Decision Support Systems最新文献_第4页

Can causal machine learning reveal individual bid responses of bank customers? — A study on mortgage loan applications in Belgium

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-12-24 DOI: 10.1016/j.dss.2024.114378

Christopher Bockel-Rickermann , Sam Verboven , Tim Verdonck , Wouter Verbeke

引用次数: 0

Excessive use in the metaverse: The role of multisensory interaction 虚拟世界中的过度使用：多感官互动的作用

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-12-24 DOI: 10.1016/j.dss.2024.114390

Chongyang Chen , Yao-Yu Wang , Kem Z.K. Zhang , Fenghua Xie

{"title":"Excessive use in the metaverse: The role of multisensory interaction","authors":"Chongyang Chen , Yao-Yu Wang , Kem Z.K. Zhang , Fenghua Xie","doi":"10.1016/j.dss.2024.114390","DOIUrl":"10.1016/j.dss.2024.114390","url":null,"abstract":"<div><div>The metaverse allows users to interact with the real and virtual worlds naturally by stimulating multimodal sensations. Meanwhile, the attractive environments created by the metaverse may also bring challenges such as excessive use. There is a great deal of uncertainty about the undesirable risks of the metaverse. Therefore, this study makes efforts to introduce a theoretical framework and explain why the advanced design of multisensory interaction can result in excessive use in the context of metaverse games. Considering the influence of multisensory interaction, we point out the important yet little investigated role of feelings in this research, especially when previous studies mostly focus on the effects of cognition. We thus apply the theory of feelings-as-information as our theoretical basis. We first systematically identify specific types of sensation stimulation in multisensory interaction. Then, we interpret the process that a desirable characteristic (multisensory interaction), which contributes to realistic feelings (plausibility illusion and place illusion), may affect users to generate maladaptive judgment (i.e., time distortion) and finally lead to unexpected outcome of excessive use. Our research model is tested with a scenario-based survey method. The empirical data confirms the proposed model. This study provides noteworthy insights on the potential dangers of the metaverse. The implications are discussed.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"190 ","pages":"Article 114390"},"PeriodicalIF":6.7,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decision support through deep reinforcement learning for maximizing a courier's monetary gain in a meal delivery environment

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-12-20 DOI: 10.1016/j.dss.2024.114388

Weiwen Zhou, Hossein Fotouhi, Elise Miller-Hooks

{"title":"Decision support through deep reinforcement learning for maximizing a courier's monetary gain in a meal delivery environment","authors":"Weiwen Zhou, Hossein Fotouhi, Elise Miller-Hooks","doi":"10.1016/j.dss.2024.114388","DOIUrl":"10.1016/j.dss.2024.114388","url":null,"abstract":"<div><div>Meal delivery is a fast-growing industry supported by couriers participating in the gig economy. This paper takes a single courier's perspective and provides decision support for an individual courier who works at will in repositioning between jobs and order-taking to optimize her profit during a work period. A hybrid discrete-time, discrete-event simulation environment was developed based on data from a real-world meal delivery environment to replicate daily operations. The single courier's repositioning and order-taking decision problem is formulated as a Markov decision process. Two classes of deep reinforcement learning (DRL) methodologies, value-based and policy-gradient algorithms, were implemented to determine the courier's best decisions to take as the courier's work shift progresses. In numerical experiments, the best optimal policy resulting from the DRL algorithms is shown to outperform all considered static policies in all demand environments. Insights from studying the decisions suggested by the best of the DRL methods were employed to create a promising static policy by generating decision trees for relocation and order-taking. The results indicate that as couriers find more intelligent strategies for maximizing their rewards, the meal delivery platform will have even greater need to incentivize couriers to fulfill less attractive orders, especially in surge periods. Finally, the impact of a multi-courier DRL environment, where multiple couriers have the advantage of the DRL strategy, was studied. For this purpose, a multi-agent DRL was implemented and numerical experiments were conducted to investigate the tradeoffs between individual courier gains and system-level performance. Findings from this multi-agent extension show the negative impacts of selfish behavior on not only the system, but the couriers themselves.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"190 ","pages":"Article 114388"},"PeriodicalIF":6.7,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

What happens when platforms disclose the purchase history associated with product reviews? 当平台披露与产品评论相关的购买记录时会发生什么？

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-11-14 DOI: 10.1016/j.dss.2024.114367

Miaomiao Liu , Xiaohua Zeng , Cheng Zhang , Yong Liu

{"title":"What happens when platforms disclose the purchase history associated with product reviews?","authors":"Miaomiao Liu , Xiaohua Zeng , Cheng Zhang , Yong Liu","doi":"10.1016/j.dss.2024.114367","DOIUrl":"10.1016/j.dss.2024.114367","url":null,"abstract":"<div><div>In striking a balance between attracting more product reviews versus maintaining review quality, online platforms have started to label reviews with whether they are associated with verifiable purchases. This paper examines the impact of such disclosure policy on the strategic behavior of review writers and the helpfulness of verified reviews (VRs) and non-verified reviews (NVRs) for review users. We propose that the introduction of the verified purchase tag induces two competing effects for VRs, increased credibility and concerns for acquisition bias, which in turn influence the behaviors of both writers and users. By exploiting the exogenous shock resulting from a policy change on Amazon, we find that, after the disclosure, NVRs became longer in length and VRs started to contain more unique information. Surprisingly, we find strong evidence that VRs receive fewer helpfulness votes than NVRs. We further explore the underlying mechanism, namely review users' concerns about acquisition bias associated with VRs, and identify conditions under which these unexpected effects can be mitigated. Our findings generate important implications for online platforms seeking to design a more effective review ecosystem and for review writers aiming to produce more helpful content.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114367"},"PeriodicalIF":6.7,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142701504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comparative analysis of the effect of initiative risk statement versus passive risk disclosure on the financing performance of Kickstarter campaigns 主动风险声明与被动风险披露对 Kickstarter 活动融资绩效影响的比较分析

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-11-09 DOI: 10.1016/j.dss.2024.114366

Wei Wang , Ying Li , Jian Mou , Kevin Zhu

{"title":"A comparative analysis of the effect of initiative risk statement versus passive risk disclosure on the financing performance of Kickstarter campaigns","authors":"Wei Wang , Ying Li , Jian Mou , Kevin Zhu","doi":"10.1016/j.dss.2024.114366","DOIUrl":"10.1016/j.dss.2024.114366","url":null,"abstract":"<div><div>Extending the theory of perceived risk, this study examines how risk perception, a vital factor in determining investment decisions, comprising both initiative risk statement generated by fundraisers and passive risk disclosure published by backers, influences crowdfunding financing performance. Utilizing a corpus of 126,593 innovative projects from Kickstarter, text analytics is employed to classify risks into controllable and uncontrollable types for an empirical comparative examination. The results show that initiative risk statement negatively impacts financing performance, while passive risk disclosure has a positive influence. Comparatively, passive risk disclosure is superior to initiative risk statement. Uncontrollable (controllable) risks in initiative (passive) risk statement are superior to controllable (uncontrollable) ones. Additionally, a textual cognitive load negatively impacted initiative risk statement and passive risk disclosure. Multiple additional tests, including continuous and discrete measurements of risk, endogeneity correction, and dynamic effects over time, demonstrate the robustness of the results. This study contributes to extending the understanding of online financing risks and providing practical implications for fundraisers and backers in innovative online projects.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114366"},"PeriodicalIF":6.7,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Revisiting time-varying dynamics in stock market forecasting: A multi-source sentiment analysis approach with large language model

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-11-08 DOI: 10.1016/j.dss.2024.114362

Zhiqi Shao , Xusheng Yao , Feng Chen , Ze Wang , Junbin Gao

{"title":"Revisiting time-varying dynamics in stock market forecasting: A multi-source sentiment analysis approach with large language model","authors":"Zhiqi Shao , Xusheng Yao , Feng Chen , Ze Wang , Junbin Gao","doi":"10.1016/j.dss.2024.114362","DOIUrl":"10.1016/j.dss.2024.114362","url":null,"abstract":"<div><div>This paper presents the Heterogeneous Dynamic Seemingly Unrelated Regression with Dynamic Linear Models (HD-SURDLM), an innovative framework for stock return prediction that combines cutting-edge sentiment analysis with dynamic financial modeling. The model integrates sentiment data from 2.5 million Twitter posts and various news sources, utilizing state-of-the-art sentiment analysis tools such as VADER, TextBlob, and RoBERTa. HD-SURDLM refines Gibbs sampling for enhanced numerical stability and efficiency while capturing cross-sectional dependencies across multiple assets such as a portfolio. The model consistently outperforms traditional methods like LSTM, Random Forest, and RNN in forecasting accuracy. Empirical results show a 1.02% improvement in 1-day horizon forecasts, a 0.42% gain for 20-day predictions, and a 0.36% increase for 50-day forecasts. By effectively merging public sentiment with dynamic asset modeling, HD-SURDLM offers substantial improvements in short- and long-term prediction accuracy. Its capacity to capture both cross-sectional insights and temporal dynamics makes it an invaluable tool for investors, traders, and financial institutions navigating sentiment-driven markets. HD-SURDLM not only enhances predictive accuracy but also provides a robust decision-support system for financial stakeholders.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"190 ","pages":"Article 114362"},"PeriodicalIF":6.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DeepSecure: A computational design science approach for interpretable threat hunting in cybersecurity decision making DeepSecure：在网络安全决策中采用可解释的威胁猎取计算设计科学方法

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-11-06 DOI: 10.1016/j.dss.2024.114351

Prabhat Kumar , Danish Javeed , A.K.M. Najmul Islam , Xin (Robert) Luo

{"title":"DeepSecure: A computational design science approach for interpretable threat hunting in cybersecurity decision making","authors":"Prabhat Kumar , Danish Javeed , A.K.M. Najmul Islam , Xin (Robert) Luo","doi":"10.1016/j.dss.2024.114351","DOIUrl":"10.1016/j.dss.2024.114351","url":null,"abstract":"<div><div>Businesses and industries are placing a greater emphasis on information systems for cybersecurity decision-making due to the rising cybersecurity threat landscape and the critical need to protect their digital assets. Threat hunting provides a data-driven and proactive approach to cybersecurity, enabling organizations to efficiently detect, analyze, and respond to cyber threats in real-time. Despite playing a crucial role, these systems face several obstacles, including the manual analysis of technical threat intelligence, the non-Gaussian nature of real-world data, the high rate of false positives produced during threat hunting, and the lack of interpretation and justification for these complex models. This article adopts the computational design science paradigm to develop a novel IT artifact for threat-hunting named DeepSecure. First, to automatically extract latent patterns from multivariate time series datasets, we propose a dynamic vector quantized variational autoencoder technique. Second, a multiscale hierarchical attention bi-directional gated recurrent unit-based threat-hunting mechanism is designed. Finally, we provide the visualization of attention scores to aid in model interpretation. We evaluate the DeepSecure against state-of-the-art benchmarks on two publicly available datasets, namely, ToN-IoT and CSE-CIC-IDS2018. The experimental evaluation proves that our model can efficiently identify threat types. Beyond demonstrating practical utility, the proposed framework can help address the lack of interpretation and justification for complex models in cyber threat detection and will allow organizations to respond to potential security incidents quickly.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114351"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effects of visual-preview and information-sidedness features on website persuasiveness 视觉预览和信息片面性特征对网站说服力的影响

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-11-01 DOI: 10.1016/j.dss.2024.114361

Yi-Chen Lee , Chih-Hung Peng , Choon-Ling Sia , Weiling Ke

引用次数: 0

The evolution of organizations and stakeholders for metaverse ecosystems: Editorial for the special issue on metaverse part 1 元宇宙生态系统的组织和利益相关者的演变：为元宇宙特刊第 1 部分撰写的社论

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-10-29 DOI: 10.1016/j.dss.2024.114353

Arpan Kumar Kar , Patrick Mikalef , Rohit Nishant , Xin (Robert) Luo , Manish Gupta

引用次数: 0

Know where to go: Make LLM a relevant, responsible, and trustworthy searchers 知道去哪里：让 LLM 成为相关的、负责任的、值得信赖的搜索者

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2024-10-28 DOI: 10.1016/j.dss.2024.114354

Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng, Wei Lu

{"title":"Know where to go: Make LLM a relevant, responsible, and trustworthy searchers","authors":"Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng, Wei Lu","doi":"10.1016/j.dss.2024.114354","DOIUrl":"10.1016/j.dss.2024.114354","url":null,"abstract":"<div><div>The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches. However, challenges arise in validating the reliability of generated results and the credibility of contributing sources due to the limitations of traditional information retrieval algorithms and the LLM hallucination problem. We aim to transform LLM into a relevant, responsible, and trustworthy searcher in response to these challenges. Rather than following the traditional generative retrieval approach, simply allowing the LLM to summarize the search results, we propose a novel generative retrieval framework leveraging the knowledge of LLMs to foster a direct link between queries and web sources. This framework reforms the retrieval process of the traditional generative retrieval framework by integrating an LLM retriever, and it redesigns the validator while adding an optimizer to ensure the reliability of the retrieved web sources and evidence sentences. Extensive experiments show that our method outperforms several SOTA methods in relevance, responsibility, and trustfulness. It improves search result validity and precision by 2.54 % and 1.05 % over larger-parameter-scale LLM-based systems. Furthermore, it demonstrates significant advantages over traditional frameworks in question-answering and downstream tasks.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114354"},"PeriodicalIF":6.7,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0