About

Ozlem Ergun is a Distinguished Professor and Associate Chair for Graduate Affairs at Northeastern University's College of Engineering. Her research focuses on areas within the College of Engineering, although specific details about her research interests, background, or key contributions are not provided in the page text.

Research topics

• Computer Science
• Sociology
• Business
• Computer Security
• Risk analysis (engineering)
• Marketing
• Artificial Intelligence
• Economics
• Engineering
• Mathematics
• Environmental planning
• Computer network
• Environmental resource management
• Economic growth
• Microeconomics
• Operations research
• Ecology
• Industrial organization
• Knowledge management
• Geography
• Psychology
• Management science
• Human–computer interaction
• Environmental science

Selected publications

• Multimodal Transportation Pricing Alliance Design: Large-Scale Optimization for Rapid Gains

  Transportation Science · 2025-01-23 · 2 citations

  article

  Transit agencies have the opportunity to outsource certain services to established mobility-on-demand (MOD) providers. Such alliances can improve service quality, coverage, and ridership; reduce public sector costs and vehicular emissions; and integrate the passenger experience. To amplify the effectiveness of such alliances, we develop a fare-setting model that jointly optimizes fares and discounts across a multimodal network. We capture commuters’ travel decisions with a discrete choice model, resulting in a large-scale, mixed-integer, nonconvex optimization problem. To solve this challenging problem, we develop a two-stage decomposition with the pricing decisions in the first stage and a mixed-integer linear optimization of fare discounts and passengers’ travel decisions in the second stage. To solve the decomposition, we develop a new solution approach that combines customized coordinate descent, parsimonious second-stage evaluations, and interpolations using special ordered sets. This approach, enhanced by acceleration techniques based on slanted traversal, randomization, and warm-start, significantly outperforms algorithmic benchmarks. Different alliance priorities result in qualitatively different fare designs: flat fares decrease the total vehicle-miles traveled, whereas geographically informed discounts improve passenger happiness. The model responds appropriately to equity-oriented and passenger-centric priorities, improving system utilization and lowering prices for low-income and long-distance commuters. Our profit allocation mechanism improves the outcomes for both types of operators, thus incentivizing profit-oriented MOD operators to adopt transit priorities. Funding: This material is based on work supported by the National Science Foundation [Grants 1122374 and 1750587]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/trsc.2023.0009 .

  PublisherDOI

• Enhancing Cost-Efficiency and Effectiveness in USAID’s Food Aid Supply Chain Operations in Ethiopia

  INFORMS Journal on Applied Analytics · 2025-08-11

  article

  This paper develops a data-driven optimization model of USAID/BHA’s food aid supply chain to evaluate the impact of advance demand information and commodity prepositioning strategies. Using historical data from Ethiopia and a rolling horizon solution approach, the study quantifies trade-offs between cost-efficiency and delivery performance under multiple operational scenarios.

  PublisherDOI

• Multimodal Transportation Pricing Alliance Design: Large-Scale Optimization for Rapid Gains

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• Effects of Timing of Agents’ Reactions in Pharmaceutical Supply Chains under Disruption

  2023-12-10

  article

  Disruptions in the supply chain network can have significant and far-reaching consequences, especially in pharmaceutical supply chains that affect health and financial outcomes and raise equity concerns. To inform strategies that can address this critical global problem, we study disruptions in pharmaceutical supply chains using multiagent simulations. These simulations include decision-theoretic agents with a theory of mind reasoning that allows them to reason about the other agents in the supply chain, including their trustworthiness. The simulations reveal how supplier-buyer interactions have non-local effects which can exacerbate and extend disruption impacts. In addition, a distributor’s focus on its own short-term profit can lower its long-term profit and damage equity in health centers. We also demonstrate how agents adapt to changes in the environment and changes in other agents’ behavior and how in the absence of explicit communication and coordination, the timing of these adaptations inhibits disruption mitigation efforts from transpiring.

  PublisherDOI

• When Should the FDA Inspect Pharmaceutical Manufacturing Facilities to Better Mitigate Drug Shortages?

  arXiv (Cornell University) · 2023-10-23

  preprintOpen accessSenior author

  Drug shortages have been a persistent problem in American healthcare for decades, and the resulting lack of access to necessary drugs has been disastrous to patient health. A majority of these shortages were caused by quality issues related to problems in the manufacturing process. More frequent inspections can reduce quality concerns, but deciding when to inspect is a complex problem; strict regulation enforcement can force low-profit facilities to close due to excessive maintenance costs, while lax enforcement allows for regulation violations to persist, both of which can cause drug shortages. We propose a novel model to assist the FDA in determining when to inspect manufacturing facilities. We formulate this problem as a finite-horizon partially observable Markov decision process (POMDP) based on the classifications the FDA assigns to each facility after inspection, as well two disruptive events: a manufacturing failure occurring or the facility closing for non-mandatory maintenance. We theoretically show that this problem can be reduced to only needing to consider whether or not to inspect immediately, which is independent of the time horizon. We additionally determine the sensitivity of the optimal inspection time on the penalty incurred for an unexpected disruptive event occurring. Our computational study demonstrates a quadratic relationship between the relative difference in average value accumulated between inspecting based on the optimal inspection time produced by our model and inspecting based on the expected time to an unexpected disruptive event, highlighting the importance of allocating more inspection resources to high-risk facilities that produce drugs that highly impact public health. We additionally find that optimal inspection time is more sensitive to changes in the penalty incurred from a disruptive event occurring the longer it has been since the last inspection.

  PublisherOA PDFDOI

• Matching medical staff to long term care facilities to respond to COVID-19 outbreak

  BMC Health Services Research · 2023-06-07 · 3 citations

  articleOpen access

  BACKGROUND: Staff shortage is a long-standing issue in long term care facilities (LTCFs) that worsened with the COVID-19 outbreak. Different states in the US have employed various tools to alleviate this issue in LTCFs. We describe the actions taken by the Commonwealth of Massachusetts to assist LTCFs in addressing the staff shortage issue and their outcomes. Therefore, the main question of this study is how to create a central mechanism to allocate severely limited medical staff to healthcare centers during emergencies. METHODS: For the Commonwealth of Massachusetts, we developed a mathematical programming model to match severely limited available staff with LTCF demand requests submitted through a designed portal. To find feasible matches and prioritize facility needs, we incorporated restrictions and preferences for both sides. For staff, we considered maximum mileage they are willing to travel, available by date, and short- or long-term work preferences. For LTCFs, we considered their demand quantities for different positions and the level of urgency for their demand. As a secondary goal of this study, by using the feedback entries data received from the LTCFs on their matches, we developed statistical models to determine the most salient features that induced the LTCFs to submit feedback. RESULTS: We used the developed portal to complete about 150 matching sessions in 14 months to match staff to LTCFs in Massachusetts. LTCFs provided feedback for 2,542 matches including 2,064 intentions to hire the matched staff during this time. Further analysis indicated that nursing homes and facilities that entered higher levels of demand to the portal were more likely to provide feedback on the matches and facilities that were prioritized in the matching process due to whole facility testing or low staffing levels were less likely to do so. On the staffing side, matches that involved more experienced staff and staff who can work afternoons, evenings, and overnight were more likely to generate feedback from the facility that they were matched to. CONCLUSION: Developing a central matching framework to match medical staff to LTCFs at the time of a public health emergency could be an efficient tool for responding to staffing shortages. Such central approaches that help allocate a severely limited resource efficiently during a public emergency can be developed and used for different resource types, as well as provide crucial demand and supply information in different regions and/or demographics.

  PublisherOA PDFDOI

• Future Themes in the Sharing Economy

  Cambridge University Press eBooks · 2023-03-30 · 1 citations

  book-chapterOpen access

  This chapter provides an overview of five core dimensions that are central to the challenge of optimizing for a just sharing economy: Understanding socioeconomic externalities; pursuing resilience; charting more just and systems-oriented business directions; defining the future of work; and prioritizing access and equity. It highlights the multiple ways in which the analyses throughout the book intersect with these dimensions and argues that each of these dimensions conveys significant information about the values that must be prioritized in the next generation of sharing economy platforms. Finally, the chapter discusses a set of key questions that remain for future research and exploration.

  PublisherOA PDFDOI

• Shared Last Mile Delivery

  Cambridge University Press eBooks · 2023-03-30 · 4 citations

  book-chapterOpen access

  Last mile delivery is the most expensive part of the delivery operations. Especially with the significant growth in e-commerce, last mile delivery operations continue to increase. Since most of the parcels are delivered to urban and suburban areas, the delivery operations have a considerable impact on our lives, by increasing the air and noise pollution and worsening the traffic within cities. The crowdsourcing and sharing economy approaches, such as crowdsourced delivery and shared urban distribution centers, in last mile delivery may reduce these negative externalities. However, since these approaches are relatively new and bring new aspects that were not part of the conventional business models, open questions arise in both business applications and academic research. In this chapter, we provide a brief history of e-commerce and related optimization literature. We introduce several sharing economy business models in last mile delivery and discuss the open problems that might be studied by comparing these business models to the conventional ones.

  PublisherOA PDFDOI

• Multimodal Transportation Pricing Alliance Design: Large-Scale Optimization for Rapid Gains

  arXiv (Cornell University) · 2023-01-09

  preprintOpen access

  Transit agencies have the opportunity to outsource certain services to established Mobility-on-Demand (MOD) providers. Such alliances can improve service quality, coverage, and ridership; reduce public sector costs and vehicular emissions; and integrate the passenger experience. To amplify the effectiveness of such alliances, we develop a fare-setting model that jointly optimizes fares and discounts across a multimodal network. We capture commuters' travel decisions with a discrete choice model, resulting in a large-scale, mixed-integer, non-convex optimization problem. To solve this challenging problem, we develop a two-stage decomposition with the pricing decisions in the first stage and a mixed-integer linear optimization of fare discounts and passengers' travel decisions in the second stage. To solve the decomposition, we develop a new solution approach combining tailored coordinate descent, parsimonious second-stage evaluations, and interpolations using special ordered sets. This approach, enhanced by acceleration techniques based on slanted traversal, randomization and warm-start, significantly outperforms algorithmic benchmarks. Different alliance priorities result in qualitatively different fare designs: flat fares decrease the total vehicle-miles traveled, while geographically-informed discounts improve passenger happiness. The model responds appropriately to equity-oriented and passenger-centric priorities, improving system utilization and lowering prices for low-income and long-distance commuters. Our profit allocation mechanism improves outcomes for both types of operators, thus incentivizing profit-oriented MOD operators to adopt transit priorities.

  PublisherOA PDFDOI

• Thought Bubbles: A Proxy into Players’ Mental Model Development

  2023-04-19 · 4 citations

  preprintOpen access

  Studying mental models has recently received more attention, aiming to understand the cognitive aspects of human-computer interaction. However, there is not enough research on the elicitation of mental models in complex dynamic systems. We present Thought Bubbles as an approach for eliciting mental models and an avenue for understanding players’ mental model development in interactive virtual environments. We demonstrate the use of Thought Bubbles in two experimental studies involving 250 participants playing a supply chain game. In our analyses, we rely on Situation Awareness (SA) levels, including perception, comprehension, and projection, and show how experimental manipulations such as disruptions and information sharing shape players’ mental models and drive their decisions depending on their behavioral profile. Our results provide evidence for the use of thought bubbles in uncovering cognitive aspects of behavior by indicating how disruption location and availability of information affect people’s mental model development and influence their decisions.

  PublisherOA PDFDOI

Recent grants

• Collaborative Proposal: Resource Allocation with Learning in Dynamic and Partially Observable Networks

  NSF · $161k · 2015–2019

• CAREER: Efficient Network Design and Routing Algorithms for Logistics and Communications Networks

  NSF · $400k · 2003–2010

• RAPID: Earthquake Debris Management in Haiti: Data-driven Decision-Support

  NSF · $39k · 2010–2011

• Managing Debris Collection and Disposal Operations

  NSF · $335k · 2010–2014

• RAPID: Collecting Supply, Demand, and Matching Data for Assigning Medical Staff to Long Term Care Facilities During the COVID-19 Pandemic

  NSF · $101k · 2020–2022

Frequent coauthors

• Pınar Keskinocak

  14 shared

• James B. Orlin

  11 shared

• Julie Swann

  North Carolina State University

  10 shared

• Stacy Marsella

  Universidad del Noreste

  9 shared

• Luyi Gui

  University of California, Irvine

  8 shared

• Jacqueline Griffin

  Northeastern University

  8 shared

• Casper Harteveld

  Northeastern University

  8 shared

• David Kaeli

  Northeastern University

  7 shared

Labs

• The Institute for Experiential AIPI