Data-Driven Modeling of Human Decision Making Processes
Jacob Avery

Citation
Jacob Avery. "Data-Driven Modeling of Human Decision Making Processes". Talk or presentation, 28, May, 2015.

Abstract
Many systems, particularly in transportation, require significant interactions of automation with human decision makers. An understanding of the objective functions that drive these decision processes is required to model these systems. These objective functions can then be used for either for optimizing system performance, or in the development of decision support tools. In this presentation, we present a case study in identifying discrete-choice models of decision-making using operational data. Discrete choice models reflect the relative importance of various attributes that influence the decision by identifying both the structure of the decision process, and the underlying utility function. The proposed approach is used to learn models of the airport runway configuration selection process. Using forecasts of weather and traffic demand, and the current runway configuration, the identified model predicts the runway configuration up to 3 hours in advance. The proposed approach is evaluated using data from New York’s LaGuardia airport.

Electronic downloads

Internal. This publication has been marked by the author for FORCES-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Jacob Avery. <a
  href="http://www.cps-forces.org/pubs/61.html"
  ><i>Data-Driven Modeling of Human Decision Making
  Processes</i></a>, Talk or presentation,  28,
  May, 2015.

• Plain text

  Jacob Avery. "Data-Driven Modeling of Human Decision
  Making Processes". Talk or presentation,  28, May, 2015.

• BibTeX

  @presentation{Avery15_DataDrivenModelingOfHumanDecisionMakingProcesses,
      author = {Jacob Avery},
      title = {Data-Driven Modeling of Human Decision Making
                Processes},
      day = {28},
      month = {May},
      year = {2015},
      abstract = {Many systems, particularly in transportation,
                require significant interactions of automation
                with human decision makers. An understanding of
                the objective functions that drive these decision
                processes is required to model these systems.
                These objective functions can then be used for
                either for optimizing system performance, or in
                the development of decision support tools. In this
                presentation, we present a case study in
                identifying discrete-choice models of
                decision-making using operational data. Discrete
                choice models reflect the relative importance of
                various attributes that influence the decision by
                identifying both the structure of the decision
                process, and the underlying utility function. The
                proposed approach is used to learn models of the
                airport runway configuration selection process.
                Using forecasts of weather and traffic demand, and
                the current runway configuration, the identified
                model predicts the runway configuration up to 3
                hours in advance. The proposed approach is
                evaluated using data from New York’s LaGuardia
                airport.},
      URL = {http://cps-forces.org/pubs/61.html}
  }
  

Posted by Carolyn Winter on 10 Jun 2015.
Groups: forces
For additional information, see the Publications FAQ or contact webmaster at cps-forces org.