3730 Walnut Street
565 Jon M. Huntsman Hall
Philadelphia, PA 19104
Research Interests: artificial intelligence and computational rationality, decision support systems, evolutionary computation (including genetic algorithms) and metaheuristics for constrained optimization, logic modeling and agent communication languages, text mining
Christine Chou, Steven O. Kimbrough, Frederic H. Murphy, John Sullivan-Fedock, Jason Woodard (Working), On Empirical Validation of Compactness Measures for Electoral Redistricting and its Significance for Applications of Models in the Social Sciences.
Mark Kohler, Niels Feldmann, Steven O. Kimbrough, Hansjoerg Fromm (2014), Service Innovation Analytics: Leveraging Existing Unstructured Data to Assess Service Innovation Capability, International Journal of Information System Modeling and Design, 5 (2), pp. 1-21.
Holger Johann, Margeret Hall, Steven O. Kimbrough, Nicholas Quintus, Christof Weinhardt (Work In Progress), Service District Optimization.
Steven O. Kimbrough Solution Pluralism (And its relevance to KAPSARC).
Yevgeniy Vorobeychik, Steven O. Kimbrough, Howard Kunreuther (2014), A Framework for Computational Strategic Analysis: Applications to Iterated Interdependent Security Games, Computational Economics.
Ram Gopalan, Steven O. Kimbrough, Frederic H. Murphy, Nicholas Quintus (2013), Interfaces, Interfaces. 10.1287/inte.2013.0697
Steven O. Kimbrough Solution Pluralism, Deliberation, and Metaheuristics. Extracting More Value from Optimization Models Part 1: Motivation and Examples.
Description: Presentation at the Metaheuristics International Conference, SIngapore, 5-8 August 2013 http://research.larc.smu.edu.sg/mic2013/
Steven O. Kimbrough Solution Pluralism, Deliberation, and Metaheuristics. Extracting More Value from Optimization Models Part 2: Engineering and Scientific Challenges.
Description: Presentation at Metaheuristics International Conference, Singapore, 5-8 August http://research.larc.smu.edu.sg/mic2013/
Christine Chou, Steven O. Kimbrough, Frederic H. Murphy, John Sullivan-Fedock, Jason Woodard (2013), On Empirical Validation of Compactness Measures for Electoral Redistricting and Its Significance for Application of Models in the Social Sciences, Social Science Computer Review, forthcoming.
Abstract: Use of optimization models in science and policy applications is often problematic because the best available models are very inaccurate representations of the originating problems. Such is the case with electoral districting models, for which there exist no generally accepted measures of compactness, in spite of many proposals and much analytical study. This paper reports on an experimental investigation of subjective judgments of compactness for electoral districts. The experiment draws on a unique database of 116 distinct, legally valid districting plans for the Philadelphia City Council, discovered with evolutionary computation. Subjects in the experiment displayed, in the aggregate, remarkable agreement with several standard measures of compactness, thus providing warrant for use of these measures that has heretofore been unavailable. The exercise also lends support to the underlying methodology on display here, which proposes to use models based on subjective judgments in combination with algorithms that find multiple solutions in order to support application of optimization models in contexts in which they are only very approximate representations.
Steven O. Kimbrough and Frederic H. Murphy (2013), Strategic Bidding of Offer Curves: An Agent-Based Approach to Exploring Supply Curve Equilibria, European Journal Operational Research, in press.
Abstract: We model a market in which suppliers bid step-function offer curves using agent-based modeling. Our model is an abstraction of electricity markets where step-function offer curves are given to an independent system operator that manages the auctions in electricity markets. Positing an elementary and computationally accessible learning model, Probe and Adjust, we present analytic results that characterize both the behavior of the learning model and the properties of step-function equilibria. Thus, we have developed a framework for validating agent-based models prior to using them in situations that are too complicated to be analyzed using traditional economic theory. In addition, we demonstrate computationally that, by using alternative policies, even simple agents can achieve monopoly rewards for themselves by pursuing more industry-oriented strategies. This raises the issue of how participants in oligopolistic markets actually behave.
This course enables students to undertake self-directed study on a topic in Architecture, under the supervision of a faculty member. Students are required to make a proposal for the study to the Department Chair, outlining the subject and method of investigation, and confirming the course supervisor at least two weeks prior to the beginning of the semester.
Departmental permission required
This course is taught with the more descriptive title of "Scripting for Business Analytics." "Business Analytics" refers to modeling and analysis undertaken for purposes of management and supporting decision making. The varieties of techniques and methods are numerous and growing, including simple equational models, constrained optimization models, probabilistic models, visualization, data analysis, and much more. Elementary modeling of this sort can be undertaken in Excel and other spreadsheet programs, but "industrial strength" applications typically use more sophisticated tools, based on scripting languages. Scripting languages are programming languages that are designed to be learned easily and to be used for special purposes, rather than for large-scale application programming. This course focuses on the special purposes associated with business analytics and teaches MATLAB and Python in this context. MATLAB and Python are widely used in practice (both in management and in engineering), as are the business analytic methods covered in the course. Prior programming experience is useful, but not required or presumed for this course.
This course is taught with the more descriptive title of "Agents, Games, and Evolution." It explores applications and fundamentals of strategic behavior. Strategic, or game-theoretic, topics arise throughout the social sciences. The topics include--and we discuss--trust, cooperation, market-related phenomena (including price equilibria and distribution of wealth), norms, conventions, commitment, coalition formation, and negotiation. They also include such applied matters as design of logistics systems, auctions, and markets generally (for example, markets for electric power generation). In addressing these topics we focus on the practical problem of finding effective strategies for agents in strategic situations (or games). Our method of exploration will be experimental: we review and discuss experiments, principally computational experiments, on the behavior of boundedly rational agents in strategic (or game-theoretic) situations. Course work includes readings, discussions in class (organized as a seminar), examinations, and a course project on a topic chosen by the participants.
This course focuses on agent-based computational models in the social sciences, especially in economic, in commercial and in strategic (game-theoretic) contexts. This relatively recent and now rapidly-developing form of computer simulation seeks to explain and predict complex social phenomena "from the ground up", through interactions of comparatively simple agents. The course reviews experimental and theoretical results, and exposes the students to modern development environments for this form of simulation. Students have the opportunity to design and implement agent-based simulations. Programming, however, is not required. This course aims to integrate various topics in agent-based simulation, while developing an appreciation of the problems that are particularly characteristic of this form of simulation so that students will understand its promise and potential.
This course number is currently used for several course types including independent studies, experimental courses and Management & Technology Freshman Seminar. Instructor permission required to enroll in any independent study. Wharton Undergraduate students must also receive approval from the Undergraduate Division to register for independent studies. Section 002 is the Management and Technology Freshman Seminar; instruction permission is not required for this section and is only open to M&T students. For Fall 2020, Section 004 is a new course titled AI, Business, and Society. The course provides a overview of AI and its role in business transformation. The purpose of this course is to improve understanding of AI, discuss the many ways in which AI is being used in the industry, and provide a strategic framework for how to bring AI to the center of digital transformation efforts. In terms of AI overview, we will go over a brief technical overview for students who are not actively immersed in AI (topic covered include Big Data, data warehousing, data-mining, different forms of machine learning, etc). In terms of business applications, we will consider applications of AI in media, Finance, retail, and other industries. Finally, we will consider how AI can be used as a source of competitive advantage. We will conclude with a discussion of ethical challenges and a governance framework for AI. No prior technical background is assumed but some interest in (and exposure to) technology is helpful. Every effort is made to build most of the lectures from the basics.
Models are lenses. They are instruments with which we view, interpret, and give meaning to data. In this course, students will be exposed to and do work in all phases of the modeling life-cycle, including model design and specification, model construction (including data gathering and testing), extraction of information from models during post-solution analysis, and creation of studies that use modeling results to support conclusions for scientific or decision making purposes. In addition, the course will cover critical assessments of fielded models and studies using them. The course will focus broadly on models pertaining to energy and sustainability. This is not only an inherently interesting and important area, but it is very much a public one. In consequence, models, data, and studies using them are publicly and profusely available, as is excellent journalism, which facilitates introductions to specific topics. The course covers selected topics in energy and sustainability. Essential background will be presented as needed, but the course is not a comprehensive overview of energy and sustainability. Modeling in the area of energy and sustainability analytics is rife with uncertainty, and yet decisions must be made. Uncertainty, and how to deal with it in model-based decision making, is an overarching theme of the course. We will focus on energy and sustainability, but that area is hardly unique in being beset with deep and vexing uncertainties. The lessons we learn will generalize. The overall aim of the course is to teach facility with modeling and to use real-world data, models, and studies in doing so. In addition, students with interests in investment or policy analysis in the energy sphere will find the course's subject area focus useful. OIDD 325 is not a prerequisite for this course, but it's helpful if you have already taken it.
Student arranges with a faculty member to pursue a program of reading and writing on a suitable topic.
Taiwan’s government cannot take sole credit for flattening the curve during the early days of the coronavirus pandemic. A case study by Wharton’s Steven O. Kimbrough and Christine Chou of National Dong Hwa University explains how citizens banded together to help. …Read MoreKnowledge at Wharton - 7/27/2020