Monica Chiarini Tremblay
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Monica Chiarini Tremblay has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Rajiv Kohli
Raymond A. Mason School of Business, William & Mary, Williamsburg, Virginia 23186
8 shared publications - Arturo Castellanos
Raymond A. Mason School of Business, William & Mary, Williamsburg, Virginia 23185
5 shared publications - Thomas Roderick
Flamelit Consulting, Humble, Texas 77396; and Raymond A. Mason School of Business, William and Mary, Williamsburg, Virginia 23185
5 shared publications Arturo Castellanos
4 shared publicationsDebra VanderMeer
Florida Int Univ, Informat Syst & Business Analyt, Miami, FL 33199 USA
3 shared publicationsDonald J. Berndt
Information Systems and Decision Sciences, College of Business, 4202 Fowler Ave., CIS1040, University of South Florida Tampa, FL 33620, United States
3 shared publications
Latest Publications
- 6 November 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
From Data–Model Fit to Model–World Fit: A Framework for Integrating Domain Knowledge into Artificial Intelligence
Machine learning (ML)–based artificial intelligence (AI) systems often perform well in controlled settings but fail when deployed in the real world. These failures stem from a fundamental problem: ML/AI models optimize data–model fit by increasing statistical performance on training data, whereas real-world deployment demands a new paradigm in ML/AI: model–world fit that preserves domain semantics and contextual understanding. We propose a machine learning model–world fit framework that provides both a conceptual structure for understanding how domain knowledge shapes ML/AI systems and a research road map for investigating these relationships. The framework identifies how domain knowledge can be integrated into the ML/AI development process via external knowledge representations, such as data, value, process models, or domain ontologies. Incorporating external knowledge representations can help overcome three types of knowledge deficiencies in AI: know-what, know-how, and know-why. To illustrate the framework, we apply it to a child welfare placement case, a domain in which contextual understanding is critical and statistical accuracy is an insufficient evaluation criterion. Our insights lead to several directions for scholars working at the intersection of machine learning, design science, and knowledge representation. History: Ahmed Abbasi, Senior Editor; Min Zhao, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2023.0031 .
- 6 November 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
From Data–Model Fit to Model–World Fit: A Framework for Integrating Domain Knowledge into Artificial Intelligence
Machine learning (ML)–based artificial intelligence (AI) systems often perform well in controlled settings but fail when deployed in the real world. These failures stem from a fundamental problem: ML/AI models optimize data–model fit by increasing statistical performance on training data, whereas real-world deployment demands a new paradigm in ML/AI: model–world fit that preserves domain semantics and contextual understanding. We propose a machine learning model–world fit framework that provides both a conceptual structure for understanding how domain knowledge shapes ML/AI systems and a research road map for investigating these relationships. The framework identifies how domain knowledge can be integrated into the ML/AI development process via external knowledge representations, such as data, value, process models, or domain ontologies. Incorporating external knowledge representations can help overcome three types of knowledge deficiencies in AI: know-what, know-how, and know-why. To illustrate the framework, we apply it to a child welfare placement case, a domain in which contextual understanding is critical and statistical accuracy is an insufficient evaluation criterion. Our insights lead to several directions for scholars working at the intersection of machine learning, design science, and knowledge representation. History: Ahmed Abbasi, Senior Editor; Min Zhao, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2023.0031 .
- 6 June 2026
- Published by Springer Nature
- p. 375-381
TerrainGrade: An Artifact for Flood Susceptibility Mapping
- 6 June 2026
- Published by Springer Nature
- p. 375-381
TerrainGrade: An Artifact for Flood Susceptibility Mapping
- 8 April 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
When Vulnerability Drives Action: Designing Forward-Looking Frameworks for Disaster Preparedness
Disaster preparedness policies depend on vulnerability indices to guide disaster management. Yet, commonly used tools such as the CDC Social Vulnerability Index and FEMA’s National Risk Index rely largely on static demographic proxies, producing broad vulnerability scores that offer limited insight into the specific needs communities will face during disasters. These approaches can obscure how hazards translate into different forms of harm, such as medical needs during power outages or housing repair needs after storms, and risk embedding structural bias into preparedness decisions. This research shows that vulnerability can be reframed as directly predicting disaster-related needs. We develop the Local Impact Vulnerability Assessment (LIVA), a framework that integrates demographic, housing, socioeconomic, and health indicators with historical disaster outcomes to estimate hazard-specific community needs. Using data from federally declared disasters between 2018 and 2025, LIVA demonstrates substantially stronger alignment with observed FEMA assistance needs across hazards and need categories than existing vulnerability and risk indices. The findings suggest that disaster preparedness policy should advance beyond static indices to tailored predictive planning tools that anticipate how different hazards generate different community needs. By identifying where specific forms of assistance are likely to be required, emergency management organizations can plan, prepare, and improve the equity and effectiveness of disaster response.
- 8 April 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
When Vulnerability Drives Action: Designing Forward-Looking Frameworks for Disaster Preparedness
Disaster preparedness policies depend on vulnerability indices to guide disaster management. Yet, commonly used tools such as the CDC Social Vulnerability Index and FEMA’s National Risk Index rely largely on static demographic proxies, producing broad vulnerability scores that offer limited insight into the specific needs communities will face during disasters. These approaches can obscure how hazards translate into different forms of harm, such as medical needs during power outages or housing repair needs after storms, and risk embedding structural bias into preparedness decisions. This research shows that vulnerability can be reframed as directly predicting disaster-related needs. We develop the Local Impact Vulnerability Assessment (LIVA), a framework that integrates demographic, housing, socioeconomic, and health indicators with historical disaster outcomes to estimate hazard-specific community needs. Using data from federally declared disasters between 2018 and 2025, LIVA demonstrates substantially stronger alignment with observed FEMA assistance needs across hazards and need categories than existing vulnerability and risk indices. The findings suggest that disaster preparedness policy should advance beyond static indices to tailored predictive planning tools that anticipate how different hazards generate different community needs. By identifying where specific forms of assistance are likely to be required, emergency management organizations can plan, prepare, and improve the equity and effectiveness of disaster response.
- 26 March 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning
When the justice system places juveniles into correctional institutions and recidivism rates rise, society bears substantially higher costs compared with when juveniles are placed at home or in community-based alternatives. Research indicates that mental health conditions, rather than public safety concerns, drive decisions to send juveniles to institutions. However, juvenile justice and mental health data are rarely combined for analysis, depriving policymakers of crucial insights to improve juvenile justice outcomes. Identifying the predictive factors of institutional placement is crucial to developing targeted early interventions. We introduce marginal contribution weighting (MCW), a method that compares feature importance across predictive models using Shapley additive explanations (SHAP) values to inform policy decisions. MCW preserves Shapley properties and maintains factorial weighting for marginal contributions, allowing a fair comparison of feature contributions. We apply MCW to a case study in the U.S. state of Texas that integrates mental health and juvenile justice data to predict court-ordered out-of-home placements. We develop a machine learning model using juvenile justice data and then incorporate mental health treatment records to evaluate the impact of new mental health features on accuracy and explainability. By systematically quantifying the impact of mental health features using MCW and SHAP-based analysis, our approach provides a rigorous framework for assessing feature importance across models. This methodology highlights the predictive value of mental health treatment data and ensures fairness in feature comparisons. By identifying key risk factors, our approach provides justice, law enforcement, and correctional policymakers with data-driven insights to support preventive, community-based strategies and mitigate the adverse effects of institutionalization on youth development and long-term outcomes. History: This paper has been accepted by Kaushik Dutta for the Special Issue on the Responsible AI and Data Science for Social Good. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2024.0663 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2024.0663 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 26 March 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning
When the justice system places juveniles into correctional institutions and recidivism rates rise, society bears substantially higher costs compared with when juveniles are placed at home or in community-based alternatives. Research indicates that mental health conditions, rather than public safety concerns, drive decisions to send juveniles to institutions. However, juvenile justice and mental health data are rarely combined for analysis, depriving policymakers of crucial insights to improve juvenile justice outcomes. Identifying the predictive factors of institutional placement is crucial to developing targeted early interventions. We introduce marginal contribution weighting (MCW), a method that compares feature importance across predictive models using Shapley additive explanations (SHAP) values to inform policy decisions. MCW preserves Shapley properties and maintains factorial weighting for marginal contributions, allowing a fair comparison of feature contributions. We apply MCW to a case study in the U.S. state of Texas that integrates mental health and juvenile justice data to predict court-ordered out-of-home placements. We develop a machine learning model using juvenile justice data and then incorporate mental health treatment records to evaluate the impact of new mental health features on accuracy and explainability. By systematically quantifying the impact of mental health features using MCW and SHAP-based analysis, our approach provides a rigorous framework for assessing feature importance across models. This methodology highlights the predictive value of mental health treatment data and ensures fairness in feature comparisons. By identifying key risk factors, our approach provides justice, law enforcement, and correctional policymakers with data-driven insights to support preventive, community-based strategies and mitigate the adverse effects of institutionalization on youth development and long-term outcomes. History: This paper has been accepted by Kaushik Dutta for the Special Issue on the Responsible AI and Data Science for Social Good. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2024.0663 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2024.0663 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 26 March 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning
The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning by Monica Chiarini Tremblay, Arturo Castellanos, Rajiv Kohli, Erin Espinosa, and Thomas Roderick.
- 26 March 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning
The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper Integrating Mental Health and Juvenile Justice Outcomes: A Case Study of Model-Agnostic Interpretable Machine Learning by Monica Chiarini Tremblay, Arturo Castellanos, Rajiv Kohli, Erin Espinosa, and Thomas Roderick.
- Top Cited Papers
- 1 March 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 36  (1) , 1-20
Human-Centric Information Systems Research on the Digital Future of Healthcare
Funding: I. Bardhan is grateful for the financial support provided by The University of Texas at Austin [Charles and Elizabeth Prothro Regents Chair]. E. Oborn is supported in part by the National Institute for Health Research Applied Research Centre Collaborations for Leadership in Applied Health Research and CareWest Midlands [Grant WMCLAHRC-2014-1].
- 1 March 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 36  (1) , 1-20
Top Cited PapersHuman-Centric Information Systems Research on the Digital Future of Healthcare
Funding: I. Bardhan is grateful for the financial support provided by The University of Texas at Austin [Charles and Elizabeth Prothro Regents Chair]. E. Oborn is supported in part by the National Institute for Health Research Applied Research Centre Collaborations for Leadership in Applied Health Research and CareWest Midlands [Grant WMCLAHRC-2014-1].
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Bending the Arc of the Moral Universe: Leveraging Data for Accountable Justice for Transition Age Youth
Justice requires society to protect its children and young adults and ensure they grow up to live productive and fulfilling lives. However, institutions in charge of delivering social justice, also called Human Service Organizations (HSOs), work independently and generally do not collaborate, thus making it difficult for the public to assess their effectiveness. Gathering, analyzing, and disseminating information can help society assess whether HSOs deliver justice. We describe two constructs in delivering justice: reflection and transparency. Our subsequent case study further highlights the emergence of concepts such as incentive alignment, information aggregation, and domain knowledge assimilation. Together, these insights form our Theory of Accountable Justice (TAJ), which elucidates the relationship between these constructs and the delivery of justice.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessBending the Arc of the Moral Universe: Leveraging Data for Accountable Justice for Transition Age Youth
Justice requires society to protect its children and young adults and ensure they grow up to live productive and fulfilling lives. However, institutions in charge of delivering social justice, also called Human Service Organizations (HSOs), work independently and generally do not collaborate, thus making it difficult for the public to assess their effectiveness. Gathering, analyzing, and disseminating information can help society assess whether HSOs deliver justice. We describe two constructs in delivering justice: reflection and transparency. Our subsequent case study further highlights the emergence of concepts such as incentive alignment, information aggregation, and domain knowledge assimilation. Together, these insights form our Theory of Accountable Justice (TAJ), which elucidates the relationship between these constructs and the delivery of justice.
- Top Cited PapersOpen Access
- 1 March 2023
- Published by MIS Quarterly in MIS Quarterly
- Vol. 47  (1) , 423-450
Data is the New Protein: How the Commonwealth of Virginia Built Digital Resilience Muscle and Rebounded from Opioid and COVID Shocks
During shocks, residents and businesses rely upon the government to ensure health, safety, and the continuity of services. The government’s ability to respond depends upon how well it utilizes its data resources and builds digital resilience. Yet governments often fail to integrate data from different agencies to respond effectively to shocks. We conceptualize digital resilience as a dynamic capability (DC). Although the DC framework provides a theoretical basis, it is unclear what actions managers can take to build DC. Through process tracing, we examine how the Commonwealth of Virginia (COVA) built DCs and rebounded from two shocks—the opioid crisis and the COVID-19 pandemic. COVA managers leveraged statewide data assets, built routines to disseminate data, and reconfigured operational capabilities to build three DCs—relationship building, intelligence creation, and value extraction. Data functioned as the “protein” to build the digital resilience “muscle.” We found that the relationship building DC leveraged the operational capabilities of data management, integration, and governance structure to foster data sharing, the intelligence creation DC leveraged analytics, and the value extraction DC converted analytics into cost savings, revenue generation, and new services. Whereas COVA built robust digital resilience by facilitating data sharing, the agencies exploited data assets to develop scalable solutions.
- 1 March 2023
- Published by MIS Quarterly in MIS Quarterly
- Vol. 47  (1) , 423-450
Top Cited PapersOpen AccessData is the New Protein: How the Commonwealth of Virginia Built Digital Resilience Muscle and Rebounded from Opioid and COVID Shocks
During shocks, residents and businesses rely upon the government to ensure health, safety, and the continuity of services. The government’s ability to respond depends upon how well it utilizes its data resources and builds digital resilience. Yet governments often fail to integrate data from different agencies to respond effectively to shocks. We conceptualize digital resilience as a dynamic capability (DC). Although the DC framework provides a theoretical basis, it is unclear what actions managers can take to build DC. Through process tracing, we examine how the Commonwealth of Virginia (COVA) built DCs and rebounded from two shocks—the opioid crisis and the COVID-19 pandemic. COVA managers leveraged statewide data assets, built routines to disseminate data, and reconfigured operational capabilities to build three DCs—relationship building, intelligence creation, and value extraction. Data functioned as the “protein” to build the digital resilience “muscle.” We found that the relationship building DC leveraged the operational capabilities of data management, integration, and governance structure to foster data sharing, the intelligence creation DC leveraged analytics, and the value extraction DC converted analytics into cost savings, revenue generation, and new services. Whereas COVA built robust digital resilience by facilitating data sharing, the agencies exploited data assets to develop scalable solutions.
- 27 July 2021
- Published by Springer Nature
- p. 22-33
Building a Vulnerability Index of Biological and Socioeconomic Risk Factors to Combat COVID-19 Spread
- 27 July 2021
- Published by Springer Nature
- p. 22-33
Building a Vulnerability Index of Biological and Socioeconomic Risk Factors to Combat COVID-19 Spread
- 1 July 2021
- Published by IGI Global Scientific Publishing in Journal of Database Management
- Vol. 32  (3) , 1-28
Missing Data in OLAP Cubes
Online analytical processing (OLAP) engines display aggregated data to help business analysts compare data, observe trends, and make decisions. Issues of data quality and, in particular, issues with missing data impact the quality of the information. Key decision-makers who rely on these data typically make decisions based on what they assume to be all the available data. The authors investigate three approaches to dealing with missing data: 1) ignore missing data, 2) show missing data explicitly (e.g., as unknown data values), and 3) design mitigation algorithms for missing data (e.g., allocate missing data into known value categories). The authors evaluate the approach with focus groups and controlled experiments. When one tries to inform decision-makers using the approaches in the research, the authors find that they often alter their decisions and adjust their decision confidence: individual differences of tolerance for ambiguity and pre-existing omission bias in the decision context influence their decisions.
- 1 July 2021
- Published by IGI Global Scientific Publishing in Journal of Database Management
- Vol. 32  (3) , 1-28
Missing Data in OLAP Cubes
Online analytical processing (OLAP) engines display aggregated data to help business analysts compare data, observe trends, and make decisions. Issues of data quality and, in particular, issues with missing data impact the quality of the information. Key decision-makers who rely on these data typically make decisions based on what they assume to be all the available data. The authors investigate three approaches to dealing with missing data: 1) ignore missing data, 2) show missing data explicitly (e.g., as unknown data values), and 3) design mitigation algorithms for missing data (e.g., allocate missing data into known value categories). The authors evaluate the approach with focus groups and controlled experiments. When one tries to inform decision-makers using the approaches in the research, the authors find that they often alter their decisions and adjust their decision confidence: individual differences of tolerance for ambiguity and pre-existing omission bias in the decision context influence their decisions.