About Me
I am a PhD student in Computer Science at the University of Colorado Boulder, advised by
Prof. Robin Burke.
My research focuses on interpretable and controllable recommender systems, with an emphasis on understanding why recommendation models behave the way they do and how that behavior can be meaningfully steered.
My current work spans concept bottleneck models for sequential recommendation, provider-side transparency, counterfactual and comparative explanations, personalization, and ranking. I am particularly interested in methods that make modern recommendation models easier to inspect, intervene on, and evaluate for different stakeholders.
News
2026
Two papers on provider transparency and pairwise counterfactual explanations accepted to IntRS @ ACM RecSys 2026.
Selected Research
Current and recent projects in recommender systems, interpretability, and controllable machine learning.
IntRS @ ACM RecSys 2026
Why Didn't More People See It? Recommendation Transparency for Providers
Provider-Side Transparency · Exposure · Interpretable Surrogates
Developed an interpretable surrogate framework for provider-side transparency that explains system-wide item exposure using structural recommendation features, achieving R² = 0.83–0.93 across three recommender models and two datasets and revealing model- and domain-specific exposure drivers.
IntRS @ ACM RecSys 2026
Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals
Counterfactual Explanations · Ranking · Comparative Explanations
Developed a comparative counterfactual explanation framework answering “Why was item A ranked above item B?” by identifying influential interactions in user histories whose removal reverses the ranking. Evaluated across three datasets and two recommender models, outperforming established explanation baselines in most settings.
Fairness & Explainable AI
Fairness Auditing Through the Lens of Counterfactual Explanations
Counterfactual Fairness · Qualification · Effort
Developed a counterfactual-based fairness auditing framework to assess whether sensitive groups require unequal effort to achieve favorable model outcomes. Introduced qualification- and effort-based measures and evaluated fairness across multiple classifiers on the Adult Income and Census Income datasets using KL divergence.
ICEE 2023
Review-Aware Hybrid Recommendation
NLP · Hybrid Recommendation · Attention
Developed a hybrid recommender system integrating behavioral signals with CNN-based textual representations and attention mechanisms, achieving up to 22.8% improvement over strong baselines across three datasets.
Publications
2026
Why Didn't More People See It? Recommendation Transparency for Providers
Meysam Varasteh, Robin Burke
IntRS Workshop @ ACM RecSys 2026
Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals
Meysam Varasteh, Veronika Bogina, Noam Koenigstein, Robin Burke
IntRS Workshop @ ACM RecSys 2026
2024
Comparative Explanations for Recommendation: Research Directions
Meysam Varasteh, Elizabeth McKinnie, Amanda Aird, Daniel Acuña, Robin Burke
IntRS Workshop @ ACM RecSys 2024
2023
An Improved Hybrid Recommender System: Integrating Document Context-Based and Behavior-Based Methods
Meysam Varasteh, Mehdi Soleiman Nejad, Hadi Moradi, Mohammad Amin Sadeghi, Ahmad Kalhor
31st International Conference on Electrical Engineering (ICEE 2023)
Fairness Auditing Through the Lens of Counterfactual Explanations
Yashar Deldjoo, Meysam Varasteh, Yara M. Bahram, Marco Antonio Insabato, Tommaso Di Noia
Research work on counterfactual fairness auditing
2022
Designing a Sequential Recommendation System for Heterogeneous Interactions Using Transformers
Mehdi Soleiman Nejad, Meysam Varasteh, Hadi Moradi, Mohammad Amin Sadeghi
arXiv preprint
Experience
2023 – Present
Graduate Research Assistant
University of Colorado Boulder · Boulder, CO
Developing interpretable and controllable recommender systems, including concept-based steering, provider-side transparency, and counterfactual explanations for multi-stakeholder recommendation. Advisor: Prof. Robin Burke.
2023
Graduate Research Assistant
University of Tehran
Developed recommendation methods combining textual reviews with behavioral signals and investigated Transformer-based sequential recommendation.
Education
2023 – 2028
PhD in Computer Science
University of Colorado Boulder
Research: recommender systems, interpretability, and controllable machine learning. Advisor: Prof. Robin Burke.
2018 – 2021
MSc in Electrical and Computer Engineering
University of Tehran
Thesis on hybrid recommender systems integrating document context-based and behavior-based recommendation methods.
Honors & Awards
Jan 2026
Outstanding Teaching Assistant Award from CS Department
Computer Science · University of Colorado Boulder
Jan 2026
WSDM NSF Conference Travel Grant
National Science Foundation (NSF)
Jan 2025
Departmental Summer Research Fellowship
Computer Science · University of Colorado Boulder
Jan 2024
SIGIR Conference Student Travel Grant
SIGIR
Jan 2023
Dean’s and Departmental Excellence Fellowship
Computer Science · University of Colorado Boulder
Jan 2023
Early Career Professional Development Fellowship
Computer Science · University of Colorado Boulder
Technical Skills
Programming
Python, C++, JavaScript
Machine Learning
PyTorch, TensorFlow, Hugging Face, scikit-learn, CUDA, Transformers
Recommender Systems
Ranking, Sequential Recommendation, Personalization, Concept Bottleneck Models, Counterfactual Explanations, Steering
Engineering
Docker, Podman, Git, CI/CD