siml
DESCRIPTION
SIML. A template language for an extensible data driven decision support system to support policy making. Ren Bauer Supervised by Hye-Chung Kum. Outline. What is a decision support system ( DSS )? Active vs. Passive Model vs. Data driven Related Work Design of a DSS - PowerPoint PPT PresentationTRANSCRIPT
SIMLA template language for an
extensible data driven decision support system to support policy
making
Ren BauerSupervised by Hye-Chung Kum
Outline
• What is a decision support system (DSS)?– Active vs. Passive– Model vs. Data driven
• Related Work– Design of a DSS
• SAS/Internet Markup Language– What’s it for?– What’s it look like?– How’s it work?
• Future Work• Questions
What is a DSS?
A computer based system to support decision making [1]
• Database
• Model– Decision context
• User Interface
DSS Taxonomy
• Passive– Provides information, no suggestions
• Active– Provides information and suggestions
• Cooperative– Provides information and suggestions– Takes user feedback to provide improved
suggestions [2]
DSS Taxonomy
• Communication-driven– Support multiple people working on the same task
• Data-driven– Emphasizes access to a time series of data
• Document-driven– Manages unstructured documents
• Knowledge-driven– Provides problem solving expertise stored as facts, rules
• Model-driven– Emphasize access to and manipulation of a model [3]
Related Work: Policy Support• Most systems rely on Models– Bangkok 2010 study [4]
• Long-range Energy Alternatives Planning System
– Positives• Can provide effective suggestions for new policies• Backed up by real math
– Negatives• Lots of input: difficult to apply in new situations• Not applicable to situations which do not fit models
Social workers needed a better way to extract useful information
• Lots of data– Child Welfare– Food and Nutrition Services– Work First
SIML: What’s it for?
SIML: How’s it work?
• The SIML environment includes:– Templates– External files– Compilation engine
• User writes a configuration file– SIML (XML based)– Specify template, dataset, variables, etc.
• User runs compilation engine– Combines configuration and template files– Produces SAS/Internet output file
• User opens output in a browser– Broker generates HTML from output and external files– Browser displays HTML to user
Advantages
• Extensibility– Adding new pages– Generating new views of existing data
• Usability– Systems knowledge– Basic knowledge of SAS
• Further Adaptability– Ease of integration
• User Personalization– Adaptive Menus
• More active support– Integration of policy data
Future WorkWe’ve noticed a recent increase in your work first cases. Ashe county has experienced a sharp decrease since their implementation of policy WF-9000 in 2011Q1.Click here for more details.
Works1. Henk G. Sol et al. (1987). Expert systems and artificial intelligence in decision support systems:
proceedings of the Second Mini Euroconference, Lunteren, The Netherlands, 17–20 November 1985. Springer, 1987. ISBN 9027724377. p.1-2.
2. Haettenschwiler, P. (1999). Neues anwenderfreundliches Konzept der Entscheidungsunterstützung. Gutes Entscheiden in Wirtschaft, Politik und Gesellschaft. Zurich, vdf Hochschulverlag AG: 189-208.
3. Power, D. J. (2002). Decision support systems: concepts and resources for managers. Westport, Conn., Quorum Books.
4. Aumnad Phdungsilp, Integrated energy and carbon modeling with a decision support system: Policy scenarios for low-carbon city development in Bangkok, Energy Policy, Volume 38, Issue 9, September 2010, Pages 4808-4817, ISSN 0301-4215, 10.1016/j.enpol.2009.10.026.
5. H. van Delden, R. Seppelt, R. White, A.J. Jakeman, A methodology for the design and development of integrated models for policy support, Environmental Modelling & Software, Volume 26, Issue 3, March 2011, Pages 266-279, ISSN 1364-8152, 10.1016/j.envsoft.2010.03.021.