top of page

Behavior and Demand Modeling

Every day we make decisions about how, when and where to travel. MIT research is aimed at understanding those decisions and operationalizing them to predict travel patterns at the metropolitan scale. By conducting surveys and developing new econometric techniques, MIT is pushing the boundaries of choice theory to model these complex and interconnected decisions. From these foundations, MIT faculty and students have built complete travel demand and land use models that are used by practitioners today.

The research labs and faculty working in this area are shown below. You can see a full listing of the people and labs involved with the MIT Mobility Initiative by navigating to the people page and the labs page.

Researchers

John Attanucci

Lecturer, Research Associate and Manager of the MIT Transit Research Program

Research Interests:

Transportation Planning, Transit Management and Operations, Transit Information and Decision Support Systems

Jonathan How

Richard Cockburn Maclaurin Professor of Aeronautics and Astronautics

Research Interests:

Decision Making Under Uncertainty, Robust Control, Adaptive Control, Model Predictive Control, Machine Learning, Reinforcement Learning

Tom Reynolds

Group Leader, Air Traffic Control and Weather Systems, MIT Lincoln Laboratory

Research Interests:

Air Traffic Management, Aircraft Operations, Aviation Weather Decision Support, Environmental Impacts

Moshe Ben-Akiva

Edmund K. Turner Professor in Civil Engineering

Research Interests:

Transportation Systems Analysis, Intelligent Transportation Systems, Demand Modeling, Econometrics

Ali Jadbabaie

JR East Professor of Engineering

Research Interests:

Network Science, Decision Theory, Cooperative Control Of Multi-Agent Systems, Optimal Control, Motion Coordination

Jinhua Zhao

Professor of Cities and Transportation, Founder and Faculty Director, MIT Mobility Initiative

Research Interests:

Urban Transportation, Travel Behavior, Public Transit, Automated and Shared Mobility, Machine Learning

Rounaq Basu

Postdoctoral Associate, Department of Urban Studies and Planning, MIT

Research Interests:

Sustainable Cities, Equity, Transportation and Mobility, Healthy Communities and Active Living, Urban Information, Technology, and Media and Analytics

Patrick Jaillet

Dugald C. Jackson Professor in EECS, Co-Director of the Operations Research Center

Research Interests:

Online Optimization and Learning, Machine Learning, Decision Making Under Uncertainty

Joseph F. Coughlin


Director, MIT AgeLab

Research Interests:

Consumer Behavior, Behavioral Science, Global Demographics

Chris Knittel

George P. Shultz Professor of Applied Economics

Research Interests:

Economics, Finance and Accounting

Labs

NYC Skyline BW
orc.png

Age Lab

The MIT AgeLab was created in 1999 to invent new ideas and creatively translate technologies into practical solutions that improve people's health and enable them to “do things” throughout the lifespan. Equal to the need for ideas and new technologies is the belief that innovations in how products are designed, services are delivered, or policies are implemented are of critical importance to our quality of life tomorrow.

Director:

NYC Skyline BW
orc.png

City Science Group

Founded in 1985, the MIT Media Lab is one of the world’s leading research and academic organizations. Unconstrained by traditional disciplines, Media Lab designers, engineers, artists, and scientists strive to create technologies and experiences that enable people to understand and transform their lives, communities, and environments. As part of the MIT Media Lab, the City Science research group proposes that new strategies must be found to create the places where people live and work in addition to the mobility systems that connect them, in order to meet the profound challenges of the future.

Director:

NYC Skyline BW
orc.png

Future Urban Mobility at SMART

The Future Urban Mobility IRG's grand challenge is to develop innovative mobility solutions that simultaneously tackle two opposing objectives: To improve the safety, comfort and time associated with transportation, getting individuals and good where they need to be, and when they need to be there; and to reverse the alarming, unsustainable energy and environmental trends associated with transportation, and devise transportation systems that materially enhance sustainability and societal well-being.

Director:

NYC Skyline BW
orc.png

Institute for Data, Systems and Society (IDSS)

The mission of IDSS is to advance education and research in state-of-the-art analytical methods in information and decision systems, statistics and data science, and the social sciences, and to apply these methods to address complex societal challenges in a diverse set of areas such as finance, energy systems, urbanization, social networks, and health.

Director:

Munther Dahleh
NYC Skyline BW
orc.png

Intelligent Transportation Systems Lab

The MIT Intelligent Transportation Systems (ITS) Lab was established in 1990 by Professor Moshe Ben-Akiva. Since its inception, the ITS Lab has conducted numerous studies of transportation systems and developed network modeling and simulation tools. The lab's areas of research include discrete choice and demand modeling techniques, activity-based models, freight transport modeling, and data collection methods for behavioral modeling. Today, lab members are located at MIT's Cambridge campus and its first research center outside of Cambridge: the Singapore-MIT Alliance for Research and Technology (SMART) Centre.

Director:

NYC Skyline BW
orc.png

JTL Urban Mobility Lab

The JTL Urban Mobility Lab at MIT brings behavioral science and transportation technology together to shape travel behavior, design mobility systems, and improve transportation policies. They apply this framework to managing automobile ownership and usage, optimizing public transit planning and operation, promoting active modes of walking and cycling, governing autonomous vehicles and shared mobility services, and designing multimodal urban transportation systems.

Director:

NYC Skyline BW
orc.png

Laboratory for Information and Decision Systems (LIDS)

The Laboratory for Information and Decision Systems (LIDS) at MIT is an interdepartmental research center committed to advancing research and education in the analytical information and decision sciences, specifically in systems and control, communications and networks, and inference and statistical data processing. Throughout its history, LIDS has been at the forefront of major methodological developments in a wide range of fields, including: telecommunications, information technology, the automotive industry, energy, defense, and human health. Building on past innovation and bolstered by a collaborative atmosphere, LIDS members continue to make breakthroughs that cut across traditional boundaries.

Director:

John Tsitsiklis
NYC Skyline BW
orc.png

Quest for Intelligence

MIT Quest addresses two fundamental questions: How does human intelligence work, in engineering terms? And how can we use our understanding of human intelligence to build smarter machines for the benefit of society? As part of our mission, we are developing customized AI tools for non-AI researchers, which could accelerate progress in many fields. We see an opportunity to achieve a deeper understanding of intelligence through the kind of basic research that leads to unexpected breakthroughs. We aspire for our new knowledge and newly built tools to serve the public good, in our nation and around the world.

Director:

NYC Skyline BW
orc.png

Sociotechnical Systems Research Center

The MIT Sociotechnical Systems Research Center (SSRC) is an interdisciplinary research center that focuses on the study of high-impact, complex, sociotechnical systems that shape our world. SSRC brings together faculty, researchers, students and staff from across MIT to study and seek solutions to complex societal challenges that span healthcare, energy, infrastructure networks, environment and international development. Their mission is to develop collaborative, holistic and systems-based approaches that combine knowledge and expertise from engineering and social sciences.

Director:

Courses

Transportation Systems Analysis: Demand and Economics

1.201

Covers the key principles governing transportation systems planning and management. Introduces the microeconomic concepts central to transportation systems. Topics include economic theories of the firm, consumer, and market, demand models, discrete choice analysis, cost models and production functions, and pricing theory. Applications to transportation systems - including congestion pricing, technological change, resource allocation, market structure and regulation, revenue forecasting, public and private transportation finance, and project evaluation - cover urban passenger transportation, freight, maritime, aviation, and intelligent transportation systems.

Demand Modeling

1.202

Theory and application of modeling and statistical methods for analysis and forecasting of demand for facilities, services, and products. Topics include: review of probability and statistics, estimation and testing of linear regression models, theory of individual choice behavior, derivation, estimation, and testing of discrete choice models (including logit, nested logit, GEV, probit, and mixture models), estimation under various sample designs and data collection methods (including revealed and stated preferences), sampling, aggregate forecasting methods, and iterative proportional fitting and related methods. Lectures reinforced with case studies, which require specification, estimation, testing, and analysis of models using data sets from actual applications.

Planning and Design of Airport Systems

1.231

Focuses on current practice, developing trends, and advanced concepts in airport design and planning. Considers economic, environmental, and other trade-offs related to airport location, as well as the impacts of emphasizing "green" measures. Includes an analysis of the effect of airline operations on airports. Topics include demand prediction, determination of airfield capacity, and estimation of levels of congestion; terminal design; the role of airports in the aviation and transportation system; access problems; optimal configuration of air transport networks and implications for airport development; and economics, financing, and institutional aspects. Special attention to international practice and developments.

Behavioral Science and Urban Mobility

11.158/11.478

Examines the behavioral foundation for policy design using urban transportation examples. Introduces multiple frameworks for understanding behavior while contrasting the perspectives of classic economic theory with behavioral economics and social psychology. Suggests corresponding policy interventions and establishes a mapping across behavior, theory, and policy. Presents a spectrum of instruments for positively influencing behavior and improving welfare. Challenges students to critique, design, implement and interpret experiments that nudge travel behavior. Brings behavioral insights to creative design of transport policies that are efficient and equitable as well as simple, consistent, transparent, acceptable, and adaptive to behavioral changes. Students taking graduate version complete additional assignments.

Transportation Research Design

11.250

Seminar dissects ten transportation studies from head to toe to illustrate how research ideas are initiated, framed, analyzed, evidenced, written, presented, criticized, revised, extended, and published, quoted and applied. Students design and execute their own transportation research.

Deep Learning for Urban Mobility

11.S955/11.S198

Explores deep learning (DL) methods for urban mobility applications. Covers concepts of algorithmic prediction, interpretability, causality, and fairness in the context of urban mobility system design and policy making. Topics include demand prediction at both individual and aggregate levels, decision making with and without uncertainty, vehicle and ride sharing, built environment and travel behavior, traffic prediction and control, maps and information provision, and multimodal system design. Students learn intuitions and methods in DNN, CNN, RNN and reinforcement learning, build hands-on models using real-world datasets, and design and implement group projects. At the intersection of machine learning methods and urban mobility applications, the course seeks to reconcile the tension between generic-purpose models and domain-specific knowledge. Furthermore, the course envisions and critically reflects on how machine learning methods shape transportation research and mobility industry, and examines the potentials and pitfalls of their applications in urban mobility business and policies.

bottom of page