Big Data Analytics in the Insurance Market

Introduction: The frequency and complexity of cyber assaults have grown in recent years. Consequently, organisations have increased their expenditures in more robust infrastructure to protect themselves from these cyber assaults. These organisations’ assets, data, and reputations are at risk due to rapidly increasing cybercrimes. However, complete protection from these many and ever-changing threats is very challenging as a result. To deal with them, companies are taking steps to reduce risks and limit company losses in their occurrence.

Purpose: Progressively, the insurance sector organisations are including digital protection as a component of the board’s general danger technique. Protection enterprises, then again, depend on accurately expecting risks, while a significant number of them depend on normalised approaches. Because of the exceptional attributes of the digital assaults, transporters now and again depend on subjective strategies dependent on master decisions. There is an unmistakeable absence of observational information on digital protection, specifically subjective examinations planning to comprehend and depict necessities, impediments, and cycles applicable for digital protection.

Methodology: There are various unanswered inquiries and worries about the oversight and legitimate and administrative assessment of network safety weaknesses in the protection business. In the wake-up of looking over all these worries and issues, steps to alleviate them are laid out after an extensive literature survey and secondary data sources. In this study, the authors have principally viewed the executive parts of the associations as the danger. While considering network protection, their insight of needs was taken as one among a few dangerous treatment systems, just as the necessities of the organisations’ protection in assessing the danger level of likely customers.

Findings: This section analyses past research in network safety and information security in the protection market. The danger of the executives’ strategies, the numerical models, and the forecasts of digital occassions are illustrated in this section. Lastly, the future headings are likewise expressed momentarily.

Practical implications: This review might be valuable for additional examination and logical discussion, yet additionally for down-to-earth applications. Moreover, it could be gainful to organisations as a supportive instrument for better agreement on what digital protection is and how to get ready to take on network safety and information security procedures in the association.

Significance: These associations’ resources, information, and notoriety are in danger because of quickly expanding cybercrimes. Cybercriminals are utilising more refined approaches to start digital assaults. Digital protection was anticipated to affect security conduct before any proof was gathered. Progressively, organisations are including digital protection as a feature of their general danger to the executive system. Because of the exceptional attributes of the digital assaults, transporters as often as possible depend on subjective methods dependent on master decisions. Thus, this space of network safety and information security is vital uniquely in the protection market.

Introduction: The insurance industry has unprecedented growth, and the demand for insurance has outgrown in the recent past due to the prevailing pandemic. The companies have a large base of the data set at their disposal, and companies must appropriately handle these data to come out with valuable solutions. Data mining enables insurance companies to gain an insightful approach to map strategies and gain competitive advantage, thus strengthening the profits that will allow them to identify the effectiveness of back-propagation neural network (BPNN) and support vector machines (SVMs) for the companies considered under study. Data mining techniques are the data-driven extraction techniques of information from large data repositories, thus discovering useful patterns from the voluminous data (Weiss & Indurkya, 1998).

Purpose: The present study is performed to investigate the comparative performance of BPNNs and SVMs for the selected Indian insurance companies.

Methodology: The study is conducted by extracting daily data of Indian insurance companies listed on the CNX 500. The data were then transformed into technical indicators for predictive model building using BPNN and SVMs. The daily data of the selected insurance companies for four years, that is, 1 April 2017 to 21 March 2021, were used for this. The data were further transformed into 90 data sets for different periods by categorising them into biannual, annual, and two-year collective data sets. Additionally, the comparison was made for the models generated with the help of BPNNs and SVMs for the six Indian insurance companies selected under this study.

Findings: The findings of the study exhibited that the predictive performance of the BPNN and SVM models are significantly different from each other for SBI data, General Insurance Corporation of India (GICRE) data, HDFC data, New India Assurance Company Ltd. (NIACL) data, and ICICIPRULI data at a 5% level of significance.

Purpose: This chapter aims to examine machine learning (ML) models for predicting credit card fraud (CCF).

Need for the study: With the advance of technology, the world is increasingly relying on credit cards rather than cash in daily life. This creates a slew of new opportunities for fraudulent individuals to abuse these cards. As of December 2020, global card losses reached $28.65billion, up 2.9% from $27.85 billion in 2018, according to the Nilson 2019 research. To safeguard the safety of credit card users, the credit card issuer should include a service that protects customers from potential risks. CCF has become a severe threat as internet buying has grown. To this goal, various studies in the field of automatic and real-time fraud detection are required. Due to their advantageous properties, the most recent ones employ a variety of ML algorithms and techniques to construct a well-fitting model to detect fraudulent transactions. When it comes to recognising credit card risk is huge and high-dimensional data, feature selection (FS) is critical for improving classification accuracy and fraud detection.

Methodology/design/approach: The objectives of this chapter are to construct a new model for credit card fraud detection (CCFD) based on principal component analysis (PCA) for FS and using supervised ML techniques such as K-nearest neighbour (KNN), ridge classifier, gradient boosting, quadratic discriminant analysis, AdaBoost, and random forest for classification of fraudulent and legitimate transactions. When compared to earlier experiments, the suggested approach demonstrates a high capacity for detecting fraudulent transactions. To be more precise, our model’s resilience is constructed by integrating the power of PCA for determining the most useful predictive features. The experimental analysis was performed on German credit card and Taiwan credit card data sets.

Findings: The experimental findings revealed that the KNN achieved an accuracy of 96.29%, recall of 100%, and precision of 96.29%, which is the best performing model on the German data set. While the ridge classifier was the best performing model on Taiwan Credit data with an accuracy of 81.75%, recall of 34.89, and precision of 66.61%.

Practical implications: The poor performance of the models on the Taiwan data revealed that it is an imbalanced credit card data set. The comparison of our proposed models with state-of-the-art credit card ML models showed that our results were competitive.

Introduction: In recent years, fresh big data ideas and concepts have emerged to address the massive increase in data volumes in several commercial areas. Meanwhile, the phenomenal development of internet use and social media has not only added to the enormous volumes of data available but has also posed new hurdles to traditional data processing methods. For example, the insurance industry is known for being data-driven, as it generates massive volumes of accumulated material, both structured and unstructured, that typical data processing techniques can’t handle.

Purpose: In this study, the authors compare the benefits of big data technologies to the needs for insurance data processing and decision-making. There is also a case study evaluation concentrating on the primary use cases of big data in the insurance business.

Methodology: This chapter examines the essential big data technologies and tools from the insurance industry’s perspective. The study also included an analytical analysis that supported several gains made by insurance companies, such as more efficient processing of large, heterogeneous data sets or better decision-making support. In addition, the study examines in depth the top seven use cases of big data in insurance and justifying their use and adding value. Finally, it also reviewed contemporary big data technologies and tools, concentrating on their key concepts and recommended applications in the insurance business through examples.

Findings: The study has demonstrated the value of implementing big data technologies and tools, which enable the development of powerful new business models, allowing insurance to advance from ‘understand and protect’ to ‘predict and prevent’.

Background: Insurance was discovered many centuries before Christ (BC). In the second and third millennia BC, Chinese and Babylonian traders traded risks. Insurance is now the backbone of the economy, but penetration is low in developing countries. Big data, internet of things (IoT), and InsurTech have recently ushered in the fourth industrial revolution in insurance.

Objective: This study examines the Indian challenges and solutions of using Big Data Analytics (BDA).

methodology: A SLR was used to extract themes/variables related to challenges and solutions in adopting BDA in the Indian insurance sector. Google Scholar was searched for relevant literature using keywords. Inclusion and exclusion criteria were used to filter the studies.

Findings: This study identified several barriers to BDA adoption in the Indian insurance industry. Policymakers could use the suggestions to improve insurance service delivery.

Practical implication: Insurers can understand the challenges, and accordingly, they can adopt the proposed solution in this study to enhance the insurance penetration in India.

Introduction: With the proliferation and amalgamation of technology and the emergence of artificial intelligence and the internet of things, society is now facing a rapid explosion in big data. However, this explosion needs to be handled with care. Ethically managing big data is of great importance. If left unmanageable, it can create a bubble of data waste and not help society achieve human well-being, sustainable economic growth, and development.

Purpose: This chapter aims to understand different perspectives of big data. One philosophy of big data is defined by its volume and versatility, with an annual increase of 40% per annum. The other view represents its capability in dealing with multiple global issues fuelling innovation. This chapter will also offer insight into various ways to deal with societal problems, provide solutions to achieve economic growth, and aid vulnerable sections via sustainable development goals (SDGs).

Methodology: This chapter attempts to lay out a review of literature related to big data. It examines the implication that the big data pool potentially influences ideas and policies to achieve SDGs. Also, different techniques associated with collecting big data and an assortment of significant data sources are analysed in the context of achieving sustainable economic development and growth.

Findings: This chapter presents a list of challenges linked with big data analytics in governance and achievement of SDG. Different ways to deal with the challenges in using big data will also be addressed.

Introduction: With many new technologies requiring real-time data processing, cloud computing has become challenging to implement due to high bandwidth and high latency requirements.

Purpose: To overcome this issue, edge computing is used to process data at the network’s edge. Edge computing is a distributed computing paradigm that brings computation and data storage closer to the location where it is needed. It is used to process time-sensitive data.

Methodology: The authors implemented the model using Linux Foundation’s open-source platform EdgeX Foundry to create an edge-computing device. The model involved getting data from an on-board sensor (on-board diagnostics (OBD-II)) and the GPS sensor of a car. The data are then observed and computed to the EdgeX server. The single server will send data to serve three real-life internet of things (IoT) use cases: auto insurance, supporting a smart city, and building a personal driving record.

Findings: The main aim of this model is to illustrate how edge computing can improve both latency and bandwidth usage needed for real-world IoT applications.

Introduction: Big data in the insurance industry can be defined as structured or unstructured data that can affect the rating, marketing, pricing, or underwriting. The five Vs of big data provide insurers with a valuable framework for converting their raw data into actionable information. These five Vs are specifically: (1) Volume: The need to look at the type of data and the internal systems; (2) Velocity: The speed at which big data is generated, collected, and refreshed; (3) Variety: Refers to both the structured and unstructured data; (4) Veracity: Refers to trustworthiness and confidence in data; and (5) Value: Refers to whether the data collected are good or bad.

Purpose: Insurance companies face many data challenges. However, the administration of big data has allowed insurers to acknowledge the demand of their customers and develop more personalised products. In addition, it can be used to make correct decisions about insurance operations such as risk selection and pricing.

Methodology: We do this by conducting a systematic literature review on big data. Our emphasis is on gathering information on the five Vs of the big data and the insurance market. Specifically, how big data can help in data-driven decisions.

Findings: Big data technology has created an endless series of opportunities, which have ensured a surge in its usage. It has helped businesses make the process more systematic, cost-effective, and helped in the reduction in fraud and risk prediction.

Introduction: The insurance sector provides security to society by pooling resources to manage risks. Insurers’ improved ability to analyse risks by examining vast amounts of granular data has considerably refined this technique. Compiling and analysing the fine data sets is now transformed into the ‘Big Data’ technique. The introduction of big data analytics (BDA) is transforming the insurance industry and the role data plays in insurance.

Purpose: This chapter will attempt to examine the applications and role of big data in the insurance sector and how big data affects the different insurance segments like health insurance, property and casualty, and travel insurance. This chapter will also describe the disruptive impact of big data on the insurance market.

Methodology: Systematic research is carried out by analysing case studies and literature studies, emphasising how BDA is revolutionary for the insurance market. For this purpose, various articles and studies on BDA in the insurance market are selected and studied.

Findings: The execution of big data is continuously increasing in the insurance sector. The performance of big data in the insurance market results in cost reduction, better access to insurance services, and more fraud detection that benefits the customers and stakeholders. Therefore, big data has revolutionised the insurance market and assisted insurers in targeting customers more precisely.

Introduction: Foreign direct investment (FDI) is a deciding factor in the insurance industry’s growth in any nation. Besides, similar socioeconomic conditions, some countries tend to attract more FDI inflows. This chapter focuses on exploring the FDI in the insurance industry in Brazil, Russia, India, China, and South Africa (BRICS).

Purpose: The chapter aims to explore the current situation of FDI in the insurance industry in BRICS member nations and uncover the factors that have led to higher foreign investments in some countries.

Methodology: Using descriptive and comparative approaches, this chapter explains the FDI scenario in the insurance sector of BRICS nations.

Findings: Based on a comparative analysis, the authors observed that deregulation, increased foreign engagement, and adoption of innovative technology and distribution methods are some avenues that could be worked upon to improve FDIs in the Indian insurance sector.

Purpose: This chapter aims to review the research literature on the insurance industry and map the emerging research trends in this field through a bibliometric analysis and network visualisation exercise.

Design/methodology/approach: The research literature gathered from the Web of Science (WoS) databases was applied to bibliometric analysis in this article. With the help of Biblioshiny, this research was utilised to identify documents, most prolific institutions, countries, resource titles, and WoS categories in the insurance industry. In addition, bibliometric mapping was used to identify national and institutional collaboration networks.

Findings: The author discovered that the literature had increased drastically in the academic discourse during the last two decades. According to the bibliometric data, developed countries such as the United States and the United Kingdom reign research in this sector. The research highlights the most prominent studies and writers in the insurance field and the evolution of the domain from its inception to the contemporary. It also highlights theoretical disagreements and contradictions between theoretical conceptualisation and empirical measures by presenting the significant concerns in the literature.

Originality/value: This chapter delivers the first comprehensive bibliometric analysis of the insurance sector’s literature production in connection to emerging technology, which will aid researchers and practitioners in better understanding the relationships between themes and outsiders to understand the domain area better. The author makes recommendations for future perspectives study directions and highlights the critical conceptual framework that can build future research. Overall, this research contributes to a better understanding of the insurance industry and offers new perspectives.

Introduction: New ideas and concepts of big data have emerged in recent years in response to the astounding growth of data in many industries. Furthermore, the phenomenal increase in the use of the internet and social media has added enormous amounts of data to conventional data processing systems. Still, it has also created challenges for traditional data processing.

Purpose: A significant characteristic of the insurance sector is critically dependent on information. This sector generates a great deal of structured and unstructured data, which traditional data processing techniques cannot handle. As compared to conventional insurance data processing and decision-making requirements, this lesson shows an analysis of data technology’s value additions.

Research methodology: The author assesses the primary use of cases for data in the insurance industry via a case study analysis. From the perspective of the insurance sector, this chapter examines the concepts, technologies, and tools of big data. A few analytical reviews by the insurance company are also provided, which justified several gains gained either through inefficient processing of massive, diverse data sets or by supporting better decisions.

Findings: This chapter demonstrates the importance of adopting new business models that allow insurers to move beyond understand and protect and become more predictive and preventative by using the tools and technologies of big data technology.

Purpose: This chapter aims to present the arguments for and against central bank digital currency (CBDC) increasing financial inclusion. Financial inclusion is one of the many reasons for issuing a CBDC.

Need for the study: There is a need to offer a critical perspective on the proposed financial inclusion benefits of CBDC. This is the first paper to present arguments supporting and statement against CBDC for financial inclusion.

Method: This chapter uses discourse analysis methodology to identify the arguments about CBDC promoting financial inclusion

Findings: The arguments in support of CBDC increasing financial inclusion are that CBDCs can digitise value chains, CBDCs can improve access to digital financial services, CBDCs can help to enlarge the digital economy, CBDCs can enhance the efficiency of digital payments, CBDCs can be used offline when there is no internet coverage, and CBDCs have low transaction costs. Some criticisms are that CBDC may not prioritise financial inclusion, a high price to purchase digital devices for holding a CBDC, non-interest-bearing CBDCs, the strong preference for cash over digital currency, the burdensome identification and regulatory requirements, and the imposition of transaction costs.

Implications: Overall, the arguments presented in this chapter show that there is still disagreement over whether a central bank’s digital currency can increase financial inclusion. Nevertheless, in the light of recent events, many central banks are determined to issue a CBDC for many reasons. Even though CBDCs do not achieve the intended financial inclusion objective, at least the other goals for publishing a CBDC will be performed, such as a significant reduction in cash management costs and the effective conduct of monetary policy.

Introduction: The insurance sector is playing a crucial role in the sustainable growth of the Indian economy. But in India, this sector loses crores of rupees every year due to the increasing fraud cases. With the increase in insurance customers, insurance companies need to efficiently equip themselves with a robust system to handle claims fraud. Detection of insurance fraud is a pretty challenging problem. Nowadays, machine learning (ML) and artificial intelligence (AI) are the strategic choices of many leading organisations that want to proceed in a new digital arena.

Purpose: This chapter’s main objective is to highlight the fundamental market forces driving the adoption of AI and ML and showcase the traditional and modern methods to predict insurance claims fraud intelligently.

Methodology: Various research papers have been reviewed, and ML methods have been discussed, which are all being used to predict insurance fraud claims. This chapter also highlights various driving forces influencing the adoption of ML.

Findings: This study highlights the introduction of blockchain technology in fraud detection and in combatting insurance fraud. Literature indicates that the quantity and quality of data significantly impact predictive accuracy. ML models are beneficial to identify the majority of fraudulent cases with reasonable precision. Insurance companies should explore the benefits of experienced resource persons from the same domain and develop unique business ideas/rules.

Introduction: The insurance industry is vulnerable to attacks as it deals with the personal information of its consumers and puts the insurance company’s business at risk in the event of data breach or abuse. To ensure the security of customer data, insurance companies must comply with various data protection requirements, including requirements imposed by laws, regulations, and standards. Following such a wide range of conditions can be challenging for insurance providers. For a long time, risk management has controlled data protection to ensure compliance with data protection law and ensure that data are processed correctly and that people’s fundamental rights are protected effectively.

Purpose: This chapter explains the role and significance of risk management. An organised way to identify and assess risks, mitigate or avoid risks as much as possible, and then manage and accept the remaining risks, implemented in data protection as needed, explained by the supervisory authority, is implemented by the responsible organisation. This document highlights the growing consensus surrounding risk management as an essential tool for adequate data protection. Furthermore, it addresses vital considerations that affect the role of risk in data protection law and practice.

Need for study: There is an increasing consensus towards the role and significance of risk management in data protection in the insurance market. As a result, regulators and legislators are focussing on valuable and new attention on standardising and expanding data protection in risk management practices. This paper has attempted to identify critical issues and principles of risk management in data protection.

Methodology: Secondary data analysis was conducted in this study by reviewing literature related to data protection, risk management, and the insurance sector. Again, science direct was used as a source of information. For this study, the literature review approach was chosen since it allows us to trace the growth of the subject matter and identify the patterns that have formed through time.

Findings: The insurance industry comprises general insurance and life insurance. It is found that there are various studies conducted on the privacy violation and data breaches of individuals in the insurance industry. The study also identifies the factors causing privacy issues and recommends improving data privacy management in the insurance market.

Practical implications: The current study can be referred to by academicians, marketers, industry people, and policymakers. In addition, the study encourages companies and academicians to investigate further the process of data protection in the insurance industry.

Purpose: The primary objective of this investigation is to determine the importance of big data, machine learning, and systems integration in the creation, production, and promotion of the corporation’s life insurance products marketed in India overall designated insurance carriers. It is also necessary to investigate the function of these instruments in the sectors financial designed and operated managing approaches.

Methodology: The approach used for this analysis is mainly connected to evolutionary and exploratory research. Secondary information is used to obtain the necessary data for the study topic. Secondary data included scientific papers and videos supplied by specialists in diverse domains.

Findings: In this chapter, the authors explain the financial function of large data sets, computer sciences, and content marketing modelling and simulation in the designing, developing, and deploying financial products. The researcher investigated the sale of life insurance plans in India. Insurance Governing Planning Commission is a controlling organisation from the Government of India that oversees all registered insurance businesses in India. Insurance Regulatory and Development Authority (IRDAI) regulates a total of 60 businesses. Thirty-four are in the commercial banking industry, 24 are in the life insurance industry, and 2 are more significant than the average total cost.

Practical implication: Data analytics approaches in financial technological processes and private insurers are helping them increase their business turnovers, collections, and revenue. Similarly, big analysis of data is becoming increasingly important in corporate finance in the life insurance industry, particularly in improving operations, as well as attempting to address numerous problems such as how to optimise marketing strategies and how to enhance customer experience, which has resulted in the most significant goal of improving operational efficiency in the financial industry.

Introduction: Artificial intelligence (AI), the engineering of brilliant machinery, performs intelligent human intelligence tasks, such as learning and problem-solving. Insurance is a financial protection policy either for individuals or entities to reimburse losses from the insured company. The role of AI in insurance always helps enhance customer services and understand their behaviour.

Purpose: This chapter aims to determine the role of AI in the insurance industry in India. The insurance industry is expanding very fast, and to further increase its horizons, the part of the technology of AI is essential. However, this sector has initiated using AI technology and is expanding its scope to benefit the customers.

Methodology: The authors selected research papers of the last five years to review and determine how the technology changed during the period and how an increase in AI benefits the industry and facilitates delivering the best services, and understanding the customer’s needs and behaviour.

Findings: It has been found that the industry is moving very fast and adopting the AI technology methods to enhance customer services, betterment for growing India, and serve insurance services to the nation efficiently.