Artificial Intelligence (AI) and Business Innovation in Insurance: A Comparison of Incumbent Firms versus New Entrants

2023 | HICSS | Citations: 0

Authors: Holland, Christopher; Kavuri, Anil

Abstract: Artificial Intelligence (AI) systems evolve in response to new data by using ada ... Expand

Abstract: Artificial Intelligence (AI) systems evolve in response to new data by using adaptive algorithms. The insurance industry is data intensive, and dynamic. It is therefore particularly suitable for AI implementation. An innovation triangle framework is proposed that consists of product, process and value chain innovation. A comparison of leading incumbent insurance firms with new entrants illustrates significant competitive differences. The incumbents apply AI to defend their market positions by enhancing existing strengths and capabilities across the three innovation types. The new entrants exploit AI technology to build new products with innovative features that emphasise customer value and user experience. The innovation triangle is a useful managerial tool to analyse the nature and extent of innovation in insurance and can be used to evaluate and plan AI strategies by mapping existing AI initiatives to specific types of innovation and identifying innovation objectives and opportunities. Future trends and research opportunities are outlined. Collapse

Topics: artificial intelligence innovation management user experience website marketing management

Methods: case study theoretical contribution

How individuals can shape AI through data - An AI literacy and morality perspective

2023 | European Conference On Information Systems | Citations: 0

Authors: Schneider, Johannes; Meske, Christian; Bikic, Antonio

Abstract: ... Expand

Abstract: Collapse

Topics: artificial intelligence data quality IT productivity privacy Python

Methods: case study descriptive statistic artificial neural network supervised learning logistic regression

Theories: ethical theory

Data misrepresentation detection for insurance underwriting fraud prevention

2022 | Decision Support Systems | Citations: 0

Authors: Vandervorst, Félix; Verbeke, Wouter; Verdonck, Tim

Abstract: Premium fraud concerns data misrepresentation committed by an insurance customer ... Expand

Abstract: Premium fraud concerns data misrepresentation committed by an insurance customer with the intent to benefit from an unduly low premium at the underwriting of a policy. In this paper, we propose a novel approach for evaluating the risk of underwriting premium fraud at the time of application in the presence of potentially misrepresented self-reported information. The aim of the approach is to support insurance companies in iden­ tifying fraudulent applications and their decisions to underwrite insurance contract propositions. Likewise, it can be use to make straight-through processing (i.e. automated) underwriting systems more fraudproof, by e.g., triggering a validation on applications prone to misrepresentations. Our approach is based on conditional density estimates for a set of validated contracts. The proposed approach does not require historical fraud labels and can adapt to changes in pricing policy. Moreover, the approach can be used to detect outliers in addition to predicting underwriting fraud and is extended to multivariate self-reported data. We further demonstrate a link between Shapley values in common conditional expectation problems and conditional density estimations to make our approach explainable. We report a case study involving motor insurance underwriting, in which a driver’s identity and driving record can be misrepresented to benefit from an unduly low premium; the results indicate the effectiveness of the proposed approach for detecting and preventing underwriting fraud. Collapse

Topics: price management shapley additive explanation fraud detection information graphic decision support system

Methods: random forest classification computational algorithm self reported survey case study decision tree classification

Where to Start with AI?—Identifying and Prioritizing Use Cases for Health Insurance

2022 | HICSS | Citations: 0

Authors: Weber, Michael; Limmer, Nicolas; Weking, Jörg

Abstract: Artificial Intelligence (AI) arguably represents a key technology for the digita ... Expand

Abstract: Artificial Intelligence (AI) arguably represents a key technology for the digitalization of health care. Specifically, health insurers can benefit from AI as they typically have access to vast amounts of data. However, practitioners struggle to adopt AI in productive use, and extant research lacks an overview of use cases for AI in health insurance as well as prioritization criteria that can guide their implementation. To address this gap, we conduct explorative interviews in the context of the German statutory health insurance system. We identify AI use cases in the areas of predictive health, individualized service, anomaly detection, and operations enhancement. We find that health insurers are likely to prioritize these use cases according to implementation complexity and business orientation, whereas focusing on simple use cases that target cost savings is recommended by experts. Our study advances the understanding of AI adoption in health insurance and supports practitioners in guiding future AI initiatives. Collapse

Topics: artificial intelligence insurance information system decision making organizational commitment pandemic

Methods: qualitative interview anomaly detection computational algorithm longitudinal case study longitudinal research

The Role of Fear and Trust when Disclosing Personal Data to Promote Public Health in a Pandemic Crisis

2021 | International Conference on Business Informatics | Citations: 0

Authors: Hillebrand, Kirsten

Abstract: During the 2020 pandemic crisis, state surveillance measures violated citizens’ ... Expand

Abstract: During the 2020 pandemic crisis, state surveillance measures violated citizens’ privacy rights to track the virus spread. Rather little civic protest resulted—“safety first”? Indeed, many state measures were implemented during the crisis without ever having been discussed in advance of the event of a crisis, which may raise ethical considerations, as individual consent to data disclosure may change while experiencing fear. This paper investigates citizens’ consent to voluntary and legally obliging data disclosure to the state and what drives their consent. Results from an online survey conducted with 1,156 respondents during the onset of the crisis in Germany in mid-March show that (1) fear increases consent to voluntary data disclosure, (2) fear increases consent to legally obliging data disclosure directly and indirectly by fostering distrust in others, and (3) trust in the government increases voluntary and legally obliging data disclosure. Collapse

Topics: pandemic Facebook Instagram privacy insurance information system

Methods: survey archival research statistical hypothesis test experiment

Theories: privacy calculus theory

SERVICE INNOVATION THROUGH PLATFORMISATION OF A PRIVATE HEALTH INSURANCE: AN ACTIVITY THEORY PERSPECTIVE OF THE CASE OF GHANA

2020 | European Conference On Information Systems | Citations: 0

Authors: Renner-Micah, Anthony; Effah, John; Boateng, Richard

Abstract: ... Expand

Abstract: Collapse

Topics: digital platform business process innovation innovation management information system use insurance information system

Methods: case study field study qualitative content analysis system dynamics personal interview

Theories: activity theory

Institutionalisation of Health Insurance Digital Claims Platform

2020 | Americas Conference on Information Systems | Citations: 0

Authors: Renner-Micah, Anthony; Effah, John; Boateng, Richard

Abstract: This study aims to understand how institutionalisation of health insurance digi ... Expand

Abstract: This study aims to understand how institutionalisation of health insurance digital claims platform gets facilitated or constrained. The study is situated in a developing country context of Ghana. A growing body of information systems research on digital platforms to organise public health care exists and continues to evolve; however, the facilitators and constraints to institutionalisation of digital platform in health insurance have received little attention. This paper, therefore, applies a sociotechnical approach using institutional theory as the analytical lens and qualitative interpretive case study as the methodology. The findings show that institutionalisation of digital platforms is not linear and incremental, but goes through several iterations, sudden and non-linear disruptions. The critical barriers identified limiting institutionalisation of digital platform include; (1) Heterogeneous health care provider environment. (2) political change and leadership; and, (3) Management of the innovation process. Collapse

Topics: insurance information system digital platform information system use health information system website

Methods: case study qualitative interview qualitative content analysis single case study computational algorithm

Theories: institutional theory

Sharing Personal Health and Fitness Data with Health Insurance Providers: An Empirical Study Considering Trust and Risk

2020 | HICSS | Citations: 0

Authors: Seiferth, Aurica; Schaarschmidt, Mario

Abstract: Digital self-tracking with wearable devices and mobile applications is exceeding ... Expand

Abstract: Digital self-tracking with wearable devices and mobile applications is exceedingly popular. The arising data is not only crucial for individual use but also for actors in the healthcare segment. This paper focuses on German health insurance providers and their expanding call for clients’ personal health and fitness data in a highly complex and regulated environment. As clients need to be willing to share health-related information, an experimental study was conducted, consisting of different modes of rewardbased insurance offerings. Trust and perceived risk were assessed as prominent psychological constructs, assessing participants’ willingness to share their personal information. Results show that examined factors such as company publicity or monetary incentives are scarcely influential. However, trust and perceived risk affect an individual’s willingness to share. Taking up the health insurance provider’s perspective, alternative aspects need to be considered to successfully gain consumer trust to collect the clients’ health and fitness information. Collapse

Topics: insurance information system privacy

Methods: survey statistical hypothesis test survey design factor analysis data transformation

Blockchain Regulations and Decentralized Applications: Panel Report from AMCIS 2018

2020 | Communications of the Association for Information Systems | Citations: 0

Authors: Subramanian, Hemang; Cousins, Karlene; Bouyad, Lina Bouyad; Sheth, Alpen; Conway, Dan

Abstract: Blockchain represents one of the 21st century’s most impactful inventions. In ad ... Expand

Abstract: Blockchain represents one of the 21st century’s most impactful inventions. In addition to creating cryptocurrencies such as Bitcoin, this technology enables smart contract functionality and supports decentralized, secure, and private transactions. By design, blockchains enable decentralized functionality for many of today’s business applications and transform traditional centralized information systems. In this paper, we summarize four research areas that will appeal to IS scholars that a panel at AMCIS 2018 discussed: 1) cryptocurrency regulation, 2) Etherisc (a smart contractbased application), 3) decentralized blockchain applications in healthcare, and 4) Bitcoin as a blockchain application and issues with decentralization. To account for the European Union’s General Data Protection Regulation’s requirements to provide people with the right to be forgotten and modify personal data, we modified Pedersen et al.’s (2019) framework to accommodate off-chain data storage requirements. We deployed Pedersen et al.’s (2019) modified framework to evaluate whether one can use blockchains for three different applications. We summarize several research questions and present a research agenda that emerged from the issues highlighted during the panel discussion. Collapse

Topics: blockchain Bitcoin cryptocurrency insurance information system smart contract

Methods: archival research design artifact

Automobile insurance classification ratemaking based on telematics driving data

2019 | Decision Support Systems | Citations: 13

Authors: Huang, Yifan; Meng, Shengwang

Abstract: Usage-based insurance (UBI), given the development of in-vehicle networking and ... Expand

Abstract: Usage-based insurance (UBI), given the development of in-vehicle networking and big data technologies, has received a growing amount of attention in recent years from both insurers and policyholders. The UBI product derives certain driving behavior variables from telematics data, which have stronger causal relationships with accidents and thus effectively improve the pricing accuracy of automobile insurance. This paper mainly investigates the use of extensive driving behavior variables in predicting the risk probability and claim frequency of an insured vehicle. More specifically, logistic regression and four machine learning techniques - support vector machines, random forests, XGBoost, and artificial neural networks - are employed as risk probability models, while Poisson regression as claim frequency model. In addition, aiming at the interpretability requirements of insurance pricing, a data augmentation method of variable binning is adopted to discretize continuous variables and construct tariff classes with significant predictive effects. As a result, our pricing framework can simultaneously improve the interpretability and predictive accuracy of the model, and thus provides a novel solution to implement classification ratemaking for UBI products. The empirical results, based on a dataset from a property and casualty insurance company in China, show the selection of significant variables and the estimation of their specific effects on driving risk, verifying the great potential of driving behavior variables in automobile insurance. Collapse

Topics: price management evaluation criteria IS value insurance information system user behavior

Methods: machine learning XGBoost logistic regression conceptual modelling artificial neural network