Journal of Economy and Technology最新文献

User segmentation under blockchain-based privacy protection 基于区块链的隐私保护下的用户细分

Journal of Economy and Technology

Pub Date : 2026-01-01 DOI: 10.1016/j.ject.2025.09.002

Jiayao Wang , Hao Dong , Junwu Zhu , Yizhang Wang , Qilin Wu , Dongfang Zhao

User segmentation is a marketing strategy that allows companies to more accurately position their products and services, thereby enhancing marketing efficiency and customer satisfaction. However, existing user segmentation approaches continue to face significant challenges related to personal information leakage and data security. To address these issues, this study proposes a data storage architecture that integrates localized differential privacy mechanisms with blockchain technology to ensure user data security and reduce the risk of privacy breaches. Building on this foundation, a clustering algorithm based on a density distance metric, referred to as the KDE-KMeans algorithm, is designed and implemented. In this algorithm, a density distance score is introduced as the core metric for measuring the similarity between samples and cluster centers. This scoring mechanism comprehensively considers the traditional distance as the primary factor in similarity evaluation, while also incorporating the density difference between samples as a secondary factor. Together, these elements form a more detailed and robust similarity evaluation framework.Experimental results demonstrate that the KDE-KMeans algorithm significantly outperforms baseline algorithms in clustering accuracy. Its advantages are especially pronounced when processing datasets with substantial density variations between clusters, highlighting the algorithm’s effectiveness and adaptability in complex data environments.

用户细分是一种营销策略，可以让企业更准确地定位自己的产品和服务，从而提高营销效率和客户满意度。然而，现有的用户细分方法仍然面临着与个人信息泄露和数据安全相关的重大挑战。针对这些问题，本研究提出了一种将本地化差分隐私机制与区块链技术相结合的数据存储架构，以确保用户数据安全，降低隐私泄露风险。在此基础上，设计并实现了基于密度距离度量的聚类算法（称为KDE-KMeans算法）。该算法引入密度距离分数作为衡量样本与聚类中心相似度的核心指标。该评分机制综合考虑了传统距离作为相似性评价的主要因素，同时也将样本间密度差作为次要因素。总之，这些元素形成了一个更详细和健壮的相似性评估框架。实验结果表明，KDE-KMeans算法在聚类精度上明显优于基线算法。在处理集群间密度变化较大的数据集时，其优势尤为明显，突出了该算法在复杂数据环境中的有效性和适应性。

{"title":"User segmentation under blockchain-based privacy protection","authors":"Jiayao Wang , Hao Dong , Junwu Zhu , Yizhang Wang , Qilin Wu , Dongfang Zhao","doi":"10.1016/j.ject.2025.09.002","DOIUrl":"10.1016/j.ject.2025.09.002","url":null,"abstract":"<div><div>User segmentation is a marketing strategy that allows companies to more accurately position their products and services, thereby enhancing marketing efficiency and customer satisfaction. However, existing user segmentation approaches continue to face significant challenges related to personal information leakage and data security. To address these issues, this study proposes a data storage architecture that integrates localized differential privacy mechanisms with blockchain technology to ensure user data security and reduce the risk of privacy breaches. Building on this foundation, a clustering algorithm based on a density distance metric, referred to as the KDE-KMeans algorithm, is designed and implemented. In this algorithm, a density distance score is introduced as the core metric for measuring the similarity between samples and cluster centers. This scoring mechanism comprehensively considers the traditional distance as the primary factor in similarity evaluation, while also incorporating the density difference between samples as a secondary factor. Together, these elements form a more detailed and robust similarity evaluation framework.Experimental results demonstrate that the KDE-KMeans algorithm significantly outperforms baseline algorithms in clustering accuracy. Its advantages are especially pronounced when processing datasets with substantial density variations between clusters, highlighting the algorithm’s effectiveness and adaptability in complex data environments.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 307-322"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037155","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}

引用次数: 0

Impact of entrepreneurial leadership on employees’ innovative behavior: A mediation analysis of organizational motivation to innovate and employees’ creativity 企业家领导对员工创新行为的影响：组织创新动机与员工创造力的中介分析

Journal of Economy and Technology

Pub Date : 2026-01-01 DOI: 10.1016/j.ject.2025.09.001

Yohannes Mekonnen Yesuf , Ziska Fields

Academic literature widely recognizes the importance of entrepreneurial leadership (EL) within agricultural research institutes. However, empirical investigations into how leadership styles influence employees’ innovative work behavior in this sector remain scarce. In particular, scholars have paid limited attention to how leaders in agricultural research institutes shape and enhance employees’ innovation-related behaviors. This study fills that gap by examining how EL influences employees’ innovative behavior (EIB), emphasizing organizational motivation to innovate (OMI) and creativity as the key mechanisms that leaders use to promote innovation among employees in Ethiopian agricultural research institutions. Using a proportionate systematic random sampling method, we drew the sample from the Amhara Agricultural Research Institute (ARARI). The study employed validated questionnaires to examine the hypothesized relationships among EL, EIB, OMI, and employees’ creativity (EC). The findings reveal that OMI serves as a mediator between EL and EIB. Moreover, EC mediates the relationship between OMI and EIB. The study discusses the insights derived from the findings and offers recommendations for fostering creative behavior among staff in agricultural research institutes. Doing so contributes to the literature on entrepreneurial leadership and innovative behavior, particularly relevant to agricultural research institutes in Ethiopia’s developing economy. It also extends previous empirical research by examining how EL influences EIB in agricultural research settings, with OMI and individual creativity as key mediators.

学术文献广泛认识到创业型领导（EL）在农业研究机构中的重要性。然而，关于领导风格如何影响该领域员工创新工作行为的实证调查仍然很少。特别是，学者们对农业科研机构领导者如何塑造和增强员工创新相关行为的关注有限。本研究通过考察EL如何影响员工的创新行为（EIB）填补了这一空白，强调组织创新动机（OMI）和创造力是领导者用来促进埃塞俄比亚农业研究机构员工创新的关键机制。采用比例系统随机抽样方法，从阿姆哈拉农业研究所（ARARI）抽取样本。本研究采用有效的问卷调查，检验了假设的情商、EIB、OMI和员工创造力之间的关系。研究结果表明，OMI在EL和EIB之间起中介作用。此外，EC在OMI和EIB之间起到中介作用。该研究讨论了从研究结果中得出的见解，并为培养农业研究机构工作人员的创造性行为提供了建议。这样做有助于企业领导和创新行为的文献，特别是与埃塞俄比亚发展中经济体的农业研究机构相关。它还扩展了以前的实证研究，考察了在农业研究背景下，个人学习能力如何影响EIB， OMI和个人创造力是关键的中介因素。

{"title":"Impact of entrepreneurial leadership on employees’ innovative behavior: A mediation analysis of organizational motivation to innovate and employees’ creativity","authors":"Yohannes Mekonnen Yesuf , Ziska Fields","doi":"10.1016/j.ject.2025.09.001","DOIUrl":"10.1016/j.ject.2025.09.001","url":null,"abstract":"<div><div>Academic literature widely recognizes the importance of entrepreneurial leadership (EL) within agricultural research institutes. However, empirical investigations into how leadership styles influence employees’ innovative work behavior in this sector remain scarce. In particular, scholars have paid limited attention to how leaders in agricultural research institutes shape and enhance employees’ innovation-related behaviors. This study fills that gap by examining how EL influences employees’ innovative behavior (EIB), emphasizing organizational motivation to innovate (OMI) and creativity as the key mechanisms that leaders use to promote innovation among employees in Ethiopian agricultural research institutions. Using a proportionate systematic random sampling method, we drew the sample from the Amhara Agricultural Research Institute (ARARI). The study employed validated questionnaires to examine the hypothesized relationships among EL, EIB, OMI, and employees’ creativity (EC). The findings reveal that OMI serves as a mediator between EL and EIB. Moreover, EC mediates the relationship between OMI and EIB. The study discusses the insights derived from the findings and offers recommendations for fostering creative behavior among staff in agricultural research institutes. Doing so contributes to the literature on entrepreneurial leadership and innovative behavior, particularly relevant to agricultural research institutes in Ethiopia’s developing economy. It also extends previous empirical research by examining how EL influences EIB in agricultural research settings, with OMI and individual creativity as key mediators.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 296-306"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145975952","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}

引用次数: 0

The determinants of the Initial Coin Offering (ICO). A cross-country study 首次代币发行（ICO）的决定因素。一项跨国研究

Journal of Economy and Technology

Pub Date : 2026-01-01 DOI: 10.1016/j.ject.2025.07.004

Ana Claudia de A. Moxotó , Elias Soukiazis , Paulo Melo

This study provides a cross-country analysis of the determinants of Initial Coin Offering (ICO) emergence. Our empirical findings indicate a positive correlation between ICO activity and a country's environmental orientation, as well as the quality of its educational and research institutions. Conversely, the emergence of ICOs is negatively impacted by political instability, high country risk, significant bank concentration, high bank default rates, and restricted financial freedom. These results suggest ICOs are more prevalent in environmentally conscious nations, likely driven by demand for sustainable technology. They also function as alternative assets in politically unstable regions where trust in traditional monetary policy is diminished. The study provides valuable insights for entrepreneurs, investors, and policymakers by identifying the key institutional and economic factors that shape the ICO landscape. Future research is encouraged to explore country-specific characteristics and the evolving regulatory framework governing this financing mechanism.

本研究对首次代币发行（ICO）出现的决定因素进行了跨国分析。我们的实证研究结果表明，ICO活动与一个国家的环境取向以及教育和研究机构的质量之间存在正相关关系。相反，ico的出现受到政治不稳定、国家风险高、银行集中度高、银行违约率高和金融自由受限的负面影响。这些结果表明，ico在有环保意识的国家更为普遍，这可能是由对可持续技术的需求推动的。在对传统货币政策失去信任的政治不稳定地区，它们还可以作为另类资产发挥作用。该研究通过确定影响ICO格局的关键制度和经济因素，为企业家、投资者和政策制定者提供了有价值的见解。鼓励今后的研究探讨具体国家的特点和管理这一筹资机制的不断演变的管理框架。

引用次数: 0

Evaluating machine learning performance using python for neural network models in urban transportation in New York city case study 纽约城市交通中使用python神经网络模型评估机器学习性能的案例研究

Journal of Economy and Technology

Pub Date : 2025-11-25 DOI: 10.1016/j.ject.2025.11.001

Mohsen Mohammadagha, Saeed Asadi, Hajar Kazemi Naeini

This study investigates neural network performance optimization for New York City taxi trip duration prediction to address critical gaps in transportation machine learning, where reproducibility, comprehensive diagnostics, and computational efficiency remain underreported. The research addresses limitations in prior literature that emphasize accuracy without standardized preprocessing, leakage prevention, or systematic cost-performance analysis. The objective was to develop a unified, reproducible framework combining an auditable, from-scratch NumPy neural network with production-grade Keras MLPs, systematically benchmarked against classical models under identical preprocessing and data splits. Methodology encompasses four independent phases: theoretical validation using XOR classification, statistical benchmarking through rigorous cross-validation on 1.3 million NYC taxi records, systematic architecture optimization across small/medium/large configurations, and advanced optimization achieving state-of-the-art performance. Key results demonstrate perfect XOR convergence validation (loss reduction from 0.7065 to 0.0198), competitive baseline performance against Random Forest (93.3 %±0.013 vs 90.5 %±0.044 accuracy), optimal medium architecture achieving 0.459 RMSLE, and final proposed model reaching 0.3092 RMSLE—representing 31.8 % improvement over Random Forest (0.4536) and 27.4 % over enhanced Keras baselines (0.4261). The framework incorporates comprehensive residual diagnostics, feature importance analysis, and computational profiling with statistical significance testing. Results establish new benchmarks for NYC taxi duration prediction while providing a methodologically replicable framework for future urban mobility analytics and operational ETA systems.

本研究探讨了纽约市出租车行程持续时间预测的神经网络性能优化，以解决交通机器学习中再现性、综合诊断和计算效率仍然被低估的关键差距。该研究解决了先前文献中强调准确性而没有标准化预处理、泄漏预防或系统成本性能分析的局限性。目标是开发一个统一的、可重复的框架，将一个可审计的、从头开始的NumPy神经网络与生产级Keras mlp结合起来，在相同的预处理和数据分割下，系统地对经典模型进行基准测试。方法包括四个独立的阶段：使用异或分类的理论验证，通过对130万纽约市出租车记录进行严格交叉验证的统计基准，跨小/中/大配置的系统架构优化，以及实现最先进性能的高级优化。关键结果显示完美的XOR收敛验证（损失从0.7065降低到0.0198），与随机森林相比具有竞争力的基线性能（93.3 %±0.013 vs 90.5 %±0.044准确率），最优的中间架构达到0.459 RMSLE，最终提出的模型达到0.3092 RMSLE -比随机森林（0.4536）提高31.8% %，比增强的Keras基线（0.4261）提高27.4 %。该框架结合了综合残差诊断、特征重要性分析和统计显著性测试的计算分析。结果为纽约市出租车持续时间预测建立了新的基准，同时为未来的城市交通分析和运营ETA系统提供了方法上可复制的框架。

{"title":"Evaluating machine learning performance using python for neural network models in urban transportation in New York city case study","authors":"Mohsen Mohammadagha, Saeed Asadi, Hajar Kazemi Naeini","doi":"10.1016/j.ject.2025.11.001","DOIUrl":"10.1016/j.ject.2025.11.001","url":null,"abstract":"<div><div>This study investigates neural network performance optimization for New York City taxi trip duration prediction to address critical gaps in transportation machine learning, where reproducibility, comprehensive diagnostics, and computational efficiency remain underreported. The research addresses limitations in prior literature that emphasize accuracy without standardized preprocessing, leakage prevention, or systematic cost-performance analysis. The objective was to develop a unified, reproducible framework combining an auditable, from-scratch NumPy neural network with production-grade Keras MLPs, systematically benchmarked against classical models under identical preprocessing and data splits. Methodology encompasses four independent phases: theoretical validation using XOR classification, statistical benchmarking through rigorous cross-validation on 1.3 million NYC taxi records, systematic architecture optimization across small/medium/large configurations, and advanced optimization achieving state-of-the-art performance. Key results demonstrate perfect XOR convergence validation (loss reduction from 0.7065 to 0.0198), competitive baseline performance against Random Forest (93.3 %±0.013 vs 90.5 %±0.044 accuracy), optimal medium architecture achieving 0.459 RMSLE, and final proposed model reaching 0.3092 RMSLE—representing 31.8 % improvement over Random Forest (0.4536) and 27.4 % over enhanced Keras baselines (0.4261). The framework incorporates comprehensive residual diagnostics, feature importance analysis, and computational profiling with statistical significance testing. Results establish new benchmarks for NYC taxi duration prediction while providing a methodologically replicable framework for future urban mobility analytics and operational ETA systems.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 266-283"},"PeriodicalIF":0.0,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145683671","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}

引用次数: 0

Corrigendum to “Asynchronous distributed charging protocol for plug-in electric vehicles” [J. Econ. Technol., (2026) 29–47] 插电式电动汽车异步分布式充电协议的修正[J]。经济学。抛光工艺。，（2026） 29-47]

Journal of Economy and Technology

Pub Date : 2025-10-25 DOI: 10.1016/j.ject.2025.09.003

Yunfan Zhang , Yifan Su , Yue Chen , Feng Liu

引用次数: 0

Corrigendum to “Next generation of electronic medical record search engines to support chart reviews: A systematic user study and future research direction” [Journal of Economy and Technology (2024) 22–30] “支持图表审查的下一代电子病历搜索引擎：系统的用户研究和未来研究方向”的勘误表[经济与技术杂志（2024）22-30]

Journal of Economy and Technology

Pub Date : 2025-10-25 DOI: 10.1016/j.ject.2025.09.004

Cheng Ye, Daniel Fabbri

引用次数: 0

Encrypted intelligence: A comparative analysis of homomorphic encryption frameworks for privacy-preserving AI 加密智能：保护隐私的人工智能同态加密框架的比较分析

Journal of Economy and Technology

Pub Date : 2025-08-29 DOI: 10.1016/j.ject.2025.08.001

Aadit Shah, Surindernath Sivakumar, Prabakaran N

This paper presents a comparative study of various homomorphic encryption models to evaluate their qualitative and quantitative benefits and drawbacks in performing computations on encrypted data. Within the framework of ethical AI, the study focuses on enhancing privacy, secrecy, and security, addressing limitations in existing privacy-preserving solutions such as differential privacy and secure multi-party computation. To provide context, related encryption paradigms such as symmetric, asymmetric, hybrid, and multi-party computation are also discussed. The review synthesizes findings from recent literature, comparing schemes based on key performance metrics including encryption and decryption speed, memory consumption and quantum resistance. Published benchmark results and case studies are used to highlight trade-offs between privacy guarantees and computational feasibility. The study highlights the practicality of homomorphic encryption for real-world applications, providing information on its potential to advance privacy-preserving AI while maintaining computational feasibility. The paper also surveys practical applications of homomorphic encryption in machine learning, secure data analytics, and federated learning, along with emerging challenges such as quantum-safe cryptography and hardware acceleration. This review serves as a consolidated reference for researchers and practitioners seeking to select appropriate encryption techniques for AI applications, providing both a broad overview of the field and a focused discussion on homomorphic encryption’s capabilities and limitations.

本文对各种同态加密模型进行了比较研究，以评估它们在对加密数据进行计算时定性和定量的优点和缺点。在伦理人工智能的框架内，该研究侧重于增强隐私、保密和安全，解决现有隐私保护解决方案（如差分隐私和安全多方计算）的局限性。为了提供上下文，还讨论了相关的加密范式，如对称、非对称、混合和多方计算。这篇综述综合了最近文献的发现，比较了基于关键性能指标的方案，包括加密和解密速度、内存消耗和量子阻力。发布的基准测试结果和案例研究用于强调隐私保证和计算可行性之间的权衡。该研究强调了同态加密在现实世界应用中的实用性，提供了有关其在保持计算可行性的同时推进隐私保护AI的潜力的信息。本文还研究了同态加密在机器学习、安全数据分析和联邦学习中的实际应用，以及量子安全密码学和硬件加速等新兴挑战。本综述为研究人员和从业者寻求为人工智能应用选择适当的加密技术提供了综合参考，提供了该领域的广泛概述，并重点讨论了同态加密的能力和局限性。

{"title":"Encrypted intelligence: A comparative analysis of homomorphic encryption frameworks for privacy-preserving AI","authors":"Aadit Shah, Surindernath Sivakumar, Prabakaran N","doi":"10.1016/j.ject.2025.08.001","DOIUrl":"10.1016/j.ject.2025.08.001","url":null,"abstract":"<div><div>This paper presents a comparative study of various homomorphic encryption models to evaluate their qualitative and quantitative benefits and drawbacks in performing computations on encrypted data. Within the framework of ethical AI, the study focuses on enhancing privacy, secrecy, and security, addressing limitations in existing privacy-preserving solutions such as differential privacy and secure multi-party computation. To provide context, related encryption paradigms such as symmetric, asymmetric, hybrid, and multi-party computation are also discussed. The review synthesizes findings from recent literature, comparing schemes based on key performance metrics including encryption and decryption speed, memory consumption and quantum resistance. Published benchmark results and case studies are used to highlight trade-offs between privacy guarantees and computational feasibility. The study highlights the practicality of homomorphic encryption for real-world applications, providing information on its potential to advance privacy-preserving AI while maintaining computational feasibility. The paper also surveys practical applications of homomorphic encryption in machine learning, secure data analytics, and federated learning, along with emerging challenges such as quantum-safe cryptography and hardware acceleration. This review serves as a consolidated reference for researchers and practitioners seeking to select appropriate encryption techniques for AI applications, providing both a broad overview of the field and a focused discussion on homomorphic encryption’s capabilities and limitations.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 252-265"},"PeriodicalIF":0.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623301","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}

引用次数: 0

Synergizing transformer-based models and financial sentiment analysis: A framework for generative AI in economic decision-making 基于转换器的模型和金融情绪分析的协同作用：经济决策中生成人工智能的框架

Journal of Economy and Technology

Pub Date : 2025-07-23 DOI: 10.1016/j.ject.2025.07.003

Nouri Hicham , Nassera Habbat

This study introduces a new way to analyze financial sentiment by combining advanced transformer-based models with generative artificial intelligence (AI) to better understand the language and context of financial discussions. The objective is to enhance the predictive accuracy of market behavior through improved understanding of investor sentiment. The proposed sentiment analysis framework leverages six domain-specific datasets: Social Sentiment Indices (X-Scores), Fin-SoMe, SemEval-2017 Task 5, Fin-Lin, Sanders, and Taborda. These datasets, primarily sourced from social media, reflect diverse investor perspectives. Generative AI models, like GPT-3.5 and GPT-4, are used to create more data, and the meaning of words is enhanced using techniques like BERT and Word2Vec. The model is trained with a cross-entropy loss function and fine-tuned using Few-shot Learning, Chain-of-Thought reasoning, and ReAct strategies, ensuring computational efficiency. Experimental results show consistent improvements across all datasets in accuracy, precision, recall, specificity, and F1 score. The use of generative AI and transformer architectures makes the model stronger and better at understanding how investors feel in real financial situations. This research contributes to the field of explicable AI in finance by demonstrating the impact of domain-adapted models and generative techniques in advancing sentiment analysis. The findings offer practical value for investors and analysts seeking data-driven insights into market dynamics and decision-making processes.

本研究引入了一种分析金融情绪的新方法，将先进的基于变压器的模型与生成式人工智能（AI）相结合，以更好地理解金融讨论的语言和背景。目标是通过提高对投资者情绪的理解来提高市场行为的预测准确性。提出的情绪分析框架利用了六个特定领域的数据集：社会情绪指数（X-Scores）、Fin-SoMe、SemEval-2017 Task 5、Fin-Lin、Sanders和Taborda。这些数据集主要来自社交媒体，反映了投资者的不同观点。生成式人工智能模型，如GPT-3.5和GPT-4，用于创建更多的数据，并使用BERT和Word2Vec等技术增强单词的含义。该模型使用交叉熵损失函数进行训练，并使用Few-shot Learning、Chain-of-Thought推理和ReAct策略进行微调，以确保计算效率。实验结果显示，所有数据集在准确性、精密度、召回率、特异性和F1评分方面都有一致的改进。生成式人工智能和变压器架构的使用使模型更强大，更能理解投资者在真实金融状况下的感受。本研究通过展示领域适应模型和生成技术在推进情绪分析方面的影响，为金融领域的可解释人工智能领域做出了贡献。研究结果为寻求数据驱动的市场动态和决策过程洞察的投资者和分析师提供了实用价值。

{"title":"Synergizing transformer-based models and financial sentiment analysis: A framework for generative AI in economic decision-making","authors":"Nouri Hicham , Nassera Habbat","doi":"10.1016/j.ject.2025.07.003","DOIUrl":"10.1016/j.ject.2025.07.003","url":null,"abstract":"<div><div>This study introduces a new way to analyze financial sentiment by combining advanced transformer-based models with generative artificial intelligence (AI) to better understand the language and context of financial discussions. The objective is to enhance the predictive accuracy of market behavior through improved understanding of investor sentiment. The proposed sentiment analysis framework leverages six domain-specific datasets: Social Sentiment Indices (X-Scores), Fin-SoMe, SemEval-2017 Task 5, Fin-Lin, Sanders, and Taborda. These datasets, primarily sourced from social media, reflect diverse investor perspectives. Generative AI models, like GPT-3.5 and GPT-4, are used to create more data, and the meaning of words is enhanced using techniques like BERT and Word2Vec. The model is trained with a cross-entropy loss function and fine-tuned using Few-shot Learning, Chain-of-Thought reasoning, and ReAct strategies, ensuring computational efficiency. Experimental results show consistent improvements across all datasets in accuracy, precision, recall, specificity, and F1 score. The use of generative AI and transformer architectures makes the model stronger and better at understanding how investors feel in real financial situations. This research contributes to the field of explicable AI in finance by demonstrating the impact of domain-adapted models and generative techniques in advancing sentiment analysis. The findings offer practical value for investors and analysts seeking data-driven insights into market dynamics and decision-making processes.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 146-170"},"PeriodicalIF":0.0,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827816","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}

引用次数: 0

Valuation of a sequential compound option considering electricity generation and transmission expansions 考虑发电和输电扩建的顺序复合方案的估值

Journal of Economy and Technology

Pub Date : 2025-07-16 DOI: 10.1016/j.ject.2025.07.002

Gazi Nazia Nur, Cameron A. MacKenzie, Kyung Jo Min

An integrated model considering both generation and transmission expansions is needed for long-term planning in the electrical sector because of the interlinked nature of these decisions. Our paper presents a sequential compound option framework to assist decision-makers in the electric power industry in evaluating generation and transmission expansion investments. By incorporating electricity demand uncertainty into the decision-making process, this framework offers a structured approach for assessing short-term generation decisions and long-term transmission decisions in a coordinated manner. Assuming electricity demand follows geometric Brownian motion (GBM), we employ a binomial lattice model to map uncertain demand and evaluate the value of the compound option. The locational marginal price (LMP), which reflects the physical constraints of the power network, is used as the basis for valuation in our model, and reductions in LMP resulting from expansions serve as the measure of project benefit. This integrated approach enables decision-makers to assess the feasibility of generation and transmission expansion projects within a unified framework and determine the optimal timing for exercising the underlying options.

电力部门的长期规划需要考虑发电和输电扩展的综合模型，因为这些决策具有相互联系的性质。本文提出了一个顺序复合期权框架，以帮助电力行业决策者评估发电和输电扩建投资。通过将电力需求不确定性纳入决策过程，该框架为以协调的方式评估短期发电决策和长期输电决策提供了一种结构化的方法。假设电力需求遵循几何布朗运动（GBM），我们采用二项格模型来映射不确定需求并评估复合选项的价值。区位边际价格（LMP）反映了电网的物理约束条件，在我们的模型中被用作评估的基础，而由于扩建而导致的LMP减少则作为项目效益的衡量标准。这种综合方法使决策者能够在统一的框架内评估发电和输电扩建项目的可行性，并确定行使潜在期权的最佳时机。

{"title":"Valuation of a sequential compound option considering electricity generation and transmission expansions","authors":"Gazi Nazia Nur, Cameron A. MacKenzie, Kyung Jo Min","doi":"10.1016/j.ject.2025.07.002","DOIUrl":"10.1016/j.ject.2025.07.002","url":null,"abstract":"<div><div>An integrated model considering both generation and transmission expansions is needed for long-term planning in the electrical sector because of the interlinked nature of these decisions. Our paper presents a sequential compound option framework to assist decision-makers in the electric power industry in evaluating generation and transmission expansion investments. By incorporating electricity demand uncertainty into the decision-making process, this framework offers a structured approach for assessing short-term generation decisions and long-term transmission decisions in a coordinated manner. Assuming electricity demand follows geometric Brownian motion (GBM), we employ a binomial lattice model to map uncertain demand and evaluate the value of the compound option. The locational marginal price (LMP), which reflects the physical constraints of the power network, is used as the basis for valuation in our model, and reductions in LMP resulting from expansions serve as the measure of project benefit. This integrated approach enables decision-makers to assess the feasibility of generation and transmission expansion projects within a unified framework and determine the optimal timing for exercising the underlying options.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 57-76"},"PeriodicalIF":0.0,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703400","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}

引用次数: 0

A resource-efficient ensemble machine learning framework for detecting rank attacks in RPL-based IoT networks 一种资源高效的集成机器学习框架，用于检测基于rpl的物联网网络中的等级攻击

Journal of Economy and Technology

Pub Date : 2025-07-01 DOI: 10.1016/j.ject.2025.06.003

Sattenapalli Kalyani, Vydeki D

The Internet of Things (IoT) links intelligent devices across various sectors, including healthcare, smart cities, and industrial systems, aiming to improve everyday experiences. Despite its benefits, RPL-based routing is commonly adopted in IoT networks operating under low-power and lossy network conditions, which are susceptible to security vulnerabilities, most notably Rank attacks, which distort the routing structure and reduce network performance. Traditional rule-based defenses struggle to scale with dynamic traffic and complex attack patterns, necessitating more adaptive solutions. This paper presents a lightweight, ensemble-based Intrusion Detection System (IDS) that integrates Support Vector Machine (SVM) and XGBoost algorithms to detect Rank attacks in RPL-based IoT environments. A comprehensive dataset was generated by simulating both static and dynamic Rank attack scenarios. Mutual Information and Recursive Feature Elimination (RFE) methods were employed for feature selection. The developed ensemble model exhibited robust performance, reaching an average accuracy of 98.4 %, a precision of 98.2 %, a recall of 97.1 %, an F1-score of 0.97, and a False Positive Rate (FPR) is 1.8 %, an Area Under the Curve (AUC) greater than 0.96 when evaluated using 5-fold cross-validation. Comparative experiments were conducted with traditional machine learning algorithms such as Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF), alongside advanced deep learning architectures including Long Short-Term Memory (LSTM) networks and hybrid models like CNN-LSTM, to effectively demonstrate the superior efficiency and detection capabilities of the proposed approach. Unlike deep models, the proposed solution is resource-efficient and well-suited for deployment on constrained IoT devices. Practical considerations such as latency, computational overhead, and model interpretability are discussed to support real-world applicability. This work introduces one of the initial ensemble learning frameworks tailored for Rank attack detection in RPL, offering both academic insights and engineering relevance for secure IoT deployments.

物联网（IoT）将各个领域的智能设备连接起来，包括医疗保健、智慧城市和工业系统，旨在改善日常体验。尽管具有优势，但基于rpl的路由通常用于在低功耗和有损网络条件下运行的物联网网络，这些网络容易受到安全漏洞的影响，最明显的是Rank攻击，Rank攻击会扭曲路由结构并降低网络性能。传统的基于规则的防御难以适应动态流量和复杂的攻击模式，因此需要更具适应性的解决方案。本文提出了一种轻量级的、基于集成的入侵检测系统（IDS），该系统集成了支持向量机（SVM）和XGBoost算法，用于检测基于rpl的物联网环境中的Rank攻击。通过模拟静态和动态Rank攻击场景，生成了一个全面的数据集。特征选择采用互信息法和递归特征消除法。所开发的集成模型表现出稳健的性能，平均准确率为98.4% %，精密度为98.2% %，召回率为97.1 %，f1得分为0.97，假阳性率（FPR）为1.8 %，曲线下面积（AUC）大于0.96。通过与支持向量机（SVM）、决策树（DT）和随机森林（RF）等传统机器学习算法，以及长短期记忆（LSTM）网络等先进深度学习架构和CNN-LSTM等混合模型进行对比实验，有效证明了所提方法的卓越效率和检测能力。与深度模型不同，所提出的解决方案具有资源效率，非常适合在受限的物联网设备上部署。讨论了诸如延迟、计算开销和模型可解释性等实际考虑因素，以支持现实世界的适用性。这项工作介绍了为RPL中的Rank攻击检测量身定制的初始集成学习框架之一，为安全的物联网部署提供了学术见解和工程相关性。

{"title":"A resource-efficient ensemble machine learning framework for detecting rank attacks in RPL-based IoT networks","authors":"Sattenapalli Kalyani, Vydeki D","doi":"10.1016/j.ject.2025.06.003","DOIUrl":"10.1016/j.ject.2025.06.003","url":null,"abstract":"<div><div>The Internet of Things (IoT) links intelligent devices across various sectors, including healthcare, smart cities, and industrial systems, aiming to improve everyday experiences. Despite its benefits, RPL-based routing is commonly adopted in IoT networks operating under low-power and lossy network conditions, which are susceptible to security vulnerabilities, most notably Rank attacks, which distort the routing structure and reduce network performance. Traditional rule-based defenses struggle to scale with dynamic traffic and complex attack patterns, necessitating more adaptive solutions. This paper presents a lightweight, ensemble-based Intrusion Detection System (IDS) that integrates Support Vector Machine (SVM) and XGBoost algorithms to detect Rank attacks in RPL-based IoT environments. A comprehensive dataset was generated by simulating both static and dynamic Rank attack scenarios. Mutual Information and Recursive Feature Elimination (RFE) methods were employed for feature selection. The developed ensemble model exhibited robust performance, reaching an average accuracy of 98.4 %, a precision of 98.2 %, a recall of 97.1 %, an F1-score of 0.97, and a False Positive Rate (FPR) is 1.8 %, an Area Under the Curve (AUC) greater than 0.96 when evaluated using 5-fold cross-validation. Comparative experiments were conducted with traditional machine learning algorithms such as Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF), alongside advanced deep learning architectures including Long Short-Term Memory (LSTM) networks and hybrid models like CNN-LSTM, to effectively demonstrate the superior efficiency and detection capabilities of the proposed approach. Unlike deep models, the proposed solution is resource-efficient and well-suited for deployment on constrained IoT devices. Practical considerations such as latency, computational overhead, and model interpretability are discussed to support real-world applicability. This work introduces one of the initial ensemble learning frameworks tailored for Rank attack detection in RPL, offering both academic insights and engineering relevance for secure IoT deployments.</div></div>","PeriodicalId":100776,"journal":{"name":"Journal of Economy and Technology","volume":"4 ","pages":"Pages 171-185"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911911","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}

引用次数: 0