Decision Analytics Journal最新文献

{"title":"A data-driven risk assessment of cybersecurity challenges posed by generative AI","authors":"Rami Mohawesh ,&nbsp;Mohammad Ashraf Ottom ,&nbsp;Haythem Bany Salameh","doi":"10.1016/j.dajour.2025.100580","DOIUrl":"10.1016/j.dajour.2025.100580","url":null,"abstract":"<div><div>Generative artificial intelligence (GenAI) refers to machines that can create new ideas and generate outputs similar to human cognition. This technology has ushered in a new era, offering remarkable learning capabilities and producing unique results. In this paper, we explore the role of GenAI in cybersecurity, highlighting potential risks such as data poisoning attacks, privacy concerns, and bias in decision-making. The study aims to examine how GenAI can enhance cybersecurity by improving AI algorithms and propose strategies for mitigating associated risks. As GenAI continues to gain significance across industries, especially healthcare, it is crucial to understand its potential benefits and the risks it may pose to ensure safe and responsible deployment.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100580"},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904543","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":"A dual-phase framework for detecting authentic and computer-generated customer reviews using large language models","authors":"Dina Nawara ,&nbsp;Rasha Kashef","doi":"10.1016/j.dajour.2025.100581","DOIUrl":"10.1016/j.dajour.2025.100581","url":null,"abstract":"<div><div>Customer reviews are crucial in potential buyers’ decision-making process. However, on online platforms, the credibility of these reviews is often undermined by fake reviews, which can mislead users. With advancements in large language models (LLMs), the review landscape has transformed, making it more common to encounter computer-generated reviews created using state-of-the-art language models rather than genuine user feedback. This evolution poses significant challenges in distinguishing authentic reviews from artificially generated ones. To address these challenges, we propose a novel dual-phase framework that first generates high-diversity synthetic reviews using advanced LLMs to learn their patterns, and then it leverages this knowledge to enhance fake reviews detection. Our methodology involves two key phases. In the first phase, we generate computer-generated reviews by leveraging advanced methods, including generative transformers, trained on genuine user reviews. In the second phase; traditional and deep learning based classifiers, are incorporated as detection models which classify reviews as either authentic or computer-generated. Evaluated on a benchmark Amazon review dataset, our framework demonstrate (1) the efficacy of our approach in generating diverse and contextually relevant human-based and computerized-based reviews and (2) the robustness of our system in classifying and verifying the authenticity of reviews.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100581"},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912894","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":"A novel lift adjustment methodology for improving association rule interpretation","authors":"Bilal Sowan ,&nbsp;Li Zhang ,&nbsp;Nasim Matar ,&nbsp;J. Zraqou ,&nbsp;Firas Omar ,&nbsp;Athari Alnatsheh","doi":"10.1016/j.dajour.2025.100582","DOIUrl":"10.1016/j.dajour.2025.100582","url":null,"abstract":"<div><div>Association rules can offer a human-interpretable insight extracted from data. The lift measures used for evaluating association rules in classical Association Rule Mining (ARM) contexts are mainly based on traditional and well-known ones but suffer from interpretation inadequacy when dealing with skewed distributions or low support. This study introduces a new lift adjustment approach with four methods to overcome traditional lift measures and identify the best rules in association rule mining. More concretely, our main objective is to improve the interpretability of association rules to make them more practically relevant for decision-making. We propose an approach incorporating four novel lift adjustment methods (smoothed, weighted, log, and threshold-adjusted lift) to achieve this. We introduce a flexible, dynamic approach combined with four new lift adjustment methods: smoothed, weighted, logarithm, and threshold-adjusted lift. Each technique addresses specific limitations of the traditional lift measure and better captures the reliable representation of item associations by exaggerating stronger relationships or smoothing weaker ones. The proposed methods applied context-aware rule evaluation and adjustment based on measures of relative significance (e.g., Jaccard similarity). The experimental results involving real-world data and synthetic datasets reveal new methods’ effectiveness and robustness in understanding the strengths of association rules and provide a comprehensive view that considers item importance. We evaluate the performance stability of our proposed methods using statistical analysis, including ANOVA, chi-squared, t-tests, and effect size metrics.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100582"},"PeriodicalIF":0.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924103","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":"A multiple factor analysis and hierarchical clustering of global logistics governance and development","authors":"Delimiro Visbal-Cadavid ,&nbsp;Enrique Delahoz-Domínguez ,&nbsp;Adel Mendoza-Mendoza","doi":"10.1016/j.dajour.2025.100579","DOIUrl":"10.1016/j.dajour.2025.100579","url":null,"abstract":"<div><div>This study integrates the Logistics Performance Index (LPI), Worldwide Governance Indicators (WGI), and Human Development Index (HDI) through Multiple Factor Analysis (MFA) and hierarchical clustering to create a comprehensive perspective on global development. By clustering countries based on these indicators, the analysis reveals distinct profiles highlighting variations in logistics performance, governance quality, and socio-economic development, yielding insights essential for addressing global development challenges. Three primary clusters emerged, representing countries with socio-economic vulnerabilities, emerging economies with moderate governance, and highly developed nations with advanced infrastructure. Key results demonstrate that Cluster 1 countries require substantial support in governance and infrastructure, while Cluster 2 nations benefit from institutional and logistical investment. Cluster 3 exemplifies governance and socio-economic standards benchmarks, offering sustainable development models. MFA and hierarchical clustering have proven effective in categorising countries with complex data, allowing policymakers to tailor development strategies. The study underscores the need for ongoing research to capture shifts in country profiles and assess intervention impacts over time.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100579"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898990","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":"A Stackelberg game analysis of livestreaming sales and product returns in e-commerce","authors":"Fangfang Wei ,&nbsp;Hao Hao ,&nbsp;Pourya Pourhejazy ,&nbsp;Zhaoran Xu","doi":"10.1016/j.dajour.2025.100578","DOIUrl":"10.1016/j.dajour.2025.100578","url":null,"abstract":"<div><div>Many enterprises selling products on e-commerce platforms have adopted livestreaming to increase sales volume. A high return rate, caused by an exaggerated presentation of the products, can overwhelm the supply chain. Livestreaming considering the product return issue has received little attention in the academic literature. Building on the existing knowledge of the traditional e-commerce sales model, a Stackelberg game model led by an apparel enterprise is established to study livestreaming as a new sales strategy, considering the return rates, the livestreaming anchors’ commission, and the products’ diminishing time-value. A comparative analysis investigates whether the livestreaming sales model increases profitability, considering that some products may be returned. The results show that the return rate has a meaningfully different impact on the optimal price and sales volume of both the apparel enterprise and the third-party liquidation seller. In livestreaming sales, if the commission charged by the anchor passes a certain threshold, the apparel enterprise’s profit will be less than its traditional e-commerce profit, even with a low return rate. It is also found that a higher diminishing time-value coefficient of apparel may correspond to lower pricing by the third-party liquidation seller.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100578"},"PeriodicalIF":0.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898989","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":"Multi-criteria decision making to explore the relationship between supply chain mapping and performance","authors":"Md Ainul Kabir ,&nbsp;Sharfuddin Ahmed Khan ,&nbsp;Angappa Gunasekaran ,&nbsp;Muhammad Shujaat Mubarik","doi":"10.1016/j.dajour.2025.100577","DOIUrl":"10.1016/j.dajour.2025.100577","url":null,"abstract":"<div><div>In today’s highly dynamic and volatile business environment, the performance of a supply chain significantly depends on its structure, technological capabilities, and the adaptability of its constituent stages. Supply chain mapping, an approach to represent complex supply chain networks, is crucial for enhancing supply chain performance by identifying critical linkages, flows, and relationships. Despite its strategic importance, the specific impacts of supply chain mapping attributes on various performance indicators remain underexplored. Addressing this research gap, this study investigates the relationships between key supply chain mapping attributes (<em>e.g</em>., information flow, lead-time, mode of transportation) and supply chain performance indicators (<em>e.g</em>., reliability, responsiveness, agility). To achieve this, the study employs a multi-step analytical approach: first, relevant attributes are identified through a systematic literature review; second, these attributes are validated using the Delphi method involving international supply chain experts; finally, the Grey Decision-Making Trial and Evaluation Laboratory (Grey-DEMATEL) technique is applied to establish interrelationships among the attributes. Findings reveal that information flow is the most influential supply chain mapping attribute, significantly impacting multiple performance indicators, especially supply chain responsiveness. The novelty of this research lies in its integrative use of Delphi and Grey-DEMATEL methods, providing practitioners with actionable insights into effectively leveraging supply chain mapping to achieve strategic performance improvements.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100577"},"PeriodicalIF":0.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886652","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":"A systematic review of machine learning for hybrid intelligence in production management","authors":"Carl René Sauer,&nbsp;Peter Burggräf,&nbsp;Fabian Steinberg","doi":"10.1016/j.dajour.2025.100574","DOIUrl":"10.1016/j.dajour.2025.100574","url":null,"abstract":"<div><div>The increasing use of intelligent data processing and its capacity to handle vast data sets enhance efficiency and effectiveness in production management. Consequently, machine learning models have become essential for decision-making in this domain. Previous literature reviews have not considered the perspective of real business requirements from the domain environment, including a knowledge base of theoretical foundations and available methods within the domain. To provide a scientific overview of the current state of the art and to establish a starting point for developing new approaches, this paper presents the results of a systematic literature review. 217 publications were analyzed and synthesized. The publications are classified based on a developed framework that considers the decision type, the production management application, the underlying objective, type, technique, concrete algorithm of the ML model, and decision support for production management issues. A descriptive analysis reveals that there are approaches for all decision types, including unstructured decisions. Surprisingly, some of these approaches are not solely based on simulations to find an optimum. Remarkably, the number of publications related to the type of decision support does not decrease with increasing complexity. Although this paper provides practical guidance to practitioners in selecting applications and ML models to assist their decisions in their production environment, there is a significant need for further research to assist production managers. This can be achieved by developing hybrid models involving interaction between machine and human agents.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100574"},"PeriodicalIF":0.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848670","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":"A systematic review of time series algorithms and analytics in predictive maintenance","authors":"Md Asif Bin Syed ,&nbsp;Md Rabiul Hasan ,&nbsp;Nahian Ismail Chowdhury ,&nbsp;Md Hadisur Rahman ,&nbsp;Imtiaz Ahmed","doi":"10.1016/j.dajour.2025.100573","DOIUrl":"10.1016/j.dajour.2025.100573","url":null,"abstract":"<div><div>The evolution of Industry 5.0, along with its predecessor Industry 4.0, has significantly boosted the adoption of predictive maintenance through integrating Internet of Things (IoT) sensors and real-time big data analysis, enabling the identification and prevention of equipment failures. This integration has also facilitated the development of time series-based predictive maintenance methods, addressing univariate and multivariate problems to capture temporal relationships and predict future equipment conditions. These approaches encompass prognostic tasks such as Remaining Useful Life (RUL) estimation, anomaly detection, failure classification, and clustering. Despite the extensive application of time series techniques in predictive maintenance, a comprehensive review focusing specifically on integrating time series methods with traditional and advanced machine learning and deep learning models is still missing. This study aims to fill that gap by systematically reviewing the literature on using time series algorithms in predictive maintenance. Using the PRISMA framework, we extracted and analyzed relevant literature from two major scientific databases, SCOPUS and Web of Science (WOS). The focus is on peer-reviewed journal papers on predictive maintenance and time series algorithms published since 2018. The review identified 55 peer-reviewed papers that utilized time series algorithms in predictive maintenance. This study systematically analyzed the most commonly used time series algorithms in predictive maintenance, including benchmark datasets and implementation methods. It highlighted common preprocessing steps for time series analysis and provides a comparative analysis of these algorithms and their performance metrics. The study also explored the challenges in utilizing time series algorithms for predictive maintenance and suggested potential research areas and future directions.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100573"},"PeriodicalIF":0.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879317","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":"A systematic review of artificial intelligence applications in education: Emerging trends and challenges","authors":"Tomás Matos ,&nbsp;Walter Santos ,&nbsp;Eftim Zdravevski ,&nbsp;Paulo Jorge Coelho ,&nbsp;Ivan Miguel Pires ,&nbsp;Filipe Madeira","doi":"10.1016/j.dajour.2025.100571","DOIUrl":"10.1016/j.dajour.2025.100571","url":null,"abstract":"<div><div>The academic world is becoming increasingly interested in the applications of Artificial Intelligence technology in education. A systematic review examines AI applications in education, focusing on their effectiveness, challenges, and implications. A comprehensive analysis of studies published between 2011 and 2024 encompassed 45 research articles from major databases, such as PubMed Central, IEEE Xplore, Elsevier, Springer, MDPI, ACM, and PMC. The findings highlight the predominant use of generative AI tools like ChatGPT (30%), followed by other advanced technologies, such as GPT-4, machine learning, and virtual reality. Research across global regions, particularly in Canada (18%), the United States (12%), and China (8%), highlights the multifaceted applications of AI in enhancing personalized learning, fostering critical thinking, and supporting professional education. Tools such as ChatGPT have demonstrated strong performance in theoretical knowledge delivery and medical education, while augmented and virtual reality excels in practical skill development. Despite these advances, challenges such as data privacy concerns, algorithmic bias, and the need for specialized educator training remain critical.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100571"},"PeriodicalIF":0.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870711","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":"An unsupervised machine learning approach for cyber threat detection using geographic profiling and Domain Name System data","authors":"Seyed-Ali Sadegh-Zadeh,&nbsp;Mostafa Tajdini","doi":"10.1016/j.dajour.2025.100576","DOIUrl":"10.1016/j.dajour.2025.100576","url":null,"abstract":"<div><div>Cyber threat detection is a critical challenge in cybersecurity, with numerous existing solutions relying on rule-based systems, supervised learning models, and entropy-based anomaly detection. However, rule-based methods are often limited by their dependence on predefined signatures, making them ineffective against novel attacks. Supervised learning approaches require extensive labelled​ datasets, which are often unavailable or quickly outdated due to evolving threats. Traditional entropy-based anomaly detection techniques struggle with high false positive rates and computational inefficiencies when applied to large-scale DNS traffic. These limitations necessitate a more adaptive and scalable approach. This study integrates geographic profiling with Domain Name System (DNS) data analysis to enhance cyber threat detection, offering a novel approach to understanding cyber threats through geographical insights. The primary objective is to develop unsupervised machine learning models to identify potentially malicious IP addresses based on DNS query anomalies, leveraging the correlation between geographic locations and DNS behaviours. The proposed method utilizes K-means clustering to process geolocation and passive DNS datasets, detect anomalies, and identify cyber threat hotspots. Our results demonstrate the effectiveness of geographic profiling in cyber threat intelligence, with K-means clustering achieving a high silhouette score of 0.985, indicating well-separated and meaningful threat groupings. Additionally, our entropy-based anomaly detection identified high-risk DNS activities with an accuracy of 92.3%, reducing false positives compared to traditional DNS monitoring techniques. The geospatial analysis revealed that 82% of cyber threats originate from 15 high-entropy regions, aligning with global cybersecurity incident reports. The proposed predictive framework significantly improves cyber threat detection, enhancing real-time threat visibility and response capabilities. By integrating geographic profiling with DNS data analysis, we advance cybersecurity defences by providing a more nuanced and data-driven understanding of cyber threats.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100576"},"PeriodicalIF":0.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870712","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}