Daniel Dolk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Daniel Dolk has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Donald J. Kridel
University Blvd
3 shared publications - David Castillo
CNAG-CRG, Centre for Genomic Regulation (CRG), Barcelona Institute of Science and Technology (BIST), Barcelona, Spain
2 shared publications - Donald Kridel
U Missouri St Louis Univ. of Virginia Naval Postgrad School Capital One, Inc
2 shared publications - Alok Chaturvedi
Purdue University
1 shared publication - David Castillo
Early Warning. Inc., Scottsdale, AZ, USA
1 shared publication - Haluk Demirkan
Arizona State University
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by HICSS Conference Office
Unified Explanations in Machine Learning Models: A Perturbation Approach
A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Previous work has uncovered predictive models generating explanations contrasting domain experts, or excessively exploiting bias in data that renders a model useless in highly-regulated settings. These inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.
- 1 January 2023
- Published by HICSS Conference Office
Open AccessUnified Explanations in Machine Learning Models: A Perturbation Approach
A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Previous work has uncovered predictive models generating explanations contrasting domain experts, or excessively exploiting bias in data that renders a model useless in highly-regulated settings. These inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.
- Open Access
- 1 January 2020
- Published by HICSS Conference Office
Model Interpretation and Explainability towards Creating Transparency in Prediction Models
Explainable AI (XAI) has a counterpart in analytical modeling which we refer to as model explainability. We tackle the issue of model explainability in the context of prediction models. We analyze a dataset of loans from a credit card company using the following three steps: execute and compare four different prediction methods, apply the best known explainability techniques in the current literature to the model training sets to identify feature importance (FI) (static case), and finally to cross-check whether the FI set holds up under "what if" prediction scenarios for continuous and categorical variables (dynamic case). We found inconsistency in FI identification between the static and dynamic cases. We summarize the "state of the art" in model explainability and suggest further research to advance the field.
- 1 January 2020
- Published by HICSS Conference Office
Open AccessModel Interpretation and Explainability towards Creating Transparency in Prediction Models
Explainable AI (XAI) has a counterpart in analytical modeling which we refer to as model explainability. We tackle the issue of model explainability in the context of prediction models. We analyze a dataset of loans from a credit card company using the following three steps: execute and compare four different prediction methods, apply the best known explainability techniques in the current literature to the model training sets to identify feature importance (FI) (static case), and finally to cross-check whether the FI set holds up under "what if" prediction scenarios for continuous and categorical variables (dynamic case). We found inconsistency in FI identification between the static and dynamic cases. We summarize the "state of the art" in model explainability and suggest further research to advance the field.
- 22 March 2012
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 11 (1) , 1-11
Analytical, computational and conceptual modeling in service science and systems
- 22 March 2012
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 11 (1) , 1-11
Analytical, computational and conceptual modeling in service science and systems
- 13 December 2011
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 11 (1) , 119-140
Automated self-service modeling: predictive analytics as a service
- 13 December 2011
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 11 (1) , 119-140
Automated self-service modeling: predictive analytics as a service
- 20 October 2005
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 4 (1) , 25-48
Computational experimentations in market and supply-chain co-design: a mixed agent approach
- 20 October 2005
- Published by Springer Nature in Information Systems and e-Business Management
- Vol. 4 (1) , 25-48
Computational experimentations in market and supply-chain co-design: a mixed agent approach
- 1 April 1993
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Interfaces
- Vol. 23 (2) , 3-13
Modeling Telecommunications Demand Analysis
Over the last 20 years, legal and regulatory decisions, culminating in the divestiture of the Bell Operating Companies (BOCs) by American Telephone and Telegraph (AT&T) in 1984, have led to an upsurge in the importance of applied econometrics in the telecommunications industry. Increased attention to demand analysis, or empirical economics, has fostered a commensurate increase in modeling sophistication—both for the analyst and for the underlying modeling component of decision support systems. Whereas (aggregate) pooled regression models were more appropriate for the rate-case environment, (disaggregate) optimization-based models have proved more useful for the marketing orientation. Stand-alone analytical systems are no longer sufficient. The critical transition in organizational perspective reflects a need for integrated modeling environments that offer multiple modeling paradigms, linkage among models, consistent access to data resources, and intelligent support.
- 1 April 1993
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Interfaces
- Vol. 23 (2) , 3-13
Modeling Telecommunications Demand Analysis
Over the last 20 years, legal and regulatory decisions, culminating in the divestiture of the Bell Operating Companies (BOCs) by American Telephone and Telegraph (AT&T) in 1984, have led to an upsurge in the importance of applied econometrics in the telecommunications industry. Increased attention to demand analysis, or empirical economics, has fostered a commensurate increase in modeling sophistication—both for the analyst and for the underlying modeling component of decision support systems. Whereas (aggregate) pooled regression models were more appropriate for the rate-case environment, (disaggregate) optimization-based models have proved more useful for the marketing orientation. Stand-alone analytical systems are no longer sufficient. The critical transition in organizational perspective reflects a need for integrated modeling environments that offer multiple modeling paradigms, linkage among models, consistent access to data resources, and intelligent support.
- 18 December 1991
- Published by Taylor & Francis in Journal of Management Information Systems
- Vol. 8 (3) , 151-169
GOST: An Active Modeling System for Costing and Planning NASA Space Programs
This paper describes an active, or symbiotic, decision support system developed for the National Aeronautics and Space Administration called the Generic Operations Simulation Technique (GOST). GOST combines parametric modeling techniques (regression) with discrete-event simulation to cost and plan future space programs. GOST differs from previous process modeling approaches by providing an “artificially intelligent modeling expert” and an “artificially intelligent domain expert” for assisting the user in developing and analyzing process models. An object oriented knowledge representation system provides the foundation for the GOST environment. A taxonomy of Computer Directed Process Managers, implemented within the representation system, controls the appropriate processes responsible for delivering active modeling support.
- 18 December 1991
- Published by Taylor & Francis in Journal of Management Information Systems
- Vol. 8 (3) , 151-169
GOST: An Active Modeling System for Costing and Planning NASA Space Programs
This paper describes an active, or symbiotic, decision support system developed for the National Aeronautics and Space Administration called the Generic Operations Simulation Technique (GOST). GOST combines parametric modeling techniques (regression) with discrete-event simulation to cost and plan future space programs. GOST differs from previous process modeling approaches by providing an “artificially intelligent modeling expert” and an “artificially intelligent domain expert” for assisting the user in developing and analyzing process models. An object oriented knowledge representation system provides the foundation for the GOST environment. A taxonomy of Computer Directed Process Managers, implemented within the representation system, controls the appropriate processes responsible for delivering active modeling support.