Decision Support Systems最新文献

{"title":"Bridging information systems and marketing: Charting collaborative pathways","authors":"Stephen L. France ,&nbsp;Mahyar Sharif Vaghefi ,&nbsp;Brett Kazandjian ,&nbsp;Merrill Warkentin","doi":"10.1016/j.dss.2024.114328","DOIUrl":"10.1016/j.dss.2024.114328","url":null,"abstract":"<div><p>Corporate information systems (IS) functions have become ever closer and more intertwined with firms' marketing functions. Marketing technology and e-commerce implementations require synergy between these functions, which has been reflected in the emergence of researchers and practitioners who can work at the intersection of these disciplines. This article utilizes a systematic literature review to understand this environment and to provide a forward-looking analysis of research at the intersection of IS and marketing. First, a business-focused introduction describes the motivation for the review and puts it into context. This is followed by a bibliographic analysis to select articles at this intersection. A semi-automated content analysis of the selected articles groups them into homogeneous research clusters and further analysis is used to develop cluster themes. This process sheds light on the potential areas of collaboration, offering an in-depth comprehension of their symbiotic relationship. A set of pathways for future research is described based on “collaboration areas” between IS and marketing. These areas, including consumer trust and decision making, social media, online reviews, mobile platforms &amp; apps, and marketing channels, among others, represent the specific areas where marketing and IS overlap and mutually influence each other. Insights are presented on bridging academia and industry and suggestions are proposed for enhancing research at the junction of IS and marketing.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114328"},"PeriodicalIF":6.7,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167923624001611/pdfft?md5=2a48fedfd003cbc70c924abc5797ec14&pid=1-s2.0-S0167923624001611-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228849","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}

{"title":"Channel and bundling strategies: Forging a “win-win” paradigm in product and service operations","authors":"Yudi Zhang ,&nbsp;Xiaojun Wang ,&nbsp;Bangdong Zhi ,&nbsp;Jie Sheng","doi":"10.1016/j.dss.2024.114325","DOIUrl":"10.1016/j.dss.2024.114325","url":null,"abstract":"<div><p>While many companies have benefited from online sales as their sole sales channel with the rapid growth of online retailing, this approach has limitations, especially for products that contain non-digital information and require a complementary service to fully attract customers. Sellers of these types of products are actively considering or have already adopted a multichannel strategy, which includes maintaining the existing online channel and opening physical brick-and-mortar stores. To stimulate sales, the service operator may consider offering a product bundle with the product manufacturer by providing subsidies to them. Decisions on product bundling could potentially facilitate or pose barriers to channel expansion. This study employs a game-theoretic model to explore the optimal pricing, multichannel and bundling strategies for a product manufacturer and a service operator who offer the core products with ancillary services in either bundled or non-bundled format. Our equilibrium analysis yields several insights. First, the manufacturer’s offline expansion allows customers who visit in-store to try and inspect the product, which raises not only the offline price but also the manufacturer’s online price. Interestingly, this price increase is more significant for the bundled format compared to the non-bundled format. Second, the bundling strategy influences the manufacturer’s decision to expand into multichannel operations. Specifically, product bundling incentivises multichannel expansion if the newly added physical stores can attract a significant number of new customers, indicating that demand spillover is significant. Conversely, product bundling may deter multichannel expansion if the online hassle cost is moderate.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114325"},"PeriodicalIF":6.7,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167923624001581/pdfft?md5=9b4418310bd993ea67f53940c05cd454&pid=1-s2.0-S0167923624001581-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142158306","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}

{"title":"How credibility assessment technologies affect decision fairness in evidence-based investigations: A Bayesian perspective","authors":"Xinran Wang ,&nbsp;Zisu Wang ,&nbsp;Mateusz Dolata ,&nbsp;Jay F. Nunamaker","doi":"10.1016/j.dss.2024.114326","DOIUrl":"10.1016/j.dss.2024.114326","url":null,"abstract":"<div><p>Recently, a growing number of credibility assessment technologies (CATs) have been developed to assist human decision-making processes in evidence-based investigations, such as criminal investigations, financial fraud detection, and insurance claim verification. Despite the widespread adoption of CATs, it remains unclear how CAT and human biases interact during the evidence-collection procedure and affect the fairness of investigation outcomes. To address this gap, we develop a Bayesian framework to model CAT adoption and the iterative collection and interpretation of evidence in investigations. Based on the Bayesian framework, we further conduct simulations to examine how CATs affect investigation fairness with various configurations of evidence effectiveness, CAT effectiveness, human biases, technological biases, and decision stakes. We find that when investigators are unconscious of their own biases, CAT adoption generally increases the fairness of investigation outcomes if the CAT is more effective than evidence and less biased than the investigators. However, the CATs' positive influence on fairness diminishes as humans become aware of their own biases. Our results show that CATs' impact on decision fairness highly depends on various technological, human, and contextual factors. We further discuss the implications for CAT development, evaluation, and adoption based on our findings.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114326"},"PeriodicalIF":6.7,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142172502","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}

{"title":"Modeling the co-diffusion of competing memes in online social networks","authors":"Saike He ,&nbsp;Weiguang Zhang ,&nbsp;Jun Luo ,&nbsp;Peijie Zhang ,&nbsp;Kang Zhao ,&nbsp;Daniel Dajun Zeng","doi":"10.1016/j.dss.2024.114324","DOIUrl":"10.1016/j.dss.2024.114324","url":null,"abstract":"<div><p>Online social networks have greatly facilitated the spread of information of all sorts. Meanwhile, the abundance of information in today's world also means different pieces of information will increasingly compete for people's finite attention. When different pieces of information spread together in an online social network, why would some become trendy while others fail to emerge? Existing research either models the diffusion of each piece of information independently, or fails to consider users' inactivity in online social networks. Modeling each piece of information as a meme, this paper addresses this gap by proposing a unified model for the co-diffusion of competing memes simultaneously spreading across an online social network. We are the first to identify a ubiquitous threshold for competing meme. The threshold also functions as an effective predictor that contributes to better performance in determining the outcome of meme competitions. Outcomes from this study have important implications for online campaigns and mobilizations as well as the fight against misinformation.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114324"},"PeriodicalIF":6.7,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S016792362400157X/pdfft?md5=1d51874245e0e8b8066e62560cdb692d&pid=1-s2.0-S016792362400157X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142162805","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}

{"title":"Optimal dynamic advertising policy considering consumer ad fatigue","authors":"Rui Guo ,&nbsp;Zhengrui Jiang","doi":"10.1016/j.dss.2024.114323","DOIUrl":"10.1016/j.dss.2024.114323","url":null,"abstract":"<div><p>In the age of digital advertising, consumers are bombarded with an overwhelming number of advertisements from various channels every day. While repeated exposures to advertising can capture consumers' attention and stimulate their purchases, it is crucial to recognize that excessive advertising campaigns can cause consumer fatigue, diminished responsiveness, or even irritation. In the present study, our objective is to formulate the optimal advertising policy considering the effect of consumer ad fatigue. By introducing an attenuation factor that accounts for the negative impact of excessive advertising expenditure, we modify the dynamics of goodwill in the classical Nerlove-Arrow model. This modification results in the advertising response function exhibiting an inverted U-shaped curve with respect to the advertising expenditure. Our analysis indicates that when consumers experience ad fatigue, it is advisable for the firm to proportionally reduce its advertising expenditure in all time periods. However, the firm should maintain its original direction of trajectory of optimal advertising expenditure despite the presence of consumer ad fatigue.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114323"},"PeriodicalIF":6.7,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142270998","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}

{"title":"What can we learn from multimorbidity? A deep dive from its risk patterns to the corresponding patient profiles","authors":"Xiaochen Wang ,&nbsp;Runtong Zhang ,&nbsp;Xiaomin Zhu","doi":"10.1016/j.dss.2024.114313","DOIUrl":"10.1016/j.dss.2024.114313","url":null,"abstract":"<div><p>Multimorbidity, the presence of two or more chronic conditions within an individual, represents one of the most intricate challenges for global health systems. Traditional single-disease management often fails to address the multifaceted nature of multimorbidity. Network model emerges as a growing field for elucidating the interconnections among multimorbidity. However, the field lacks a standardized method to compute and visually represent of these networks. Given the challenges, this study proposes a three-stage methodology to decipher multimorbidity. First, we integrate the Failure Modes and Effects Analysis (FMEA) method with the multimorbidity encapsulation framework to develop the Multimorbidity Risk Network (MRN). Second, we use complex network techniques to identify high-risk patterns within MRN communities. Finally, we apply machine learning techniques to correlate these communities with the biological attributes of patients that have been marginalized in most studies. Our approach advocates a paradigm shift from the conventional focus on single diseases to a holistic, patient-centric approach, providing decision-makers with integrated information technology artifacts for deciphering the multimorbidity.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"186 ","pages":"Article 114313"},"PeriodicalIF":6.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142151015","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}

{"title":"Emotional expressions of care and concern by customer service chatbots: Improved customer attitudes despite perceived inauthenticity","authors":"Junbo Zhang ,&nbsp;Jiandong Lu ,&nbsp;Xiaolei Wang ,&nbsp;Luning Liu ,&nbsp;Yuqiang Feng","doi":"10.1016/j.dss.2024.114314","DOIUrl":"10.1016/j.dss.2024.114314","url":null,"abstract":"<div><p>In customer service, emotional expressions by chatbots are considered a promising direction to improve customer experience. However, there is a lack of comprehensive understanding of how and when chatbots' emotional expressions improve customer attitudes. Although chatbots' emotional expressions of care and concern may feel inauthentic to customers in the inferential path, which can negatively affects customer attitudes, we propose that the positive effect of the affective reactions path can result in a positive effect on customer attitude based on the dual-path view of Emotions as Social Information (EASI). The relative strengths of the two EASI paths can be moderated, and we explored the moderating effects of rational thinking styles (information processing in EASI) and beliefs in computer emotion (perceived appropriateness in EASI). According to EASI, situation can affect the meaning of emotions, so we conducted experiments in two situations. With chatbot identity disclosure, we found that the chatbot's emotional expressions reduce customers' perceived authenticity (reflecting the inferential path in EASI) but ultimately improve customer attitudes. Belief in computer emotions and rational thinking style moderated the negative relationship between emotional expressions and authenticity. With chatbot identity non-disclosure, the chatbot's emotional expressions still improve customer attitudes but with no effect on authenticity. Because there is high likelihood of chatbot identities being discovered by customers, this finding of the moderating effect of perceived humanness on authenticity is highly relevant. Our findings make important contributions to research on computer emotion and service authenticity.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"186 ","pages":"Article 114314"},"PeriodicalIF":6.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142150984","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}

{"title":"Approaches to improve preprocessing for Latent Dirichlet Allocation topic modeling","authors":"Jamie Zimmermann ,&nbsp;Lance E. Champagne ,&nbsp;John M. Dickens ,&nbsp;Benjamin T. Hazen","doi":"10.1016/j.dss.2024.114310","DOIUrl":"10.1016/j.dss.2024.114310","url":null,"abstract":"<div><p>As a part of natural language processing (NLP), the intent of topic modeling is to identify topics in textual corpora with limited human input. Current topic modeling techniques, like Latent Dirichlet Allocation (LDA), are limited in the pre-processing steps and currently require human judgement, increasing analysis time and opportunities for error. The purpose of this research is to allay some of those limitations by introducing new approaches to improve coherence without adding computational complexity and provide an objective method for determining the number of topics within a corpus. First, we identify a requirement for a more robust stop words list and introduce a new dimensionality-reduction heuristic that exploits the number of words within a document to infer importance to word choice. Second, we develop an eigenvalue technique to determine the number of topics within a corpus. Third, we combine all of these techniques into the Zimm Approach, which produces higher quality results than LDA in determining the number of topics within a corpus. The Zimm Approach, when tested against various subsets of the 20newsgroup dataset, produced the correct number of topics in 7 of 9 subsets vs. 0 of 9 using highest coherence value produced by LDA.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"185 ","pages":"Article 114310"},"PeriodicalIF":6.7,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142088817","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}

{"title":"Learning-based dynamic pricing strategy with pay-per-chapter mode for online publisher with case study of COL","authors":"Lang Fang,&nbsp;Zhendong Pan,&nbsp;Jiafu Tang","doi":"10.1016/j.dss.2024.114311","DOIUrl":"10.1016/j.dss.2024.114311","url":null,"abstract":"<div><p>We consider how to make dynamic pricing decision for Chinese Online (COL) at <em>T</em> time-points, an online publisher that allow authors to sell their ongoing book projects. Instead of paying for a book, readers pay for each chapter (pay-per-chapter mode) of the ongoing book project. This mode allows readers to pay for as many chapters as they want without taking the risk that the releasing of new chapters might be delayed or stopped. Despite of the dynamics of chapter-by-chapter released of COL products, the fixed pricing strategy (FPS) does not make fully use of the reading data generated by releasing chapters of the ongoing book. We propose a learning-based dynamic pricing strategy (LDPS) that exploits the newly information to maximize cumulative revenue for the publisher. The LDPS captures the ever changing features of readers. It employs the Thompson sampling method to balance the exploration of investigating different prices sufficiently with the exploitation of settling on the optimal price. Taking COL as a case study and implementing our strategy in the context of the aforementioned real-life data set, we show that LDPS outperform several classical strategies such as Greedy, Prior-Free TS and Prior-Given TS, and average revenue of LDPS is increased by 0.5 % average per time-point compared to the publisher's historical decisions. We also provide some management implications for the COL publisher by analyzing the pricing range of different genres of books and the choice of the exploration threshold parameter.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"186 ","pages":"Article 114311"},"PeriodicalIF":6.7,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142150986","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}

{"title":"Reliability estimation for individual predictions in machine learning systems: A model reliability-based approach","authors":"Xiaoge Zhang ,&nbsp;Indranil Bose","doi":"10.1016/j.dss.2024.114305","DOIUrl":"10.1016/j.dss.2024.114305","url":null,"abstract":"&lt;div&gt;&lt;p&gt;The conventional aggregated performance measure (i.e., mean squared error) with respect to the whole dataset would not provide desired safety and quality assurance for each individual prediction made by a machine learning model in risk-sensitive regression problems. In this paper, we propose an informative indicator &lt;span&gt;&lt;math&gt;&lt;mi&gt;ℛ&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt; to quantify model reliability for individual prediction (MRIP) for the purpose of safeguarding the usage of machine learning (ML) models in mission-critical applications. Specifically, we define the reliability of a ML model with respect to its prediction on each individual input &lt;span&gt;&lt;math&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/math&gt;&lt;/span&gt; as the probability of the observed difference between the prediction of ML model and the actual observation falling within a small interval when the input &lt;span&gt;&lt;math&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/math&gt;&lt;/span&gt; varies within a small range subject to a preset distance constraint, namely &lt;span&gt;&lt;math&gt;&lt;mi&gt;ℛ&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;mo&gt;=&lt;/mo&gt;&lt;mi&gt;P&lt;/mi&gt;&lt;mfenced&gt;&lt;mrow&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;msup&gt;&lt;mi&gt;y&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;msup&gt;&lt;mover&gt;&lt;mi&gt;y&lt;/mi&gt;&lt;mo&gt;̂&lt;/mo&gt;&lt;/mover&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mo&gt;≤&lt;/mo&gt;&lt;mi&gt;ε&lt;/mi&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;mo&gt;∈&lt;/mo&gt;&lt;mi&gt;B&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;/mrow&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt;, where &lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mi&gt;y&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/math&gt;&lt;/span&gt; denotes the observed target value for the input &lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;mo&gt;,&lt;/mo&gt;&lt;/math&gt;&lt;/span&gt; &lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mover&gt;&lt;mi&gt;y&lt;/mi&gt;&lt;mo&gt;̂&lt;/mo&gt;&lt;/mover&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/math&gt;&lt;/span&gt; denotes the model prediction for the input &lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/math&gt;&lt;/span&gt;, and &lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/math&gt;&lt;/span&gt; is an input in the neighborhood of &lt;span&gt;&lt;math&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/math&gt;&lt;/span&gt; subject to the constraint &lt;span&gt;&lt;math&gt;&lt;mi&gt;B&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;mo&gt;=&lt;/mo&gt;&lt;mfenced&gt;&lt;mrow&gt;&lt;mfenced&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;/mfenced&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mfenced&gt;&lt;mrow&gt;&lt;msup&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;mo&gt;∗&lt;/mo&gt;&lt;/msup&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mrow&gt;&lt;/mfenced&gt;&lt;mo&gt;≤&lt;/mo&gt;&lt;mi&gt;δ&lt;/mi&gt;&lt;/mrow&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt;. The developed MRIP indicator &lt;span&gt;&lt;math&gt;&lt;mi&gt;ℛ&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt; provides a direct, objective, quantitative, and general-purpose measure of “reliability” or the probability of success of the ML model for each individual prediction by fully exploiting the local information associated with the input &lt;span&gt;&lt;math&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/math&gt;&lt;/span&gt; and ML model. Next, to mitigate the intensive computational effort involved in MRIP estimation, we develop a two-stage ML-based framework to directly learn the relationship between &lt;span&gt;&lt;math&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/math&gt;&lt;/span&gt; and its MRIP &lt;span&gt;&lt;math&gt;&lt;mi&gt;ℛ&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt;, thus enabling to provide the reliability estimate &lt;span&gt;&lt;math&gt;&lt;mi&gt;ℛ&lt;/mi&gt;&lt;mfenced&gt;&lt;mi&gt;x&lt;/mi&gt;&lt;/mfenced&gt;&lt;/math&gt;&lt;/span&gt; for any unseen input instantly. Thirdly, we pr","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"186 ","pages":"Article 114305"},"PeriodicalIF":6.7,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142151016","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}