About

Alexander Tuzhilin is a faculty member associated with the Learning Science Lab at NYU Stern. The lab is a team of creatives, educators, designers, and technologists who collaborate with faculty to build meaningful learning environments and create engaging, interactive courses to advance business school education. Tuzhilin's work involves partnering with faculty to develop innovative learning experiences, integrating technology into teaching, and enhancing educational methods through research and practical applications. His contributions support the lab's mission to improve learning outcomes by leveraging technology and design principles in business education.

Research topics

• Artificial Intelligence
• Machine Learning
• Information Retrieval
• Computer Science
• Data Mining
• Data science
• Mathematics

Selected publications

• Workshop on Context-Aware Recommender Systems

  2025-09-06

  article
  PublisherDOI

• Deep Multi-Objective Multi-Stakeholder Recommendations in the Media Industry

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems

  MIS Quarterly · 2025-11-18 · 2 citations

  preprintOpen accessSenior author

  Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are heterogeneous across different consumers and dynamically fluctuate according to different contexts, resulting in a Pareto-frontier in the result of recommendations, where the improvement of any objective comes at the cost of others. Existing multi-objective recommender systems do not systematically consider such dynamic relationships; instead, they balance between these objectives in a static and uniform manner, resulting in only suboptimal recommendation performance. In this paper, we propose a Deep Pareto Reinforcement Learning (DeepPRL) method, where we (1) comprehensively model the complex relationships between multiple recommendation objectives; (2) effectively capture personalized and contextual consumer preferences for each objective; (3) optimize both the short-term and the long-term recommendation performance. As a result, our method achieves significant Pareto-dominance over the state-of-the-art baselines across four offline experiments. Furthermore, we conducted a controlled experiment on Alibaba's video streaming platform, where our method simultaneously improved three conflicting business objectives significantly over the latest production system, demonstrating its tangible economic impact in practice.

  PublisherOA PDFDOI

• SENTRA: Selected-Next-Token Transformer for LLM Text Detection

  2025-01-01

  articleOpen access

  LLMs are becoming increasingly capable and widespread.Consequently, the potential and reality of their misuse is also growing.In this work, we address the problem of detecting LLM-generated text that is not explicitly declared as such.We present a novel, generalpurpose, and supervised LLM text detector, SElected-Next-Token tRAnsformer (SENTRA).SENTRA is a Transformer-based encoder leveraging selected-next-token-probability sequences and utilizing contrastive pre-training on large amounts of unlabeled data.Our experiments on three popular public datasets across 24 domains of text demonstrate SENTRA is a general-purpose classifier that significantly outperforms popular baselines in the out-ofdomain setting.

  PublisherOA PDFDOI

• Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems

  MIS Quarterly · 2025-11-18

  articleSenior author

  Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are heterogeneous across different consumers and dynamically fluctuate according to different contexts, resulting in a Pareto-frontier in the result of recommendations, where the improvement of any objective comes at the cost of others. Existing multi-objective recommender systems do not systematically consider such dynamic relationships; instead, they balance between these objectives in a static and uniform manner, resulting in only suboptimal recommendation performance. In this paper, we propose a Deep Pareto Reinforcement Learning (DeepPRL) method, where we (1) comprehensively model the complex relationships between multiple recommendation objectives; (2) effectively capture personalized and contextual consumer preferences for each objective; (3) optimize both the short-term and the long-term recommendation performance. As a result, our method achieves significant Pareto-dominance over the state-of-the-art baselines across four offline experiments. Furthermore, we conducted a controlled experiment on Alibaba's video streaming platform, where our method simultaneously improved three conflicting business objectives significantly over the latest production system, demonstrating its tangible economic impact in practice.

  PublisherDOI

• Physicochemical Studies of the Decomposition of Mineral Aluminum-Containing Raw Materials by Acidic Methods

  Russian Metallurgy (Metally) · 2025-01-01

  article

  Abstract—The chemical and mineral compositions of the Kanash clay and sands from the Chuvash deposit are studied. The results of search for the decomposition of the Kanash clays by sulfuric and hydrochloric acids are presented for the further use of the prepared solutions as coagulants for the purification of drinking and waste waters. The preliminarily calcined clay is subjected to leaching and sulfating roasting followed by water leaching.

  PublisherDOI

• A Dynamical System Framework for Exploring Consumer Trajectories in Recommender System

  SSRN Electronic Journal · 2024-01-01 · 2 citations

  articleOpen accessSenior author
  PublisherDOI

• HyperCARS: Using Hyperbolic Embeddings for Generating Hierarchical Contextual Situations in Context-Aware Recommender Systems

  Information Systems Research · 2024-07-08 · 9 citations

  article

  Contextual situations, such as having dinner at a restaurant on Friday with the spouse, became a useful mechanism to represent context in context-aware recommender systems (CARS). Prior research has shown important advantages of using latent embedding representation approaches to model contextual information in the Euclidean space leading to better recommendations. However, these traditional approaches have major challenges with the construction of proper embeddings of hierarchical structures of contextual information, as well as with interpretations of the obtained representations. To address these problems, we propose the HyperCARS method that models hierarchical contextual situations in the latent hyperbolic space. HyperCARS combines hyperbolic embeddings with hierarchical clustering to construct contextual situations, which allows loose coupling of the contextual modeling component with recommendation algorithms and, therefore, provides flexibility to use a broad range of previously developed recommendation algorithms. We demonstrate empirically that HyperCARS better captures and interprets hierarchical contextual representations, leading to better context-aware recommendations. Because hyperbolic embeddings can also be used in many other applications besides CARS, we also propose the latent embeddings representation framework that systematically classifies prior work on embeddings and identifies novel research streams for hyperbolic embeddings across information systems applications.

  PublisherDOI

• Workshop on Context-Aware Recommender Systems (CARS) 2024

  2024-10-08 · 21 citations

  articleOpen access

  Contextual information has been widely recognized as an important modeling dimension in social sciences and in computing. In particular, the role of context has been recognized in enhancing recommendation results and retrieval performance. While a substantial amount of existing research has focused on context-aware recommender systems (CARS), many interesting problems remain under-explored. The CARS 2024 workshop provides a venue for presenting and discussing the important features of the next generation of CARS and application domains that may require the use of novel types of contextual information and cope with their dynamic properties in group recommendations and in online environments.

  PublisherOA PDFDOI

• Does the Long Tail of Context Exist and Matter? The Case of Dialogue-based Recommender Systems

  2024-06-22 · 1 citations

  articleOpen accessSenior author

  Context has been an important topic in recommender systems over the past two decades. Most of the prior CARS papers manually selected and considered only a few crucial contextual variables in an application, such as time, location, and company of a person. This prior work demonstrated significant recommendation performance improvements when various CARS-based methods have been deployed in numerous applications. In this paper, we study “context-rich” applications dealing with a large variety of different types of contexts. We demonstrate that supporting only a few of the most important contextual variables that could be manually identified, although useful, is not sufficient. In particular, we develop an approach to extract a large number of contextual variables for the dialogue-based recommender systems. In our study, we processed dialogues of bank managers with their clients and managed to identify over two hundred types of contextual variables forming the Long Tail of Context (LTC). We empirically demonstrate that LTC matters, and using all these contextual variables from the Long Tail leads to better recommendation performance.

  PublisherOA PDFDOI

Recent grants

• EAGER: Collaborative Research: Sequential Recommender Systems in Mobile and Pervasive Environments

  NSF · $75k · 2012–2014

Frequent coauthors

• Gediminas Adomavičius

  49 shared

• Konstantin Bauman

  Temple University

  20 shared

• Moshe Unger

  College of Management Academic Studies

  16 shared

• Bamshad Mobasher

  16 shared

• Michele Gorgoglione

  Polytechnic University of Bari

  14 shared

• James Clifford

  14 shared

• Pan Li

  Case Western Reserve University

  13 shared

• Balaji Padmanabhan

  13 shared