludes by offering a social marketing campaign as a tool for reducing the incidence and severity of single‐claims fraud, the latter believed to be the largest source of consumer insurance fraud.

This paper affords a macro‐level view of a common and expensive social problem, suggests a practical solution with the promise of reducing long‐term losses at all levels.

This paper aims to present a bibliometric analysis of publications from the Scopus database on fraud detection studies.

The current research used Microsoft Excel to conduct the frequency analysis, VOSviewer for data visualisation and Harzing’s Publish or Perish for citation metrics and analysis.

In alignment with these research results, the publications on fraud detection studies have been consistently increasing since 2005. India was rated first as the most active country in fraud detection research. Tongji University from China was the most active institution that published significant publications related to fraud detection research. A total of 160 scholars from 89 various countries and 160 different institutions published several fraud detections studies with multi-authors’ participation in different languages.

To the best of the authors knowledge, this study is the first study to review fraud detections publications in the Scopus science database.

Digital technology is revolutionizing insurance distribution allowing the insurer companies to reach customers via multichannel. The aim of this study is to segment potential customers of life insurance based on their information search, purchasing channels and personal characteristics in the digital environment.

The study uses cross-sectional research survey. In total, 422 questionnaires were collected through a convenience sample of the Romanian population. The data was segmented based on consumer information touchpoints (online vs offline), purchase channel preference (offline by a professional vs online by a standardized platform) and personal characteristics (age, marital status and children).

The channel segmentation analysis revealed that information channel preferences are the most important clustering variables, followed by purchase channel preferences, marital status, having children and age. Four distinct segments were identified: young fully offliners (23.7%), mature fully offliners (31.5%), committed online searchers (23.2%) and cross-channel onliners (21.6%).

Insurance companies should adapt their communication and distribution strategy based on multichannel segmentation and should focus on digital touchpoints with costumers.

Firstly, the paper reveals multichannel and hybrid segmentation for life insurance. Secondly, it extends the already studied retail channels with search engines and companies' websites. Thirdly, it extends the behavioural variables for channel segmentation with technology acceptance behaviour, attitude towards life insurance, knowledge about life insurance, attitude towards personal selling and quality appraisal of online information sources.

The purpose of this paper is to examine customers’ ethical attitudes (EA) and intentions toward two types of insurance frauds. This study proposes that the factors, such as fraud types (i.e. opportunistic and planned insurance fraud), moral intensity and fairness perception (FP), can affect the customers’ acceptance of the insurance frauds.

To test the research hypotheses of this study, Taiwanese insurance customers are invited in the empirical investigation, and a scenario-based questionnaire is used to collect the data. The hypotheses of this study are tested by using a partial least squares regression.

The results show that moral intensity constructs and FP significantly relate to the respondents’ acceptance of insurance frauds, while fraud types also have significant impacts on the respondents’ perceptions of moral intensity and fairness.

There is no research which has examined the relationships among fraud types, moral intensity, FP, demographic variables and customers’ EA and intentions toward insurance frauds. Understanding the relationships among these variables could provide implications for those involved in the practice of anti-fraud programs.

The purpose of this paper is to investigate which factors will affect the insurance claims adjusters’ attitude and behavior intention toward lenient claims handling practices. These factors include organizational justice, behavioral-based control, significant others, and customer complaints.

Data are collected with questionnaires from full-time licensed insurance claims adjusters in Taiwan. Partial least squares method is used to test the hypotheses.

The main results show that significant others and organizational justice have significant effects on the claims adjusters’ attitude toward the lenient claims handling practices. Significant others and attitude have significant effects on the behavioral intention.

The influence of claims management on insurance companies’ operation is quite considerable. Poor claims management may not only harm insurance companies’ finance, but also affect the adjustment of future premiums. Yet, in reality, some claims adjusters are found to make flawed claims decisions. Very few studies discuss this problem. This study provides an initial step toward understanding this issue.

The fact that complaints regarding general insurance claims are three times as numerous as those of life insurance claims suggests that claims behaviour of general insurers be investigated to minimize operating losses and ensure operational excellence. This paper seeks to address this issue.

Study of variance and factor analysis has been undertaken to achieve the objective of identifying factors which govern claims in general insurance business. In order to understand the dependency of claims over the sectors and segments, statistical hypothesis testing along with cross tab analysis has been conducted. The study also evaluates the relationship of these factors over the sectors and segments by running a multiple regression.

An empirical result of the study proves that there exists an association between type of sectors, i.e. public and private and segments of insurance namely fire, marine and miscellaneous. The study also suggests a claim projection model for the general insurance players.

Exclusion of specialized players due to the reason being new entrants and in order to maintain common parlance of sectors may be a limitation to this study.

The study recommends that insurance players should not treat the claims settlement strategies in isolation of segments. The claims projection model as suggested in the study may prove to be extremely helpful in projecting the claims and in turn reduce the increasing underwriting losses.

Insurance frauds deeply affect insurance companies, policyholders, and the insurance industry as a whole. The cost of fraudulent damage affects the profitability of companies, and has negative effects on the society in terms of moral values. Increases in insurance costs can lead to increases in the premiums paid by policyholders, each family, and, ultimately, all of the insured. Recently, new legal regulations related to this issue have been performed in Turkey and higher institutions have been created. A regulation issued by the Under-secretariat of the Treasury, on June 1, 2011, defines insurance fraud as aggravated fraud. Insurance fraud in Turkey usually takes the form of intentional misrepresentations of facts to the insurance company to get the company to pay for something not actually covered by the policy. Studies examined the insurance industry in terms of the concept of financial crime, and inclusion of the concept of financial crime in insurance regulations was proposed since financial crimes have an important place in the current problems of the industry. In addition, it is seen that insurance frauds have changed over time as a result of studies.