Regulating Telematics Insurance

Boom, Freyja van den

doi:10.1007/978-3-030-52738-9_12

Cited by 6 publications

(3 citation statements)

References 38 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Insurance companies have recently started using artificial intelligence to gain valuable insights about drivers and vehicle security, analysing data retrieved from telematics smart boxes mounted on board [29]. Our work considers a specific use case in this domain where an AI model, also referred to as an "AI agent," is employed to optimise the assistance service of the insurance company Generali Italia S.p.A.…”

Section: A Use Casementioning

confidence: 99%

Translating Image XAI to Multivariate Time Series

Tronchin,

Cordelli,

Celsi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

As Artificial Intelligence (AI) is becoming part of our daily lives, the need to understand and trust its decisions is becoming a pressing issue. EXplainable AI (XAI) aims at answering this demand, providing tools to get insights into the models' behaviour and reasoning. Following this trend, our research paper explores the explainability of a deployed multimodal architecture applied to a real-world dataset of multivariate time series. The study aims to enhance the trustworthiness of an AI agent responsible for crash detection in an insurance company's automatic assistance service. By introducing an XAI layer, we provide insights into the AI agent's decision-making process, enabling the optimization of emergency medical services allocation. The dataset consists of real-world telematics data collected from vehicles equipped with black box technology. The challenge lies in explaining the complex interactions within the multivariate time series data to accurately understand the forces applied to vehicles during accidents. To this end, we adapt to this context two state-of-the-art XAI model-specific approaches, originally designed for images. We offer a qualitative and a quantitative evaluation, also comparing with a well-known agnostic method, and further validating our findings on an external dataset. The results show that Integrated Gradients, among the methodologies examined, is the most effective approach. Its ability to handle the complexity of the data provides the most comprehensive and insightful explanations for the considered use case. The findings emphasize the potential of XAI to enhance the trustworthiness of AI systems and optimize emergency response in the insurance industry. Code is available at https://github.com/ltronchin/translating-xai-mts.git.

show abstract

Section: A Use Casementioning

confidence: 99%

Translating Image XAI to Multivariate Time Series

Tronchin,

Cordelli,

Celsi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Big data is frequently identified by several crucial attributes, commonly known as the Vs, which include volume, variety, and velocity, alongside others like veracity and value. These features underscore the extensive amount, diverse types, and rapid processing speed associated with big data analytics [17]. Big data analytics encompasses the gathering, retention, processing, and interpretation of substantial datasets to extract valuable insights for decision-making.…”

Section: Related Workmentioning

confidence: 99%

An Exhaustive and Methodical Analysis of Literature Pertaining To Technigues for Managing Big Data within the Context of the Internet of Things

Jaseem,

Kurnaz

2024

JECNAM

View full text Add to dashboard Cite

The merging of big data and the Internet of Things (IoT) has brought both exceptional difficulties and possibilities in data management. This study offers a thorough and methodical examination of the current literature on large data management approaches inside the Internet of Things framework. The study encompasses a broad spectrum of inquiry, ranging from fundamental notions to sophisticated approaches. The Internet of Things (IoT) is a powerful force that seeks to improve user experience and lifestyle. It incorporates several essential technologies including human-machine and machine-to machine communications, networking technologies, and sensor technologies. Fundamental to the success of the Internet of Things is the effective management of data transmitted through these technologies. This article explores the issues and challenges associated with data management in the context of the Internet of Things and examines different aspects of data, including its sources, collection processes, processing methods, and transmission devices. The article identifies and discusses problems arising from the need to process huge amounts of heterogeneous data in different systems. In relation to these issues, the logical and physical aspects of data management and communications networks are discussed. Additionally, the article takes an in-depth look at the data models used in IoT and explores data management, cleansing, and indexing techniques that take into account the unique characteristics of IoT data. The final sections of the paper comprehensively discuss the benefits and limitations associated with data management in IoT.

show abstract

“…In which ethics were formulated in the form of laws and legislation. Perhaps this is due to the ethics of the artificial intelligence community being characterized by abolishing police control and transforming it into self-censorship, with the psychological reference replacing the social reference [17].…”

Section: The Importance Of Ethical Aimentioning

confidence: 99%

Developing Ethical Usage Guid-elines for Customers of Artificial Intelligence and Big Data Analytics: Ethical Applications within Realm of Big Data Analytics

Khaleel,

Abdulkareem,

Hamodi

2023

JAIMLNN

View full text Add to dashboard Cite

In both the operational and customer-facing facets of the insurance sector, big data analytics and ever-evolving machine learning and artificial intelligence (AI) capabilities have become indispensable. Insurance-related goods and services, which cover things like business property insurance, auto insurance, and personal health insurance, are essential for advancing the economy and society. The significance of artificial intelligence and machine learning in preserving this equilibrium within the insurance industry has already been established. However, as AI and machine learning are used more frequently, it creates new issues and calls into question the industry's moral standards. In order to shed light on any potential new conflicts and concerns, it is vital to look into the ethical ramifications and conundrums surrounding the use of data in insurance innovation. In order to examine and gain a deeper understanding of the ethical landscape relating to the tensions surrounding the use of big data analytics, AI, and machine learning methodologies to sustain the operations of the insurance industry, this study combines the insights of insurance professionals with the expertise of an AI ethics specialist.

show abstract

Regulating Telematics Insurance

Cited by 6 publications

References 38 publications

Translating Image XAI to Multivariate Time Series

Translating Image XAI to Multivariate Time Series

An Exhaustive and Methodical Analysis of Literature Pertaining To Technigues for Managing Big Data within the Context of the Internet of Things

Developing Ethical Usage Guid-elines for Customers of Artificial Intelligence and Big Data Analytics: Ethical Applications within Realm of Big Data Analytics

Contact Info

Product

Resources

About