Data Science and Management最新文献

{"title":"Exploration of salience theory to deep learning: evidence from Chinese new energy market high-frequency trading","authors":"Qing Zhu ,&nbsp;Jinhong Du ,&nbsp;Yuze Li","doi":"10.1016/j.dsm.2024.12.001","DOIUrl":"10.1016/j.dsm.2024.12.001","url":null,"abstract":"<div><div>Salience theory has been proposed as a new stock trading strategy. To assess the validity of this proposal, a complex decision trading system was constructed based on salience theory, a variational mode decomposition (VMD) model, a bidirectional gated recurrent unit (BiGRU) model, and high-frequency trading. The system selected 30 Chinese new energy concept stocks, ranked the stocks using salience theory, and selected the top and bottom three stocks for two portfolios. Twelve stages were established, following which the VMD and BiGRU models were applied to the predictions. The final predicted annualized returns for the high <em>ST</em> (salience theory value) group A (GA) and low <em>ST</em> group B (GB) were 194.06% and 165.88%, respectively. This finding validates the powerful utility of salience theory and deep learning to analyze the Chinese new energy market. Moreover, it explains the theoretical practicality issues that the short selling restriction is the essential reason, or even perhaps the only reason, that leads to the strength of salience theory.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 3","pages":"Pages 296-309"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886670","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":"Probabilistic oil price forecasting with a variational mode decomposition-gated recurrent unit model incorporating pinball loss","authors":"Zhesen Cui ,&nbsp;Tian Li ,&nbsp;Zhe Ding ,&nbsp;Xi'an Li ,&nbsp;Jinran Wu","doi":"10.1016/j.dsm.2024.10.003","DOIUrl":"10.1016/j.dsm.2024.10.003","url":null,"abstract":"<div><div>Prediction methods have garnered significant attention in intelligent decision-making. Most existing approaches to predicting crude oil prices prioritize accuracy and stability while providing precise prediction intervals that can offer valuable insights. Thus far, we introduced a novel hybrid model to forecast future crude oil prices. Our approach leverages the variational mode decomposition (VMD) to simplify the complexity of the original time series, yielding a set of subseries. These subseries are then modeled using a deep neural network architecture called a gated recurrent unit (GRU). To address the prediction uncertainty, we employed the pinball loss function rather than the mean square error to guide the proposed VMD-GRU. This adaptation extends the traditional GRU-based point forecasting to probabilistic forecasting by estimating quantiles. We evaluated our proposed model on a well-established crude oil price series by conducting both single- and multi-step-ahead forecasting analyses. Our findings underscore the efficacy of the combined model, demonstrating its superior predictive performance compared to benchmark models.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 3","pages":"Pages 237-247"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144749080","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":"Electroencephalogram-based emotion recognition: a comparative analysis of supervised machine learning algorithms","authors":"Anagha Prakash ,&nbsp;Alwin Poulose","doi":"10.1016/j.dsm.2024.12.004","DOIUrl":"10.1016/j.dsm.2024.12.004","url":null,"abstract":"<div><div>Emotion recognition from electroencephalogram (EEG) signals has garnered significant attention owing to its potential applications in affective computing, human-computer interaction, and mental health monitoring. This paper presents a comparative analysis of different machine learning methods for emotion recognition using EEG data. The objective of this study was to identify the most effective algorithm for accurately classifying emotional states using EEG signals. The EEG brainwave dataset: Feeling emotions dataset was used to evaluate the performance of various machine-learning techniques. Multiple machine learning techniques, namely logistic regression (LR), support vector machine (SVM), Gaussian Naive Bayes (GNB), and decision tree (DT), and ensemble models, namely random forest (RF), AdaBoost, LightGBM, XGBoost, and CatBoost, were trained and evaluated. Five-fold cross-validation and dimension reduction techniques, such as principal component analysis, <em>t</em>-distributed stochastic neighbor embedding, and linear discriminant analysis, were performed for all models. The least-performing model, GNB, showed substantially increased performance after dimension reduction. Performance metrics such as accuracy, precision, recall, F1-score, and receiver operating characteristic curves are employed to assess the effectiveness of each approach. This study focuses on the implications of using various machine learning algorithms for EEG-based emotion recognition. This pursuit can improve our understanding of emotions and their underlying neural mechanisms.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 3","pages":"Pages 342-360"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931739","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":"Toward accurate credit evaluation: an efficient imputation approach for financial data","authors":"Jie Lu ,&nbsp;Shengda Zhuo ,&nbsp;Jinjie Qiu ,&nbsp;Yin Tang","doi":"10.1016/j.dsm.2025.06.001","DOIUrl":"10.1016/j.dsm.2025.06.001","url":null,"abstract":"<div><div>Missing instances and mixed data types, including discrete and ordered (e.g., continuous and ordinal) variables, are widespread in many datasets in the finance sector. In this domain, estimating missing instances is crucial because many data analysis pipelines require complete data, which is particularly challenging for mixed-type data. However, existing methods treat discrete and ordinal data as continuous values, which may reduce efficacy in addressing these challenges. To fill this gap, this study proposes a probabilistic imputation method for mixed-type and incomplete loan data (PMILD), using a mixed Gaussian Copula model that supports single and multiple imputations. The method models mixed discrete and ordinal data using latent Gaussian distributions, where observed features with arbitrary margins are mapped to the latent normal space, and feature correlations are approximated through the expectation-maximization process in the latent space. Empirical results on nine real-world datasets demonstrate that PMILD substantially outperforms state-of-the-art imputation methods, providing a highly effective solution for handling mixed-type and incomplete loan data. This advancement enhances both operational efficiency and credit evaluation accuracy in finance-related applications.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 3","pages":"Pages 374-387"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988502","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":"Understanding users’ effective use of generative conversational AI from a media naturalness perspective: a hybrid structural equation modeling-artificial neural network (SEM-ANN) approach","authors":"Kun Wang,&nbsp;Yaobin Lu,&nbsp;Zhao Pan","doi":"10.1016/j.dsm.2024.09.001","DOIUrl":"10.1016/j.dsm.2024.09.001","url":null,"abstract":"<div><div>Although generative conversational artificial intelligence (AI) can answer questions well and hold conversations as a person, the semantic ambiguity inherent in text-based communication poses challenges to effective use. Effective use reflects the users’ utilization of generative conversational AI to achieve their goals, which has not been previously studied. Drawing on the media naturalness theory, we examined how generative conversational AI’s content and style naturalness affect effective use. A two-wave survey was conducted to collect data from 565 users of generative conversational AI. Two techniques were used in this study. Initially, partial least squares structural equation modeling (PLS-SEM) was applied to determine the variables that significantly affected the mechanisms (i.e., cognitive effort and communication ambiguity) and effective use. Secondly, an artificial neural network model was used to evaluate the relative importance of the significant predictors of mechanisms and effective use identified from the PLS-SEM analysis. The results revealed that the naturalness of content and style differed in their effects on cognitive effort and communication ambiguity. Additionally, cognitive effort and communication ambiguity negatively affected effective use. This study advances the literature on effective use by uncovering the psychological mechanisms underlying effective use and their antecedents. In addition, this study offers insights into the design of generative conversational AI.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 147-159"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144146834","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":"Categorical classification of skin cancer using a weighted ensemble of transfer learning with test time augmentation","authors":"Aliyu Tetengi Ibrahim ,&nbsp;Mohammed Abdullahi ,&nbsp;Armand Florentin Donfack Kana ,&nbsp;Mohammed Tukur Mohammed ,&nbsp;Ibrahim Hayatu Hassan","doi":"10.1016/j.dsm.2024.10.002","DOIUrl":"10.1016/j.dsm.2024.10.002","url":null,"abstract":"<div><div>Skin cancer is the abnormal development of cells on the surface of the skin and is one of the most fatal diseases in humans. It usually appears in locations that are exposed to the sun, but can also appear in areas that are not regularly exposed to the sun. Due to the striking similarities between benign and malignant lesions, skin cancer detection remains a problem, even for expert dermatologists. Considering the inability of dermatologists to diagnose skin cancer accurately, a convolutional neural network (CNN) approach was used for skin cancer diagnosis. However, the CNN model requires a significant number of image datasets for better performance; thus, image augmentation and transfer learning techniques have been used in this study to boost the number of images and the performance of the model, because there are a limited number of medical images. This study proposes an ensemble transfer-learning-based model that can efficiently classify skin lesions into one of seven categories to aid dermatologists in skin cancer detection: (i) actinic keratoses, (ii) basal cell carcinoma, (iii) benign keratosis, (iv) dermatofibroma, (v) melanocytic nevi, (vi) melanoma, and (vii) vascular skin lesions. Five transfer learning models were used as the basis of the ensemble: MobileNet, EfficientNetV2B2, Xception, ResNext101, and DenseNet201. In addition to the stratified 10-fold cross-validation, the results of each individual model were fused to achieve greater classification accuracy. An annealing learning rate scheduler and test time augmentation (TTA) were also used to increase the performance of the model during the training and testing stages. A total of 10,015 publicly available dermoscopy images from the HAM10000 (Human Against Machine) dataset, which contained samples from the seven common skin lesion categories, were used to train and evaluate the models. The proposed technique attained 94.49% accuracy on the dataset. These results suggest that this strategy can be useful for improving the accuracy of skin cancer classification. However, the weighted average of F1-score, recall, and precision were obtained to be 94.68%, 94.49%, and 95.07%, respectively.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 174-184"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222281","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":"Residual-enhanced graph convolutional networks with hypersphere mapping for anomaly detection in attributed networks","authors":"Wasim Khan ,&nbsp;Afsaruddin Mohd ,&nbsp;Mohammad Suaib ,&nbsp;Mohammad Ishrat ,&nbsp;Anwar Ahamed Shaikh ,&nbsp;Syed Mohd Faisal","doi":"10.1016/j.dsm.2024.09.002","DOIUrl":"10.1016/j.dsm.2024.09.002","url":null,"abstract":"<div><div>In the burgeoning field of anomaly detection within attributed networks, traditional methodologies often encounter the intricacies of network complexity, particularly in capturing nonlinearity and sparsity. This study introduces an innovative approach that synergizes the strengths of graph convolutional networks with advanced deep residual learning and a unique residual-based attention mechanism, thereby creating a more nuanced and efficient method for anomaly detection in complex networks. The heart of our model lies in the integration of graph convolutional networks that capture complex structural relationships within the network data. This is further bolstered by deep residual learning, which is employed to model intricate nonlinear connections directly from input data. A pivotal innovation in our approach is the incorporation of a residual-based attention mechanism. This mechanism dynamically adjusts the importance of nodes based on their residual information, thereby significantly enhancing the sensitivity of the model to subtle anomalies. Furthermore, we introduce a novel hypersphere mapping technique in the latent space to distinctly separate normal and anomalous data. This mapping is the key to our model’s ability to pinpoint anomalies with greater precision. An extensive experimental setup was used to validate the efficacy of the proposed model. Using attributed social network datasets, we demonstrate that our model not only competes with but also surpasses existing state-of-the-art methods in anomaly detection. The results show the exceptional capability of our model to handle the multifaceted nature of real-world networks.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 137-146"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144146833","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 explainable feature selection framework for web phishing detection with machine learning","authors":"Sakib Shahriar Shafin","doi":"10.1016/j.dsm.2024.08.004","DOIUrl":"10.1016/j.dsm.2024.08.004","url":null,"abstract":"<div><div>In the evolving landscape of cyber threats, phishing attacks pose significant challenges, particularly through deceptive webpages designed to extract sensitive information under the guise of legitimacy. Conventional and machine learning (ML)-based detection systems struggle to detect phishing websites owing to their constantly changing tactics. Furthermore, newer phishing websites exhibit subtle and expertly concealed indicators that are not readily detectable. Hence, effective detection depends on identifying the most critical features. Traditional feature selection (FS) methods often struggle to enhance ML model performance and instead decrease it. To combat these issues, we propose an innovative method using explainable AI (XAI) to enhance FS in ML models and improve the identification of phishing websites. Specifically, we employ SHapley Additive exPlanations (SHAP) for global perspective and aggregated local interpretable model-agnostic explanations (LIME) to determine specific localized patterns. The proposed SHAP and LIME-aggregated FS (SLA-FS) framework pinpoints the most informative features, enabling more precise, swift, and adaptable phishing detection. Applying this approach to an up-to-date web phishing dataset, we evaluate the performance of three ML models before and after FS to assess their effectiveness. Our findings reveal that random forest (RF), with an accuracy of 97.41% and XGBoost (XGB) at 97.21% significantly benefit from the SLA-FS framework, while k-nearest neighbors lags. Our framework increases the accuracy of RF and XGB by 0.65% and 0.41%, respectively, outperforming traditional filter or wrapper methods and any prior methods evaluated on this dataset, showcasing its potential.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 127-136"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139015","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":"Challenges and prospects of artificial intelligence in aviation: a ​bibliometric study","authors":"Nuno Moura Lopes,&nbsp;Manuela Aparicio,&nbsp;Fátima Trindade Neves","doi":"10.1016/j.dsm.2024.11.001","DOIUrl":"10.1016/j.dsm.2024.11.001","url":null,"abstract":"<div><div>The primary motivation for this study is the recent growth and increased interest in artificial intelligence (AI). Despite the widespread recognition of its critical importance, a discernible scientific gap persists within the extant scholarly discourse, particularly concerning exhaustive systematic reviews of AI in the aviation industry. This gap spurred a meticulous analysis of 1,213 articles from the Web of Science (WoS) core database for bibliometric knowledge mapping. This analysis highlights China as the primary contributor to publications, with the Nanjing University of Finance and Economics as the leading institution in paper contributions. <em>Lecture Notes in Artificial Intelligence</em> and the <em>IEEE AIAA Digital Avionics System Conference</em> are the leading journals within this domain. This bibliometric research underscores the key focus on air traffic management, human factors, environmental initiatives, training, logistics, flight operations, and safety through co-occurrence and co-citation analyses. A chronological examination of keywords reveals a central research trajectory centered on machine learning, models, deep learning, and the impact of automation on human performance in aviation. Burst keyword analysis identifies the leading-edge research on AI within predictive models, unmanned aerial vehicles, object detection, and convolutional neural networks. The primary objective is to bridge this knowledge gap and gain comprehensive insights into AI in the aviation sector. This study delineates the scholarly terrain of AI in aviation using a bibliometric methodology to facilitate this exploration. The results illuminate the current state of research, thereby enhancing academic understanding of developments within this critical domain. Finally, a new conceptual framework was constructed based on the primary elements identified in the literature. This framework can assist emerging researchers in identifying the fundamental dimensions of AI in the aviation industry.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 207-223"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263658","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 method for a technology enhanced learning recommender system considering changing user interest based on neural collaborative filtering","authors":"Mohammad Mehran Lesan Sedgh ,&nbsp;Alimohammad Latif ,&nbsp;Sima Emadi","doi":"10.1016/j.dsm.2024.09.004","DOIUrl":"10.1016/j.dsm.2024.09.004","url":null,"abstract":"<div><div>This study introduces an advanced recommender system for technology enhanced learning (TEL) that synergizes neural collaborative filtering, sentiment analysis, and an adaptive learning rate to address the limitations of traditional TEL systems. Recognizing the critical gap in existing approaches—primarily their neglect of user emotional feedback and static learning paths—our model innovatively incorporates sentiment analysis to capture and respond to nuanced emotional feedback from users. Utilizing bidirectional encoder representations from Transformers for sentiment analysis, our system not only understands but also respects user privacy by processing feedback without revealing sensitive information. The adaptive learning rate, inspired by AdaGrad, allows our model to adjust its learning trajectory based on the sentiment scores associated with user feedback, ensuring a dynamic response to both positive and negative sentiments. This dual approach enhances the system’s adaptability to changing user preferences and improves its contentment understanding. Our methodology involves a comprehensive analysis of both the content of learning materials and the behaviors and preferences of learners, facilitating a more personalized learning experience. By dynamically adjusting recommendations based on real-time user data and behavioral analysis, our system leverages the collective insights of similar users and relevant content. We validated our approach against three datasets—MovieLens, Amazon, and a proprietary TEL dataset—and saw significant improvements in recommendation precision, F-score, and mean absolute error. The results indicate the potential of integrating sentiment analysis and adaptive learning rates into TEL recommender systems, marking a step forward in developing more responsive and user-centric educational technologies. This study paves the way for future advancements in TEL systems, emphasizing the importance of emotional intelligence and adaptability in enhancing the learning experience.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"8 2","pages":"Pages 196-206"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255255","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}