Decision Analytics Journal最新文献

{"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}

{"title":"An analytical study of structural equation modeling on organizational resilience and financial performance in Ecuadorian SMEs","authors":"Juan Diego Ochoa Crespo ,&nbsp;José Manuel Feria Domínguez ,&nbsp;Diego Marcelo Cordero Guzmán","doi":"10.1016/j.dajour.2025.100575","DOIUrl":"10.1016/j.dajour.2025.100575","url":null,"abstract":"<div><div>Organizational resilience is vital for the sustainability of SMEs in emerging economies like Ecuador. This study proposes and validates a conceptual model integrating reactive and organizational-financial resilience to assess their impact on financial performance. Based on data from 333 SMEs, findings show that employee commitment, leadership, and social capital significantly drive reactive resilience, which serves as a precursor to broader resilience. Organizational resilience, in turn, strongly influences financial outcomes, confirming its strategic relevance in volatile contexts. Although information systems had a modest impact, cohesive human and social capital proved essential. Surprisingly, general business practices showed no significant effect on resilience, indicating the need for more focused strategies. This research bridges a literature gap by offering an evidence-based framework for SMEs, guiding managerial action and policy formulation.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100575"},"PeriodicalIF":0.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863983","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 machine learning approach for text pattern diagnosis in mental health consultations","authors":"Safitri Juanita ,&nbsp;Anisah Hasratniwati Daeli ,&nbsp;Mohammad Syafrullah ,&nbsp;Wiwik Anggraeni ,&nbsp;Mauridhi Hery Purnomo","doi":"10.1016/j.dajour.2025.100572","DOIUrl":"10.1016/j.dajour.2025.100572","url":null,"abstract":"<div><div>Online health consultation services are crucial for mental health support, particularly in densely populated areas. However, the heavy reliance on human expertise often leads to delays, necessitating more efficient and automated solutions. This study developed a machine learning framework to automate doctor response patterns for mental health questions — focusing on anxiety, depression, and stress — using clinically validated data from an Indonesian Online health consultation platform. We performed comprehensive text preprocessing, including duplicate removal, special character elimination, case folding, stopword removal, tokenization, lemmatization, and part-of-speech tagging, and evaluated four feature extraction methods: Word2Vec, Bag-of-Words, N-Gram, and Global Vectors for Word Representation. Five machine learning algorithms — Naïve Bayes, K-Nearest Neighbors, Random Forest, Neural Network, and Gradient Boosting — were tested, along with hybrid models combining Bagging Classifier or Genetic Algorithm. The results showed that Gradient Boosting achieved the highest accuracy (0.842) among standalone models, with high precision (0.858) and F1-score (0.864) for depression prediction, and recall (0.850) and F1-score (0.856) for stress prediction. The Gradient Boosting-Bagging Classifier hybrid matched this accuracy (0.842), while the Gradient Boosting-Genetic Algorithm hybrid showed superior performance for anxiety prediction (precision: 0.888, recall: 0.816). N-Gram and Bag-of-Words methods and the 90:10 and 70:30 train–test splits consistently produced optimal results. This work demonstrates that machine learning can automate mental health responses at scale, with Gradient Boosting balancing accuracy and efficiency. Future research will explore transformer-based models and multilingual validation to improve broader implementation.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100572"},"PeriodicalIF":0.0,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898988","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 dynamic pharmaceutical inventory investment management model during pandemics using metaheuristic algorithms","authors":"Vinita Dwivedi,&nbsp;Mamta Keswani","doi":"10.1016/j.dajour.2025.100570","DOIUrl":"10.1016/j.dajour.2025.100570","url":null,"abstract":"<div><div>This study presents a comprehensive approach to managing pharmaceutical inventory during pandemics. The study focuses on optimizing investment strategies for promoting COVID-19 medicine across various price ranges while carefully preserving pharmaceutical products. We develop a customized inventory model that accounts for item degradation, considering factors such as price, infection rate, and preservation methods. This model is adaptable to three pandemic scenarios, with the deterioration rate influenced by the level of investment in preservation technology. Our approach employs optimal control theory to dynamically adjust investment rates, maximizing the effectiveness of resource allocation. We also utilize advanced optimization algorithms, including Ant Colony and Cuckoo Search Algorithms, to optimize pricing, preservation strategies, and replenishment schedules. Through numerical experiments, we demonstrate the efficacy of our dynamic investment approach, providing empirical evidence of its effectiveness. Additionally, sensitivity analysis on key parameters offers valuable insights for decision-makers, highlighting the importance of dynamically managing pharmaceutical inventory during pandemics. Our study provides practical solutions and managerial insights for informed pharmaceutical inventory decisions during the pandemic.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100570"},"PeriodicalIF":0.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829028","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-based logistics cooperation model for agricultural product supply chains in live streaming e-commerce","authors":"Lijun Shi ,&nbsp;Hailong Cheng","doi":"10.1016/j.dajour.2025.100569","DOIUrl":"10.1016/j.dajour.2025.100569","url":null,"abstract":"<div><div>The rapid growth of live streaming e-commerce (LSEC) has revolutionized agricultural product sales, but the perishable nature of these products poses significant challenges to supply chain logistics. Logistics is vital to the agricultural products live streaming e-commerce supply chain. This study analyzes four logistics decision models using the Stackelberg game approach: independent of the third-party logistics (TPL) provider, cooperation with the farmer, cooperation with the LSEC platform, and integrated cooperation among the players. We develop a decision model for the agricultural products live streaming e-commerce supply chain that takes into account logistics service efforts and compares and discusses the sales price, the level of logistics service effort, and market demand under different models. We use numerical examples to study the choice of logistics cooperation model for players in the agricultural products live streaming e-commerce supply chain. The study results show that logistics cooperation can effectively share the logistics service costs, reduce the sales price, and improve the level of logistics service effort. The logistics cooperation model improves the cooperating players and supply chain profits and demonstrates that reasonable profit distribution is the key to successful cooperation among supply chain players. The logistics service efforts improve supply chain profits and benefit all cooperative players. Moreover, a reasonable profit distribution threshold enhances cooperation and profitability in agricultural supply chains. This study provides a reference for the logistics cooperation among players in the agricultural products live streaming e-commerce supply chain.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100569"},"PeriodicalIF":0.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848658","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 consumer behavior analytics model for commercial district marketing using network-structured stamp rally data","authors":"Yuya Ieiri ,&nbsp;Shao Tengfei ,&nbsp;Osamu Yoshie","doi":"10.1016/j.dajour.2025.100567","DOIUrl":"10.1016/j.dajour.2025.100567","url":null,"abstract":"<div><div>Marketing strategies should target entire commercial areas, not just individual stores. This study highlights the data collected from stamp rally events as cross-sectional consumer behavior data. Although stamp rally data have been analyzed as tabular data, this approach should capture the complexity of consumer behavior observed during such events. This study focused on the co-occurrence relationships between the pairs of stores identified through data. Moreover, the study proposed a novel method to analyze consumer behavior by representing these relationships in a network structure to address this challenge. Two events were held in 2023. In one event, data were collected from 621 participants in one event, and in the other event, data were collected from 1040 participants. The collected data were analyzed using conventional frequent pattern mining methods applied to tabular data and the proposed network-based method. Consequently, the proposed method identified community hub stores that could be used as catalysts for marketing to new consumer groups beyond the community.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100567"},"PeriodicalIF":0.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808705","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 machine learning and explainability-driven methodology for identifying winning strategies in Rugby Union","authors":"Arnaud Odet ,&nbsp;Thomas Bechard ,&nbsp;Pierre Moretto ,&nbsp;Sebastien Dejean ,&nbsp;Cristian Pasquaretta","doi":"10.1016/j.dajour.2025.100568","DOIUrl":"10.1016/j.dajour.2025.100568","url":null,"abstract":"<div><div>Interest in predicting sports match outcomes has grown significantly, driven by advancements in machine learning techniques and widespread adoption. However, the utilization of these predictive models in enhancing tactical team performance remains relatively limited. We propose a methodology that combines machine learning and algorithm explainability techniques, which were demonstrated through a case study on Rugby Union. Our study unfolds in two phases: first, we identify the most suitable modeling approach for our data by establishing a prediction model based on performance indicators observed during games. Subsequently, we applied an analysis based on SHapley Additive exPlanations (SHAP) values to interpret the predictions of this model. Our findings serve three primary purposes: (i) from a global standpoint, identifying performance indicators that primarily determine match outcomes; (ii) from an aggregated point of view highlighting strengths and weaknesses of any given team; and (iii) from a local perspective, offering technical staff diagnostic analyses of past games.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100568"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143737898","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":"An investigation of Frequentist and Ensemble Bayesian-aided techniques for prioritizing anomaly detection methods in time-series data","authors":"Vignesh Divakaran ,&nbsp;Vipasha Rana","doi":"10.1016/j.dajour.2025.100566","DOIUrl":"10.1016/j.dajour.2025.100566","url":null,"abstract":"<div><div>Accurately detecting anomalous points in time-series data is critical, as false positives can mislead business stakeholders, waste valuable resources, and diminish the overall impact of the detection system. While various statistical and machine learning techniques are employed to flag potential anomalies, the challenge lies in evaluating the significance of each approach and refining the results to isolate definitive anomalies. This paper examines multiple anomaly tagging techniques and introduces novel weightage assignment methods to prioritize the most effective approaches, filtering out less reliable ones. Specifically, we explore two methods: simple Frequentist approach and Ensemble Bayesian-aided approach, with an emphasis on why the latter is particularly well-suited for anomaly detection. The proposed methodology is validated both theoretically and empirically on time-series datasets. Our findings demonstrate that the Ensemble Bayesian-aided approach significantly improves detection accuracy by accounting for future uncertainty and addressing edge case fallacies inherent in individual tagging methods. This research provides a robust framework for anomaly detection, offering a powerful solution that enhances precision and reliability across diverse applications.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"15 ","pages":"Article 100566"},"PeriodicalIF":0.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716251","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}