About

Andrew A. Li is an Assistant Professor of Operations Research at the Tepper School of Business. His profile is listed under faculty and research at Carnegie Mellon University, indicating his role in academic research and teaching within the business school. The page provides no additional details about his research focus, background, or key contributions.

Research topics

• Medicine
• Internal medicine
• Political Science
• Social psychology
• Environmental health
• Business
• Pathology
• Psychology
• Surgery
• Anesthesia
• Advertising
• Oncology
• Physical therapy

Selected publications

• Comparison of procedure-related complications and success rates between duodenoscopes with disposable end caps and conventional reusable duodenoscopes: a randomized trial

  Surgical Endoscopy · 2026-05-19

  article
  PublisherDOI

• A challenging diagnosis

  Intensive Care Medicine · 2025-01-20 · 1 citations

  article1st authorCorresponding
  PublisherDOI

• Advancing PIC Development Using Machine Learning: from Design to Fabrication to Optical Characterization

  2025-01-01

  article

  This work leverages machine learning to accelerate PIC development in design, fabrication, and optical characterization, enabling efficient design exploration, precise fabrication corrections for structural fidelity, and high-resolution optical metrology to enhance process monitoring.

  PublisherDOI

• Real-Time Personalization with Simple Transformers

  ACM SIGMETRICS Performance Evaluation Review · 2025-08-26

  article

  Real-time personalization has advanced significantly in recent years, with platforms utilizing machine learning models to predict user preferences based on rich behavioral data on each individual user. Traditional approaches usually rely on embedding-based machine learning models to capture user preferences, and then reduce the final real-time optimization task to one of nearest-neighbors, which can be performed extremely fast both theoretically and practically. However, these models struggle to capture some complex user behaviors, which are essential for making accurate recommendations. Transformer-based models, on the other hand, are known for their practical ability to model sequential behaviors, and hence have been intensively used in personalization recently to overcome these limitations. However, optimizing recommendations under transformer-based models is challenging due to their complicated architectures. In this paper, we address this challenge by considering a specific class of transformers, showing its ability to represent complex user preferences, and developing efficient algorithms for real-time personalization.

  PublisherDOI

• The Nonstationary Newsvendor with (and Without) Predictions

  Manufacturing & Service Operations Management · 2025-03-04 · 2 citations

  article

  Problem definition: The classic newsvendor model yields an optimal decision for a “newsvendor” selecting a quantity of inventory under the assumption that the demand is drawn from a known distribution. Motivated by applications such as cloud provisioning and staffing, we consider a setting in which newsvendor-type decisions must be made sequentially in the face of demand drawn from a stochastic process that is both unknown and nonstationary. All prior work on this problem either (a) assumes that the level of nonstationarity is known or (b) imposes additional statistical assumptions that enable accurate predictions of the unknown demand. Our research tackles the Nonstationary Newsvendor without these assumptions both with and without predictions. Methodology/results: In the setting without predictions, we first design a policy that we prove (via matching upper and lower bounds) achieves order-optimal regret; ours is the first policy to accomplish this without being given the level of nonstationarity of the underlying demand. We then, for the first time, introduce a model for generic (i.e., with no statistical assumptions) predictions with arbitrary accuracy and propose a policy that incorporates these predictions without being given their accuracy. We upper bound the regret of this policy and show that it matches the best achievable regret had the accuracy of the predictions been known. Managerial implications: Our findings provide valuable insights on inventory management. Managers can make more informed and effective decisions in dynamic environments, reducing costs and enhancing service levels despite uncertain demand patterns. This study advances understanding of sequential decision-making under uncertainty, offering robust methodologies for practical applications with nonstationary demand. We empirically validate our new policy with experiments based on three real-world data sets containing thousands of time-series, showing that it succeeds in closing approximately 74% of the gap between the best approaches based on nonstationarity and predictions alone. History: This paper was selected as part of the 1RR initiative between the M&SOM Journal and the MSOM Society. This particular paper was part of the 2024 MSOM Service Operations SIG Conference. Funding: L. An and B. Moseley were supported in part by a Google Research Award, an Infor Research Award, a Carnegie Bosch Junior Faculty Chair, NSF [Grants CCF-2121744 and CCF-1845146] and ONR [Grant N000142212702]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2024.1168 .

  PublisherDOI

• Near-Optimal Real-Time Personalization with Simple Transformers

  arXiv (Cornell University) · 2025-03-01

  preprintOpen access

  Real-time personalization has advanced significantly in recent years, with platforms utilizing machine learning models to predict user preferences based on rich behavioral data on each individual user. Traditional approaches usually rely on embedding-based machine learning models to capture user preferences, and then reduce the final optimization task to nearest-neighbors, which can be performed extremely fast. However, these models struggle to capture complex user behaviors, which are essential for making accurate recommendations. Transformer-based models, on the other hand, are known for their practical ability to model sequential behaviors, and hence have been intensively used in personalization recently to overcome these limitations. However, optimizing recommendations under transformer-based models is challenging due to their complicated architectures. In this paper, we address this challenge by considering a specific class of transformers, showing its ability to represent complex user preferences, and developing efficient algorithms for real-time personalization. We focus on a particular set of transformers, called simple transformers, which contain a single self-attention layer. We show that simple transformers are capable of capturing complex user preferences. We then develop an algorithm that enables fast optimization of recommendation tasks based on simple transformers. Our algorithm achieves near-optimal performance in sub-linear time. Finally, we demonstrate the effectiveness of our approach through an empirical study on datasets from Spotify and Trivago. Our experiment results show that (1) simple transformers can model/predict user preferences substantially more accurately than non-transformer models and nearly as accurately as more complex transformers, and (2) our algorithm completes simple-transformer-based recommendation tasks quickly and effectively.

  PublisherOA PDFDOI

• Cycles of inequality in the marketplace: Insights from macro, marketer, and consumer perspectives

  International Journal of Research in Marketing · 2025-09-01 · 1 citations

  articleOpen access

  Seeking inequality via differentiation is a fundamental theme in the marketing literature: consumers derive utility from products that convey socially valued attributes, and marketers target consumers by giving them opportunities to differentiate on socially valued attributes. However, as a large body of evidence shows, inequality can reduce consumer well-being and limit economic growth. In this paper, we take a systemic view of marketplace inequality, examining the interdependence among consumers, marketers, and macro forces in shaping inequality in markets for goods and services. Our broad review of the marketing literature across ten marketing journals and a variety of subdomains within the field (e.g., macromarketing, consumer behavior, marketing strategy, quantitative marketing) suggests that macro forces, marketers, and consumers are all part of a dynamic system in which each contributes to creating, perpetuating, and disrupting cycles of marketplace inequality. By highlighting the process by which inequality can be created, perpetuated, and reduced, we hope to give marketing researchers and practitioners insight into interventions that have the potential to increase consumer well-being and marketer profitability.

  PublisherDOI

• Transcriptional activity generates chromatin motion that drives nuclear blebbing

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-05-21 · 4 citations

  preprintOpen access

  Abstract Abnormal nuclear morphology is a hallmark of human diseases, including cancers and age-related disorders. Previously, maintenance of nuclear morphology and integrity was thought to be solely dependent on a force balance between nuclear mechanical resistance and actin antagonism. However, our recent work revealed that inhibiting RNA polymerase II suppresses nuclear blebbing independent of altering force balance, but the mechanism remains unknown. Through removing cell culture media serum and then adding it back, we can decrease and then restore transcriptional activity. Decreasing transcriptional activity decreases nuclear bleb formation, stability, and rupture while returning transcriptional activity restores nuclear blebbing. These modulations of transcriptional activity did not alter nuclear or actin mechanics. The mean square displacement (MSD) of chromatin domains labeled via transfected Cy3-dNTPs revealed that transcription activity regulates chromatin motion. To determine if increasing chromatin motion is a mechanism to increase nuclear blebbing, we used an established RAD51 inhibitor BO2. We verified BO2 increases chromatin domain motion which resulted in increased nuclear blebbing. We reveal the mechanism by which transcriptional activity drives nuclear blebbing is through chromatin motion. Thus, two hallmarks of human disease are directly linked via transcriptional activity and abnormal nuclear shape. Statement of Significance Nuclear blebs are hallmarks of disease progression that cause dysfunction, but how they are formed remains unanswered. We find that chromatin motion generated by transcriptional activity is essential for both nuclear bleb formation and stability. This was independent of changes in nuclear stiffness or actin antagonism. This finding provides a key advancement in our understanding of nuclear bleb formation. Furthermore, it reveals transcriptional activity as a novel contributor to nuclear blebbing in addition to the paradigm of nuclear shape determined as a force balance between nuclear resistance and actin antagonism.

  PublisherOA PDFDOI

• Do Development Financial Institutions Create Impact through Venture Capital Investments?

  SSRN Electronic Journal · 2025-01-01

  articleOpen access
  PublisherDOI

• Traction methods in endoscopic submucosal dissection: a narrative review

  Annals of Laparoscopic and Endoscopic Surgery · 2025-07-01 · 2 citations

  reviewOpen access
  PublisherDOI

Frequent coauthors

• Tariq Ahmad

  University of Exeter

  52 shared

• Charlie W. Lees

  48 shared

• Nicholas A. Kennedy

  43 shared

• Aijaz Ahmed

  Stanford University

  41 shared

• George Cholankeril

  Baylor College of Medicine

  38 shared

• Miles Parkes

  University of Cambridge

  36 shared

• Donghee Kim

  Stanford University

  34 shared

• Peter M. Irving

  Guy's and St Thomas' NHS Foundation Trust

  32 shared