International Journal of Information Management Data Insights最新文献

{"title":"Customization of health insurance premiums using machine learning and explainable AI","authors":"Manohar Kapse ,&nbsp;Vinod Sharma ,&nbsp;Rutuj Vidhale ,&nbsp;Varun Vellanki","doi":"10.1016/j.jjimei.2025.100328","DOIUrl":"10.1016/j.jjimei.2025.100328","url":null,"abstract":"<div><div>This study presents an analysis of health insurance premiums across various customer segments. Specifically, it aims to identify the factors influencing the pricing of health insurance premiums, vis a vis their impact on different customer segments. Using a dataset from consumer surveys, coupled with multiple Machine Learning models, the study analyzed and predicted features of importance for premiums paid across various age groups, gender, health conditions, policy duration, and the number of members included in the policy. Finally, the explainable AI was used to predict the weightage of each variable in determining the price of the insurance policy for the individuals. The findings provide crucial insights into the factors such as demographic factors and lifestyle that effectively influence the pricing of health insurance premiums vis a vis their impact on various customer segments. The results of this study will assist prospective buyers and decision-makers in choosing the best health insurance plans.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100328"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143226889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing recommender systems with provider fairness through preference distribution awareness","authors":"Elizabeth Gómez ,&nbsp;David Contreras ,&nbsp;Ludovico Boratto ,&nbsp;Maria Salamó","doi":"10.1016/j.jjimei.2024.100311","DOIUrl":"10.1016/j.jjimei.2024.100311","url":null,"abstract":"<div><div>Going beyond recommendations’ effectiveness, by ensuring properties such as unbiased and fair results, is an aspect that is receiving more and more attention in the literature. This means not only providing accurate recommendations but also ensuring that the visibility of providers aligns with user preferences and demographic representation, which has been identified as a key aspect of fairness in recommender systems. In particular, <em>provider fairness</em> enables the generation of results which are equitable for different (groups of) providers. In this paper, we raise the problem of <em>how recommendations are distributed when enabling provider fairness</em>. Indeed, on the one hand, users have clear preferences with respect to which providers they choose (<em>e.g.</em>, Italian users mostly buy Italian food), so recommendations should reflect these preferences. On the other hand, content providers should be able to reach a diverse audience, and be visible across the different user groups that expressed a preference for them. Specifically, we consider demographic groups based on their continent of origin for both users and providers, and assess how the preferences of the user groups are distributed across the provider groups. We first show that the state-of-the-art models and the existing approaches that enable provider fairness do not reflect the original distribution of the user preferences. To enable this property, we propose a re-ranking approach that, thanks to the use of buckets associating users and items, favors what we call <em>preference distribution-aware provider fairness</em>. Results on two real-world datasets (<em>i.e</em>., the Book-Crossing and COCO) show that our approach can enable provider fairness and tailor the recommendations to the original distribution of the user preferences, with negligible losses in effectiveness. In particular, in the Books dataset, our approach obtains an overall disparity that is around 6%. On the other hand, in the case of the COCO dataset, the disparities are reduced to 2%.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100311"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143095578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automating materiality assessment with a data-driven document-based approach","authors":"Matteo Francia,&nbsp;Enrico Gallinucci,&nbsp;Matteo Golfarelli","doi":"10.1016/j.jjimei.2024.100310","DOIUrl":"10.1016/j.jjimei.2024.100310","url":null,"abstract":"<div><div>Materiality assessment is a critical process for companies to understand the interest perceived by its stakeholders towards topics related to environmental, social, and governance issues. Materiality assessment helps companies define their growth and communicative strategies; recently, it has become crucial within sustainability reporting, i.e., the practice of annually declaring the activities conducted to pursue economic growth in a sustainable way for society. In this paper, we propose a data-driven and automated approach to carry out materiality assessment. Stakeholders’ perception of important topics is obtained by analyzing relevant textual documents (e.g., company reports, press releases, social media posts), identifying mentions of potentially interesting topics, and converting them to scores that produce materiality rankings or matrices. An iterative methodology is proposed to incrementally carry out materiality assessment by progressively building the domain knowledge required to automate the process. Efficiency and effectiveness evaluations are carried out in a real-world scenario.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100310"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143095579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital payment adoption: A revisit on the theory of planned behavior among the young generation","authors":"Berto Usman ,&nbsp;Heris Rianto ,&nbsp;Somnuk Aujirapongpan","doi":"10.1016/j.jjimei.2025.100319","DOIUrl":"10.1016/j.jjimei.2025.100319","url":null,"abstract":"<div><div>This study examines how individual behavior is influenced by intentions and factors such as financial literacy, subjective norms, and perceived behavioral control. A quantitative survey was conducted with 263 respondents familiar with fintech applications, specifically digital payments, using purposive and snowball sampling technique. Empirical analysis with Smart-PLS reveals significant effects of these factors. Notably, financial literacy and perceived behavioral control significantly influence intention, whereas subjective norms shows no clear effect. Testing for indirect relationships indicates that intention serves as the sole mediator between perceived behavioral control and digital payment usage behavior. However, intention does not mediate the relationships between financial literacy and digital payment behavior or between subjective norms and digital payment behavior. This study's exploration of intention as a mediator provides valuable insights into the dynamics of these relationships, addressing a knowledge gap in management literature and contributing to the revisit of Theory of Planned Behavior in the context of digital payment adoption.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100319"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143095583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of AI literacy on risk management skills and the roles of diagnostic capabilities and prognostic capabilities: Empirical insight from Thai gen Z accounting students","authors":"Kanokwan Meesook ,&nbsp;Narinthon Imjai ,&nbsp;Berto Usman ,&nbsp;Busaya Vongchavalitkul ,&nbsp;Somnuk Aujirapongpan","doi":"10.1016/j.jjimei.2025.100341","DOIUrl":"10.1016/j.jjimei.2025.100341","url":null,"abstract":"<div><div>This study investigates the relationship between AI literacy, diagnostic capabilities, prognostic capabilities, and risk management skills among Generation Z accounting students in Thailand. Using a quantitative research design, data were collected from 400 participants and analyzed through Partial Least Squares Structural Equation Modeling (PLS-SEM). The results show that AI literacy positively influences both diagnostic and prognostic capabilities. In turn, these capabilities significantly contribute to the development of risk management skills, with prognostic capabilities showing a stronger effect. The findings highlight the value of integrating AI literacy into accounting education to better prepare students with essential analytical and risk-related competencies for the evolving digital landscape.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100341"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the impact of social relationships and system experiences on consumers’ acceptance of social commerce in the fashion sector: an empirical study","authors":"Sahil Singh Jasrotia ,&nbsp;Alex Pak Ki Kwok ,&nbsp;Surabhi Koul","doi":"10.1016/j.jjimei.2025.100333","DOIUrl":"10.1016/j.jjimei.2025.100333","url":null,"abstract":"<div><div>This study investigated the influence of social relationships and system experiences on consumers’ acceptance of social commerce (s-commerce) in the fashion sector. Perceived social connectedness, critical mass, ease of use, system capability, enjoyment, and usefulness were examined as factors impacting consumers’ intention to use s-commerce. Data from 558 valid responses were analysed using structural equation modelling. The results revealed that perceived social connectedness indirectly influences perceived usefulness and intention to use s-commerce through system experience-related factors. However, no significant effect was found between perceived system capability and perceived usefulness. The proposed model explains 64% of the variance in perceived usefulness and 62% in intention to use. This study fills a research gap by providing insights into the impact of social relationships and system experiences on consumer acceptance of s-commerce in fashion retailing. It offers guidance for practitioners to improve their s-commerce platforms and marketing strategies.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100333"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Do chatbots support consumer performance? Investigating the role of E-lifestyle and anthropomorphism in the service industry","authors":"Retno Dewanti ,&nbsp;Ridho Bramulya Ikhsan","doi":"10.1016/j.jjimei.2025.100339","DOIUrl":"10.1016/j.jjimei.2025.100339","url":null,"abstract":"<div><div>The growing implementation of chatbots in the service industry reflects continued innovation in this area. However, concerns persist regarding chatbot competence in addressing consumer inquiries, potentially hindering both the interaction experience and consumer performance. This study investigates the factors driving consumer performance in chatbot interactions. Data were collected via an online survey of 336 Indonesian consumers. Partial least squares-structural equation modeling (PLS-SEM) was employed to test the structural model. The findings reveal that e-lifestyle significantly influences both chatbot experience and competence. Anthropomorphism significantly impacts chatbot experience, competence, and the resulting consumer performance. Moreover, both chatbot experience and competence significantly affect consumer performance. Furthermore, chatbot competence significantly shapes the user experience. This study contributes to both theoretical and practical understanding of chatbots within the service industry.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100339"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining the effect of AI-BDA on manufacturing firm performance: An Indian approach","authors":"Vaibhav S. Narwane ,&nbsp;Pragati Priyadarshinee","doi":"10.1016/j.jjimei.2024.100306","DOIUrl":"10.1016/j.jjimei.2024.100306","url":null,"abstract":"<div><div>Manufacturing firms face an uncertain and continuosly changing environment because of innovations, technological changes, and globalization. To cope with this quick and uncertain environment, firms need to be flexible. Artificial Intelligence (AI) and Big Data Analytics (BDA) are must for manufacturing firms to achieve the flexibility in procurement to manufacturing to marketing. This study explores role of AI-BDA played between Supply Chain Flexibility (SCF) and Supply chain firms performance(SCFP) through six hypothesis. A sample data of 297 responses from forty Indian manufacturing firms were collected. Exploratory and confirmatory factorial analysis were used to analyse the collected data. Out of six hypothesis, four hypothesis are supported. The results show positive impact of AI, BDA and SCF on supply chain firm performance. Also AI positively impacts on BDA. However two hypothesis not supported are positive effect of AI and BDA on SCF needs further investigated. The study can guide decision makers to understand role of AI and BDA to improve supply chain performance.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100306"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142664168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing the power of language models in cybersecurity: A comprehensive review","authors":"Ramanpreet Kaur,&nbsp;Tomaž Klobučar,&nbsp;Dušan Gabrijelčič","doi":"10.1016/j.jjimei.2024.100315","DOIUrl":"10.1016/j.jjimei.2024.100315","url":null,"abstract":"<div><div>Language models are transforming cybersecurity by addressing critical challenges such as the growing skills gap, the need for expertise augmentation, and knowledge retention. These models offer scalable, adaptable, and round-the-clock defenses against evolving cyber threats. By generating human-like text, processing data efficiently, and providing actionable responses, language models bridge the gap between automated systems and human expertise for different cybersecurity applications. However, the application and adaptation of language models for cyber security is still in its infancy. This review explores the use of general models, such as BERT, and larger models in cybersecurity research. It provides a structured framework for developing customized language models tailored to applications including content analysis, software and systems analysis, threat intelligence and monitoring, and cyber vetting. The study critically examines challenges, such as data confidentiality, infrastructure requirements, integration complexity and the evolving threat landscape. Moreover, it underscores the need for transparency, responsible use, and bias mitigation to ensure reliable and secure deployment of these models. In addition, this work critically examines the socio-technical dimensions of language model integration, focusing on their impact on organizational workflows, decision making and human-machine collaboration. By considering both technical and socio-technical considerations, this review provides a roadmap for future research and development. It highlights the potential of language models to improve organizational resilience, ensure secure implementation, and support informed decision-making in cybersecurity practice.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100315"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CovKG: A Covid-19 Knowledge Graph for enabling multidimensional analytics on Covid-19 epidemiological data considering spatiotemporal, environmental, health, and socioeconomic aspects","authors":"Rudra Pratap Deb Nath ,&nbsp;S.M. Shafkat Raihan ,&nbsp;Tonmoy Chandro Das ,&nbsp;Torben Bach Pedersen ,&nbsp;Debasish Ghose","doi":"10.1016/j.jjimei.2025.100325","DOIUrl":"10.1016/j.jjimei.2025.100325","url":null,"abstract":"<div><div>The Covid-19 pandemic is influenced by many environmental, health, and socioeconomic aspects such as air pollution, comorbidity, occupation, etc. To better manage future pandemics, decision-makers need comprehensive data on Covid-19 mortality and morbidity. Most Covid-19 data sources focus on spatiotemporal aspects, and existing research often overlook the combined impact of multiple interconnected factors. This study introduces a Covid-19 Knowledge Graph (CovKG) derived from 20 data sources, enabling multidimensional analysis of epidemiological data, including time, location, temperature, comorbidity, occupation, and others. CovKG is modeled using RDF, connected to 10,951 external resources, and semantically enriched with Data Cube (QB) and QB for OLAP (QB4OLAP) vocabularies to adhere to the FAIR principles and ensure OLAP compatibility. Finally, we perform a qualitative and comparative evaluation and extract statistical insights across multiple dimensions of Covid-19 epidemiology. When assessed, CovKG answers 100% of competency queries, outperforming other data stores that only answer 39%. CovKG and its analytical interface are available at <span><span>https://bike-csecu.com/datasets/CovKG/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100699,"journal":{"name":"International Journal of Information Management Data Insights","volume":"5 1","pages":"Article 100325"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}