Spiacenti, questo contenuto non ha traduzione nella lingua selezionata. I dati verranno visualizzati in inglese.

Using Real-Time Decision Tools to Improve Distributed Decision-Making Capabilities in High-Magnitude Crisis Situations.

Authors
Moskowitz, Herbert ; Drnevich, Paul ; Ersoy, Okan ; Altinkemer, Kemal ; Chaturvedi, Alok

Multi-organizational collaborative decision making in high-magnitude crisis situations requires real-time information sharing and dynamic modeling for effective response. Information technology (IT) based decision support tools can play a key role in facilitating such effective response. We explore one promising class of decision support tools based on machine learning, known as support vector machines (SVM), which have the capability to dynamically model and analyze decision processes. To examine this capability, we use a case study with a design science approach to evaluate improved decision-making effectiveness of an SVM algorithm in an agent-based simulation experimental environment. Testing and evaluation of real-time decision support tools in simulated environments provides an opportunity to assess their value under various dynamic conditions. Decision making in high-magnitude crisis situations involves multiple different patterns of behavior, requiring the development, application, and evaluation of different models. Therefore, we employ a multistage linear support vector machine (MLSVM) algorithm that permits partitioning decision maker response into behavioral subsets, which can then individually model and examine their diverse patterns of response behavior. The results of our case study indicate that our MLSVM is clearly superior to both single stage SVMs and traditional approaches such as linear and quadratic discriminant analysis for understanding and predicting behavior. We conclude that machine learning algorithms show promise for quickly assessing response strategy behavior and for providing the capability to share information with decision makers in multi-organizational collaborative environments, thus supporting more effective decision making in such contexts. [ABSTRACT FROM AUTHOR]/nCopyright of Decision Sciences is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Codebooks
SLR Criteria
Summary

(i) Analyze decision (choice) performance of responders and (ii) analysis of the MLSVM model with relative and absolute performance and behavior.

SLR Criteria
Summary

Case study, Synthetic environment; train the support vector machines (SVMs) in simulations

Summary

15 explanatory variables (from that, 6 were quantitative and 9 represents background information for each responder e.g. interaction between levels and departments). Response variable is the quarantine strategy (QS) in no intervention (QS1) to moderate (QS3) to extreme (QS5) intervention (quarantine) responses.

Summary

(i) develop the initial design;(ii) develop the MLSVM algorithm,(iii) evaluate and refine the solution by comparing it with other solutions; (iv)

SLR Criteria
Summary

U.S Department of Homeland Security training exercise called measured response (MR) where data streams from both simulation and real-world decision makers to the SVM tool.Survey (135 samples) and simulated Data

SLR Criteria
Summary

Use a design science approach (e.g., Hevner, March, Park, & Ram, 2004; Holmstrom, Ketokivi, & Hameri, 2009) to develop and explore the viability and effectiveness of SVMs  as a potentially more effective real-time component of integrated decision support tools which can anticipate actions that will be taken at different levels in response to a crisis situation; Follow the tradition of grounded business research (Guide & Van Wassenhove, 2007), to explore the ability of SVMs to model, explain, and predict multi-organizational collaborative decision-making behavior and response effectiveness through a case study involving a high-magnitude crisis situation

Summary

Store actions of decision maker in a DSS (decision support system)tools to support group decision makingWhen dealing with human behaviors, particularly in a multi-echelon decision-making situation, standard single stage SVMs did not adequately capture behaviors within and across organizational settings

SLR Criteria
Summary

The MLSVM algorithm was superior to all other available methods in predicting responders’ choices—indicating the high potential value of MLSVM based real-time decision support toolsOur results show that the MLSVM we developed is clearly superior to single stage SVMs in anticipating and understanding behavior 488 Using Real-Time Decision Tools to Improve because one model does not fit all patterns of behaviors

SLR Criteria
Summary

Case study to employ an agent-based synthetic environment to simulate a crisis event, and then use an MLSVM model to examine alternative response strategies to the simulated crisis as it unfolds.Objectives:validate the effectiveness of SVMs (support vector machines) as an automated generic IT–based decision support tool to model and improve the effectiveness of multi-organizational, collaborative decision making in high-magnitude crisis situationsexamine the anticipatory and explanatory effectiveness of a MLSVM (multistage linear SVM) algorithm that would effectively capture different patterns of behavior of decision makers in a multi-organizational setting

 

 

eu Il sito web Portfolio of Solutions è stato inizialmente sviluppato nell'ambito del progetto DRIVER+. Oggi, il servizio è gestito da AIT Austrian Institute of Technology GmbH, a beneficio della gestione europea delle . PoS è approvato e supportato dal Disaster Competence Network Austria (DCNA) così come dai progetti STAMINA e TeamAware H2020.