About

Negin (Nikki) Golrezaei is the Theresa Seley Associate Professor in Management Science and an Associate Professor of Operations Management at the MIT Sloan School of Management. Her research focuses on advancing the digital economy through algorithmic innovations, market and auction design, dynamic real-time optimization, and data-driven decision-making. Her work aims to create more resilient, equitable, and sustainable digital ecosystems, particularly in areas such as e-commerce, online advertising, and emissions trading systems. In addition to her academic role, Golrezaei has served as a visiting faculty member at Google Research and Meta, collaborating with research and product teams to design, test, and deploy AI-enabled mechanisms for online marketplaces. She holds a BSc and MSc in Electrical Engineering from Sharif University of Technology, Iran, and a PhD in Operations Research from the University of Southern California. Her contributions have been recognized through numerous awards, including the 2025 Best Operations Management Paper Award from INFORMS, the Poets & Quants 2025 Best 40-Under-40 MBA Professors list, the 2021 ONR Young Investigator Award, and the 2018 Google Faculty Research Award. She currently serves as a department editor at Naval Research Logistics and as an associate editor for Operations Research and Production and Operations Management.

Research topics

• Computer Science
• Machine Learning
• Microeconomics
• Economics
• Business
• Econometrics
• Mathematical optimization
• Mathematics
• Operations research

Selected publications

• Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems

  arXiv (Cornell University) · 2026-03-12

  preprintOpen access

  Users on e-commerce platforms can be uncertain about their preferences early in their search. Queries to recommendation systems are frequently ambiguous, incomplete, or weakly specified. Agentic systems are expected to proactively reason, ask clarifying questions, and act on the user's behalf, which makes handling such ambiguity increasingly important. In existing platforms, ambiguity led to excessive interactions and question fatigue or overconfident recommendations prematurely collapsing the search space. We present an Interactive Decision Support System (IDSS) that addresses ambiguous user queries using entropy as a unifying signal. IDSS maintains a dynamically filtered candidate product set and quantifies uncertainty over item attributes using entropy. This uncertainty guides adaptive preference elicitation by selecting follow-up questions that maximize expected information gain. When preferences remain incomplete, IDSS explicitly incorporates residual uncertainty into downstream recommendations through uncertainty-aware ranking and entropy-based diversification, rather than forcing premature resolution. We evaluate IDSS using review-driven simulated users grounded in real user reviews, enabling a controlled study of diverse shopping behaviors. Our evaluation measures both interaction efficiency and recommendation quality. Results show that entropy-guided elicitation reduces unnecessary follow-up questions, while uncertainty-aware ranking and presentation yield more informative, diverse, and transparent recommendation sets under ambiguous intent. These findings demonstrate that entropy-guided reasoning provides an effective foundation for agentic recommendation systems operating under uncertainty.

  PublisherDOI

• Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems

  ArXiv.org · 2026-03-12

  articleOpen access

  Users on e-commerce platforms can be uncertain about their preferences early in their search. Queries to recommendation systems are frequently ambiguous, incomplete, or weakly specified. Agentic systems are expected to proactively reason, ask clarifying questions, and act on the user's behalf, which makes handling such ambiguity increasingly important. In existing platforms, ambiguity led to excessive interactions and question fatigue or overconfident recommendations prematurely collapsing the search space. We present an Interactive Decision Support System (IDSS) that addresses ambiguous user queries using entropy as a unifying signal. IDSS maintains a dynamically filtered candidate product set and quantifies uncertainty over item attributes using entropy. This uncertainty guides adaptive preference elicitation by selecting follow-up questions that maximize expected information gain. When preferences remain incomplete, IDSS explicitly incorporates residual uncertainty into downstream recommendations through uncertainty-aware ranking and entropy-based diversification, rather than forcing premature resolution. We evaluate IDSS using review-driven simulated users grounded in real user reviews, enabling a controlled study of diverse shopping behaviors. Our evaluation measures both interaction efficiency and recommendation quality. Results show that entropy-guided elicitation reduces unnecessary follow-up questions, while uncertainty-aware ranking and presentation yield more informative, diverse, and transparent recommendation sets under ambiguous intent. These findings demonstrate that entropy-guided reasoning provides an effective foundation for agentic recommendation systems operating under uncertainty.

  PublisherOA PDF

• Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems

  Proceedings of the AAAI Symposium Series · 2026-05-18

  articleOpen access

  Users on e-commerce platforms can be uncertain about their preferences early in their search. Queries to recommendation systems are frequently ambiguous, incomplete, or weakly specified. Agentic systems are expected to proactively reason, ask clarifying questions, and act on the user’s behalf, which makes handling such ambiguity increasingly important. In existing platforms, ambiguity led to excessive interactions and question fatigue or overconfident recommendations prematurely collapsing the search space. We present an Interactive Decision Support System (IDSS) that addresses ambiguous user queries using entropy as a unifying signal. IDSS maintains a dynamically filtered candidate product set and quantifies uncertainty over item attributes using entropy. This uncertainty guides adaptive preference elicitation by selecting follow-up questions that maximize expected information gain. When preferences remain incomplete, IDSS explicitly incorporates residual uncertainty into downstream recommendations through uncertainty-aware ranking and entropy-based diversification, rather than forcing premature resolution. We evaluate IDSS using review-driven simulated users grounded in real user reviews, enabling a controlled study of diverse shopping behaviors. Our evaluation measures both interaction efficiency and recommendation quality. Results show that entropy-guided elicitation reduces unnecessary follow-up questions, while uncertainty-aware ranking and presentation yield more informative, diverse, and transparent recommendation sets under ambiguous intent. These findings demonstrate that entropy-guided reasoning provides an effective foundation for agentic recommendation systems operating under uncertainty.

  PublisherOA PDFDOI

• Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access1st authorCorresponding
  PublisherDOI

• The Contest Behind the Feed: Optimal Contest for Recommender Systems

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access1st authorCorresponding
  PublisherDOI

• Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints

  ArXiv.org · 2025-07-13

  preprintOpen access

  Motivated by applications such as cloud platforms allocating GPUs to users or governments deploying mobile health units across competing regions, we study the dynamic allocation of a reusable resource to strategic agents with private valuations. Our objective is to simultaneously (i) maximize social welfare, (ii) satisfy multi-dimensional long-term cost constraints, and (iii) incentivize truthful reporting. We begin by numerically evaluating primal-dual methods widely used in constrained online optimization and find them to be highly fragile in strategic settings -- agents can easily manipulate their reports to distort future dual updates for future gain. To address this vulnerability, we develop an incentive-aware framework that makes primal-dual methods robust to strategic behavior. Our design combines epoch-based lazy updates -- where dual variables remain fixed within each epoch -- with randomized exploration rounds that extract approximately truthful signals for learning. Leveraging carefully designed online learning subroutines that can be of independent interest for dual updates, our mechanism achieves $\tilde{\mathcal{O}}(\sqrt{T})$ social welfare regret, satisfies all cost constraints, and ensures incentive alignment. This matches the performance of non-strategic allocation approaches while being robust to strategic agents.

  PublisherOA PDFDOI

• Learning in Repeated Multi-Unit Pay-As-Bid Auctions

  SSRN Electronic Journal · 2025-01-01 · 1 citations

  articleOpen accessSenior author
  PublisherDOI

• Individual Welfare Guarantees in the Autobidding World with Machine-learned Advice

  2024-05-08 · 4 citations

  article

  Online advertising channels commonly focus on maximizing total advertiser welfare to enhance channel health, and previous literature has studied augmenting ad auctions with machine learning predictions on advertiser values (also known asmachine-learned advice ) to improve total welfare. Yet, such improvements could come at the cost of individual bidders' welfare and do not shed light on how particular advertiser bidding strategies impact welfare. Motivated by this, we present an analysis on an individual bidder's welfare loss in the autobidding world for auctions with and without machine-learned advice, and also uncover how advertiser strategies relate to such losses. In particular, we demonstrate how ad platforms can utilize ML advice to improve welfare guarantee on the aggregate and individual bidder level by setting ML advice as personalized reserve prices when the platform consists ofautobidders who maximize value while respecting a return on ad spend (ROAS) constraint. Under parallel VCG auctions with such ML advice-based reserves, we present a worst-case welfare lower-bound guarantee for an individual autobidder, and show that the lower-bound guarantee is positively correlated with ML advice quality as well as the scale of bids induced by the autobidder's bidding strategies. Further, we show that no truthful, and possibly randomized mechanism with anonymous allocations can achieve universally better individual welfare guarantees than VCG, in the presence of personalized reserves based on ML-advice of equal quality. Moreover, we extend our individual welfare guarantee results to generalized first price (GFP) and generalized second price (GSP) auctions. Finally, we present numerical studies using semi-synthetic data derived from ad auction logs of a search ad platform to showcase improvements in individual welfare when setting personalized reserve prices with ML-advice.

  PublisherDOI

• Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions

  arXiv (Cornell University) · 2024-06-06

  preprintOpen access1st authorCorresponding

  We study the bidding problem in repeated uniform price multi-unit auctions from the perspective of a value-maximizing buyer. The buyer aims to maximize their cumulative value over $T$ rounds while adhering to per-round return-on-investment (RoI) constraints in a strategic (or adversarial) environment. Using an $m$-uniform bidding format, the buyer submits $m$ bid-quantity pairs $(b_i, q_i)$ to demand $q_i$ units at bid $b_i$, with $m \ll M$ in practice, where $M$ denotes the maximum demand of the buyer. We introduce the notion of safe bidding strategies as those that satisfy the RoI constraints irrespective of competing bids. Despite the stringent requirement, we show that these strategies satisfy a mild no-overbidding condition, depend only on the valuation curve of the bidder, and the bidder can focus on a finite subset without loss of generality. Though the subset size is $O(M^m)$, we design a polynomial-time learning algorithm that achieves sublinear regret, both in full-information and bandit settings, relative to the hindsight-optimal safe strategy. We assess the robustness of safe strategies against the hindsight-optimal strategy from a richer class. We define the richness ratio $α\in (0,1]$ as the minimum ratio of the value of the optimal safe strategy to that of the optimal strategy from richer class and construct hard instances showing the tightness of $α$. Our algorithm achieves $α$-approximate sublinear regret against these stronger benchmarks. Simulations on semi-synthetic auction data show that empirical richness ratios significantly outperform the theoretical worst-case bounds. The proposed safe strategies and learning algorithm extend naturally to more nuanced buyer and competitor models.

  PublisherOA PDFDOI

• Learning in Repeated Multiunit Pay-as-Bid Auctions

  Manufacturing & Service Operations Management · 2024-12-12 · 4 citations

  articleSenior author

  Problem definition: Motivated by carbon emissions trading schemes (ETSs), Treasury auctions, procurement auctions, and wholesale electricity markets, which all involve the auctioning of homogeneous multiple units, we consider the problem of learning how to bid in repeated multiunit pay-as-bid (PAB) auctions. In each of these auctions, a large number of (identical) items are to be allocated to the largest submitted bids, where the price of each of the winning bids is equal to the bid itself. In this work, we study the problem of optimizing bidding strategies from the perspective of a single bidder. Methodology/results: Effective bidding in PAB auctions is complex due to the combinatorial nature of the action space. We show that a utility decoupling trick enables a polynomial time algorithm to solve the offline problem where competing bids are known in advance. Leveraging this structure, we design efficient algorithms for the online problem under both full information and bandit feedback settings that achieve an upper bound on regret of [Formula: see text] and [Formula: see text], respectively, where M is the number of units demanded by the bidder, and T is the total number of auctions. We accompany these results with a regret lower bound of [Formula: see text] for the full information setting and [Formula: see text] for the bandit setting. We also present additional findings on the characterization of PAB equilibria. Managerial implications: Although the Nash equilibria of PAB auctions possess nice properties such as winning bid uniformity and high welfare and revenue, they are not guaranteed under no-regret learning dynamics. Nevertheless, our simulations suggest that these properties hold anyways, regardless of Nash equilibrium existence. Compared with its uniform price counterpart, the PAB dynamics converge faster and achieve higher revenue, making PAB appealing whenever revenue holds significant social value—for example, ETSs and Treasury auctions. Funding: R. Galgana and N. Golrezaei were supported in part by the Young Investigator Program Award from the Office of Naval Research [Grant N00014-21-1-2776] and the Massachusetts Institute of Technology Research Support Award. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0403 .

  PublisherDOI

Frequent coauthors

• Alexandros G. Dimakis

  30 shared

• Andreas F. Molisch

  30 shared

• Hamid Nazerzadeh

  University of Southern California

  24 shared

• Vahab Mirrokni

  20 shared

• Ramandeep S. Randhawa

  University of Southern California

  18 shared

• Giuseppe Caire

  Technische Universität Berlin

  16 shared

• Renato Paes Leme

  13 shared

• Patrick Jaillet

  Massachusetts Institute of Technology

  13 shared

Labs

• MIT SloanPI

Education

• Ph.D., Data Sciences and Operations, Marshall School of Business

  University of Southern California

  2017

Awards & honors

• 2025 Best OM Paper Award from Operations Research
• Best 40-Under-40 MBA Professors (2025) by Poets & Quants
• 2021 ONR Young Investigator Award
• 2018 Google Faculty Research Award
• 2017 George B. Dantzig Dissertation Award