DECISION SCIENCES最新文献

Explanation seeking and anomalous recommendation adherence in human-to-human versus human-to-artificial intelligence interactions 在人与人和人与人工智能的互动中寻求解释和异常推荐的遵从性

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-11-21 DOI: 10.1111/deci.12658

Tracy Jenkin, Stephanie Kelley, Anton Ovchinnikov, Cecilia Ying

{"title":"Explanation seeking and anomalous recommendation adherence in human-to-human versus human-to-artificial intelligence interactions","authors":"Tracy Jenkin, Stephanie Kelley, Anton Ovchinnikov, Cecilia Ying","doi":"10.1111/deci.12658","DOIUrl":"https://doi.org/10.1111/deci.12658","url":null,"abstract":"The use of artificial intelligence (AI) in operational decision-making is growing, but individuals can display algorithm aversion, preventing adherence to AI system recommendations—even when the system outperforms human decision-makers. Understanding why such algorithm aversion occurs and how to reduce it is important to ensure AI is fully leveraged. While the ability to seek an explanation from an AI may be a promising approach to mitigate this aversion, there is conflicting evidence on their benefits. Based on several behavioral theories, including Bayesian choice, loss aversion, and sunk cost avoidance, we hypothesize that if a recommendation is perceived as an anomalous loss, it will decrease recommendation adherence; however, the effect will be mediated by explanations and differ depending on whether the advisor providing the recommendation and explanation is a human or an AI. We conducted a survey-based lab experiment set in the online rental market space and found that presenting a recommendation as a loss anomaly significantly reduces adherence compared to presenting it as a gain, however, this negative effect can be dampened if the advisor is an AI. We find explanation-seeking has a limited impact on adherence, even after considering the influence of the advisor; we discuss the managerial and theoretical implications of these findings.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"55 6","pages":"653-668"},"PeriodicalIF":2.8,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/deci.12658","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fine-tuning of artificial intelligence managers' logic in a supply chain with competing retailers 在有竞争零售商的供应链中对人工智能管理人员的逻辑进行微调

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-11-12 DOI: 10.1111/deci.12657

Yue Li, Ruiqing Zhao, Xiang Li, Tsan-Ming Choi

{"title":"Fine-tuning of artificial intelligence managers' logic in a supply chain with competing retailers","authors":"Yue Li, Ruiqing Zhao, Xiang Li, Tsan-Ming Choi","doi":"10.1111/deci.12657","DOIUrl":"https://doi.org/10.1111/deci.12657","url":null,"abstract":"Today, with the advance of artificial intelligence, companies in the real world are using AI as managers to make operational decisions, who can respond quickly to market shocks and whose logic can be fine-tuned to programmed pessimism/optimism, that is, underestimating/overestimating the market. The introduction of AI managers poses new challenges to supply chain management, and how to manage AI managers warrants further exploration. We investigate the optimal AI manager fine-tuning strategies in a supply chain consisting of one manufacturer and two competing retailers, each operated by an AI manager in the face of an uncertain market shock. We establish the manufacturer–retailer AI manager fine-tuning game, where the manufacturer and two retailers endogenously decide whether to fine-tune their AI managers' logic. The market may suffer an uncertain shock, and once the shock occurs, the AI managers' logic settings and price decisions can be quickly adjusted. We find that the manufacturer would never fine-tune the AI manager, while the retailers may fine-tune their AI managers to programmed optimism. Notably, AI manager's fine-tunability only benefits the retailers and harms the manufacturer, entire supply chain, consumers, and social welfare. To make AI manager's fine-tunability beneficial to all participants, that is, to reach a win–win–win situation, we design two incentive mechanisms, retailer pessimism incentive mechanism and mutual pessimism incentive mechanism (MPIM), where MPIM can lead to the win–win–win situation. Further, we endogenize the compensation, endogenous retailer pessimism compensation and endogenous mutual pessimism compensation, both achieving the win–win–win outcome. We also make several extensions and provide suggestions for supply chain firms to fine-tune their AI managers' logic.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"55 6","pages":"639-652"},"PeriodicalIF":2.8,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142860789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI in business research 商业研究中的人工智能

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-11-06 DOI: 10.1111/deci.12655

Zhi Cao, Meng Li, Paul A Pavlou

引用次数: 0

Voice or text? The role of physician media choice on patient experience in online medical communities 语音还是短信？医生媒介选择对在线医疗社区患者体验的作用

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-11-06 DOI: 10.1111/deci.12654

Anfei Xia, Sandun C. Perera, Muhammad U. Ahmed, Jianying Tang, Jian-Jun Wang

{"title":"Voice or text? The role of physician media choice on patient experience in online medical communities","authors":"Anfei Xia, Sandun C. Perera, Muhammad U. Ahmed, Jianying Tang, Jian-Jun Wang","doi":"10.1111/deci.12654","DOIUrl":"https://doi.org/10.1111/deci.12654","url":null,"abstract":"Online medical communities (OMCs) are a type of online healthcare, in which physician-patient interaction can be comprised of a variety of media options such as pictures, text, and voice. These media formats are often used to create a personalized patient experience in AI-driven conversational healthcare platforms. To explore how physician media usage affects patient experience, we propose a counterfactual causal inference model using AI-driven data mining methods on 131,083 online consultation records and 7,666,111 messages sent by physicians from one of the largest OMCs in China. Our study reveals the negative impact of physician use of voice on patient experience, compared to text. Drawing upon social support theory, we identify the mechanism by which physician media usage for voice produces a negative effect. The findings indicate that the negative effect of physicians' voice-media usage occurs mainly in low-risk disease conditions, by weakening the role of professional and emotional support. In contrast, in high-risk disease conditions, voice-media usage strengthens the role of professional and emotional support in improving the patient's experience. Our study is one of the first to focus on the social support attributes of the different media formats used in OMCs. We use advanced AI text-analysis algorithms to extract features related to social support in physician-patient conversations, and thus contribute to the use of AI in feature extraction for research.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"55 6","pages":"620-638"},"PeriodicalIF":2.8,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142860196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised news analysis for enhanced high-frequency food insecurity assessment 用于加强高频率粮食不安全评估的无监督新闻分析

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-10-13 DOI: 10.1111/deci.12653

Cascha van Wanrooij, Frans Cruijssen, Juan Sebastian Olier

引用次数: 0

Variable-weight combined forecasting model with causal analysis and clustering for refined oil sales forecasting 成品油销售预测的因果分析聚类变权组合预测模型

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-10-08 DOI: 10.1111/deci.12648

Xiaofeng Xu, Wenzhi Liu, Lean Yu, Yinsheng Yu, Wanli Yi

{"title":"Variable-weight combined forecasting model with causal analysis and clustering for refined oil sales forecasting","authors":"Xiaofeng Xu, Wenzhi Liu, Lean Yu, Yinsheng Yu, Wanli Yi","doi":"10.1111/deci.12648","DOIUrl":"https://doi.org/10.1111/deci.12648","url":null,"abstract":"Forecasting refined oil sales is essential in energy supply chain management. However, accurate forecasting is limited by several factors, including multiple influences of external features, heterogeneity of different gasoline stations, and difficulty in balancing linear and nonlinear forecasting. To address these issues, we propose a novel variable-weight combined forecasting model. In the first stage, the model incorporates causal analysis and clustering methods to provide a quantitative description of multiple effects of external features and highly correlated aggregation of homogeneous data. Subsequently, based on the patterns of external feature influences learned from historical data, variable-weight combined forecasting is realized to balance linear and nonlinear forecasting dynamically. Experiments based on real sales data procured from several regions demonstrate that the proposed model outperforms other benchmark and widely used models in terms of forecasting accuracy and statistical significance. The ablation experimental results confirm the significance of causal analysis, clustering, and variable-weight combined forecasting in improving the balance between linear and nonlinear forecasting. Moreover, our results indicate that improving the quality of clustering can yield greater benefits than improving the amount of training data. Finally, we also explore whether the forecasting superiority translates into better inventory control, and our results show that the proposed optimization model can effectively balance inventory cost and service level, while also better suppress the bullwhip effect.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"55 6","pages":"577-604"},"PeriodicalIF":2.8,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142860489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tax privacy concerns hamper digitization of the nanostore channel 税收隐私问题阻碍纳米存储通道数字化

IF 5.5 4区管理学

DECISION SCIENCES Pub Date : 2024-09-18 DOI: 10.1111/deci.12643

Rafael Escamilla, Prisca Brosi, Jan C. Fransoo, Camilo Mora‐Quiñones, Christopher Mejía‐Argueta

{"title":"Tax privacy concerns hamper digitization of the nanostore channel","authors":"Rafael Escamilla, Prisca Brosi, Jan C. Fransoo, Camilo Mora‐Quiñones, Christopher Mejía‐Argueta","doi":"10.1111/deci.12643","DOIUrl":"https://doi.org/10.1111/deci.12643","url":null,"abstract":"Various entities, such as startups, suppliers, and governments, face substantial difficulties in convincing nanostore shopkeepers to adopt digital technologies. Given the informal status of nanostores, we posit that shopkeepers experience Tax Privacy Concerns from their operational records potentially becoming transparent to the tax authorities, which hampers their inclination to digitize. Through the application of a survey and vignette experiments in the field with hundreds of shopkeepers across three cities in Latin America, we find consistent evidence for the negative role of Tax Privacy Concerns, above and beyond shopkeepers' Willingness to Share Data with various entities, Trust in the government and other entities, and general Privacy Concerns. Further, we show that having entities that shopkeepers trust and are willing to share data with offer technological solutions does not mitigate shopkeepers' Tax Privacy Concerns and boosts digitization. In contrast, positive word of mouth that data are unlikely to be shared with the tax authorities does mitigate Tax Privacy Concerns. Overall, our findings provide novel evidence for the existence and influence of privacy concerns for operational data among microentrepreneurs, which answers calls in the extant literature to explore privacy concerns beyond the consumer context.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"123 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142251305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Beneficiary appointment and delivery planning in a conflict setting 冲突环境下的受益人任命和交付规划

IF 5.5 4区管理学

DECISION SCIENCES Pub Date : 2024-08-14 DOI: 10.1111/deci.12645

Burcu Balcik, Maria Battarra, Melih Celik, Bashar Khoury, Anand Subramanian

{"title":"Beneficiary appointment and delivery planning in a conflict setting","authors":"Burcu Balcik, Maria Battarra, Melih Celik, Bashar Khoury, Anand Subramanian","doi":"10.1111/deci.12645","DOIUrl":"https://doi.org/10.1111/deci.12645","url":null,"abstract":"In this study, we explore the challenges faced by humanitarian organizations engaged in relief efforts for internally displaced individuals during armed conflicts. Based on our semistructured interviews with three local nongovernmental organizations (LNGOs) in Syria, we introduce a new appointment scheduling problem to improve decision‐making for aid delivery planning in conflict settings. Operating in a highly resource‐constrained environment, these LNGOs face complexities that necessitate effective decision support tools to streamline supply delivery at relief facilities, where a large number of registered beneficiaries are served. Our proposed appointment scheduling problem aims to optimize the allocation of delivery times for various supplies, taking into account the urgency of needs and operational limitations. We present a heuristic that addresses the complexities of the proposed scheduling problem in a flexible way. The heuristic can accommodate simple rules derived from LNGOs' operational policies on the ground, such as imposing a single visit per beneficiary, delivering a single supply type per day, and preallocating time slots to conflict groups. We present a case study based on the Latakia district of Syria to assess the performance of our heuristic and the effectiveness of simplified delivery strategies. Our results not only showcase the efficiency of the heuristic, but also provide valuable managerial insights. We find that cross‐training of staff is more beneficial when supplies are relatively abundant. Furthermore, the simplified delivery policies are effective in certain conditions contingent upon various factors, including supply scarcity, difficulty of travel, and the level of conflict in the population.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"61 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142178235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An interpretable machine learning methodology to generate interaction effect hypotheses from complex datasets 从复杂数据集生成交互效应假设的可解释机器学习方法

IF 2.8 4区管理学

DECISION SCIENCES Pub Date : 2024-08-13 DOI: 10.1111/deci.12642

Murtaza Nasir, Nichalin S. Summerfield, Serhat Simsek, Asil Oztekin

{"title":"An interpretable machine learning methodology to generate interaction effect hypotheses from complex datasets","authors":"Murtaza Nasir, Nichalin S. Summerfield, Serhat Simsek, Asil Oztekin","doi":"10.1111/deci.12642","DOIUrl":"10.1111/deci.12642","url":null,"abstract":"Machine learning (ML) models are increasingly being used in decision-making, but they can be difficult to understand because most ML models are black boxes, meaning that their inner workings are not transparent. This can make interpreting the results of ML models and understanding the underlying data-generation process (DGP) challenging. In this article, we propose a novel methodology called Simple Interaction Finding Technique (SIFT) that can help make ML models more interpretable. SIFT is a data- and model-agnostic approach that can be used to identify interaction effects between variables in a dataset. This can help improve our understanding of the DGP and make ML models more transparent and explainable to a wider audience. We test the proposed methodology against various factors (such as ML model complexity, dataset noise, spurious variables, and variable distributions) to assess its effectiveness and weaknesses. We show that the methodology is robust against many potential problems in the underlying dataset as well as ML algorithms.","PeriodicalId":48256,"journal":{"name":"DECISION SCIENCES","volume":"55 6","pages":"549-576"},"PeriodicalIF":2.8,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/deci.12642","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142178233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A real‐time decision support system to improve operations in electric bus networks 改善电动巴士网络运营的实时决策支持系统

IF 5.5 4区管理学

DECISION SCIENCES Pub Date : 2024-05-29 DOI: 10.1111/deci.12633

Ayman Abdelwahed, Pieter L. van den Berg, Tobias Brandt, Wolfgang Ketter

引用次数: 0