Home Research Publications Teaching Data Mining Lab


Kourosh Davoudi

Kourosh Davoudi

  • Associate Professor of Computer Science

  • Faculty of Science, Ontario Tech University

  • Office: SCI 4140
  • Phone: (905) 721-8668 x 2779
  • Email: heidar.davoudi at ontariotechu dot ca

My name is Heidar (aka Kourosh) Davoudi and I am an Associate Professor of Computer Science at Ontario Tech University. I received my PhD in Computer Science with focus on Machine Learning and Data Mining from York University. I was a postdoctoral research fellow in the Department of Management Sciences at University of Waterloo before joining Ontario Tech in 2019.

Currently, I am looking for highly motivated and hard-working graduate students (PhD, MSc). If you are interested in studying with me in the areas of Natural Language Processing and Machine Learning, please email me your most recent CV, and relevant skills. For more information, visit the Data Mining Lab.


Research Interests

A mechanical agent explores a database and discovers knowledge through a feedback loop

Agentic Data Mining

Agentic Data Mining explores how AI agents can plan, carry out, and refine data analysis through interaction with data, tools, and people. We investigate methods that combine language models, reasoning, and adaptive decision-making to discover patterns and turn them into useful knowledge. Our focus is on building reliable agents that can explain their findings, recognize uncertainty, and support human oversight throughout the discovery process.

Research interest

Neural-network agent and bright ivory environment tiles connected by an action and reward feedback loop

Deep and Reinforcement Learning

Deep and Reinforcement Learning explores how intelligent systems learn useful representations from data and develop decision-making strategies through experience. We investigate methods that combine deep neural networks with reward-driven learning to address complex tasks and adapt to changing environments. Our focus is on improving learning efficiency, robustness, and generalization, while understanding how model design and reward structures influence behaviour.

Research interest

Ivory language tokens with bronze attention connections leading to a contextual meaning node

Natural Language Processing

Natural Language Processing explores how intelligent systems understand, generate, and reason with human language. We investigate methods that use language models and structured knowledge to support question generation, question answering, and information discovery. Our focus is on evaluating and improving the factual accuracy, reliability, and contextual understanding of these systems, with particular attention to hallucination, uncertainty, and trustworthy use.

Research interest

Human and robotic hands jointly supporting a bronze and ivory knowledge network with an amber insight gem

Human-AI Collaboration

Human–AI Collaboration explores how people and intelligent systems can work together to solve problems and make informed decisions. We investigate methods that combine human expertise and judgement with AI capabilities, allowing people to guide, question, and refine system outputs. Our focus is on designing interactions that support transparency, appropriate trust, and meaningful human oversight, while evaluating when AI assistance improves outcomes and when it should defer to people.

Research interest

Publications

Journals

2025

  1. M. Zihayat, A. Ayanso, H. Davoudi, Mehdi Kargar, N. Mengesha, Attrition Risk Modeling during a Customer’s Journey: A Predictive Analytics Approach, Journal of Marketing Analytics, 2025.

  2. S. Bakos, H. Davoudi, Searching for the Best Student Architecture in a Knowledge Distillation Framework, Knowledge-Based Systems (KBS), Vol. 328, 2025.

2024

  1. G. Babanejaddehaki, A. An, H. Davoudi, Ontology-Based Data Collection for a Hybrid Outbreak Detection Method Using Social Media, IEEE Transactions on NanoBioscience, 23(4), 2024.

  2. M. Rumman, H. Davoudi, M. Ebrahimi, Enhancing Parkinson's Disease Diagnosis through Synthetic Image Augmentation and Deep Learning Model Evaluation, Journal of Computational Vision and Imaging Systems, Vol. 10, 2024.

  3. N. Babanejad, H. Davoudi, A. Agrawal, A. An, M. Papagelis, The Role of Preprocessing for Word Representation Learning in Affective Tasks, IEEE Transactions on Affective Computing, 15(1), pp. 254-272, 2024.

2023

  1. P. D. Nagy, M. A. Najafabadi, H. Davoudi, A Survey on Code Representation, World Scientific Annual Review of Artificial Intelligence (WSARAI), volume 1, 2023.

2021

  1. M. Zihayat, A. Ayanso, H. Davoudi, Mehdi Kargar, N. Mengesha, Leveraging Non-Respondent Data in Customer Satisfaction Modeling, Journal of Business Research, Volume 135, October, 2021.

2020

  1. S. Bryson, H. Davoudi, L. Golab, M. Kargar, Y. Lytvyn, P. Mierzejewski, J. Szlichta, M. Zihayat, Robust Keyword Search in Large Attributed Graphs, Information Retrieval Journal (IRJ), 23(5), 2020.

  2. H. Davoudi, A. An, M. Zihayat, G. Edall, Paywall Policy Learning in Digital News Media, IEEE Transactions on Knowledge and Data Engineering (TKDE), 33(10), 2020.

2019

  1. M. Zihayat, A. Ayanso, X. Zhao, H. Davoudi, A. An, A Utility-Based News Recommendation System, Decision Support Systems, 117, 14 - 27, 2019.

2017

  1. H. Davoudi, M. Zihayat, A. An, Mining Significant High Utility Gene Regulation Sequential Patterns, Journal of BMC Systems Biology, 11(6): 109, 2017.

2016

  1. E. Delpisheh, A. An, H. Davoudi, E. G. Boroujerdi, Time-Aware Topic Based Recommender System, Big Data and Information Analytics, 1(2), 2016.

Conferences

2026

  1. Z. Sun, A. Neshati, H. Davoudi, CTATutor: From Instructor-Guided Computational Thinking Blueprints to Adaptive Algorithm Tutoring, The ACM Symposium on User Interface Software and Technology (UIST), Detroit, United States, November, 2026.

  2. Y. A. Basti, Z. Sun, H. Davoudi, A. Neshati, CiteLen: In-Situ Multi-Lens Citation Analysis for Scholarly Reading, The ACM Symposium on User Interface Software and Technology (UIST), Detroit, United States, November, 2026.

  3. S. Sarkar, Y. A. Basti, H. Davoudi, A. Neshati, CoRead: Using Implicit Behavioural Signals for Mixed-Initiative AI Support in Collaborative Academic Reading, 28th ACM International Conference on Multimodal Interaction (ICMI), Napoli, Italy, October, 2026.

  4. S. Bakos, H. Davoudi, A. An, A Pre-Generation Epistemic Routing Axis in Language Models, The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, October, 2026.

  5. M. Goyani, H. Davoudi, M. Ebrahimi, Quasimetric Decision Transformers: Enhancing Goal-Conditioned Reinforcement Learning with Structured Distance Guidance, The 2026 IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria, June, 2026.

  6. M. Rumman, H. Davoudi, M. Ebrahimi, Uncertainty-Aware Fusion of Foundation and Task-Specific Models for Cardiac MRI Segmentation, SPIE Medical Imaging 2026 – Computer-Aided Diagnosis, Vancouver, Canada, February, 2026.

2025

  1. S. Bakos, C. Xing, H. Davoudi, A. An, R. DiCarlantonio, Generating Spatial Knowledge Graphs from Automotive Diagrams for Question Answering, The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Suzhou, China, November 4–9, 2025.

  2. N. Beyranvand, H. Dastmalchi, A. An, H. Davoudi, W. Chan, R. DiCarlantonio, GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems, The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Suzhou, China, November 4–9, 2025.

  3. Y. A. Basti, H. Davoudi, A. Neshati, CitePeek: Contextual Citation Exploration within Research Papers, Proceedings of the 7th ACM Conference on Conversational User Interfaces (ACM CUI), Waterloo, ON, Canada, July 8–10, 2025.

  4. S. Sarker, C. C. Garcia, P. CK Hung, H. Davoudi, A. Neshati, PaperPal: An AI-Powered Platform for Collaborative Reading and Discussion, Proceedings of the 7th ACM Conference on Conversational User Interfaces (ACM CUI), Waterloo, ON, Canada, July 8–10, 2025.

  5. S. Abbasi, A. An, H. Davoudi, R. Di Carlantonio, G. Farmaner, Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders, The 31st International Conference on Computational Linguistics (COLING 2025), Abu Dhabi, UAE, January 19–24, 2025.

2024

  1. S. Bakos, P. Madani, H. Davoudi, Noise as a Double-Edged Sword: Reinforcement Learning Exploits Randomized Defenses in Neural Networks, 2024 IEEE 6th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), Washington, DC, USA, October 28–31, 2024.

  2. J. Fletcher, N. Dehnen, S. N. Tayarani Bathaie, A. An, H. Davoudi, R. Di Carlantonio, G. Farmaner, Generating Vehicular Icon Descriptions and Indications Using Large Vision-Language Models, 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, Florida, November 12–16, 2024.

2023

  1. M. Abdollahi, H. Davoudi, M. Ebrahimi, Combined Medical Image, Super-Resolution and Modality Translation Using GAN Transformer-Based Model, 2023 International Conference on Computational Science and Computational Intelligence, IEEE, Las Vegas, NV, USA, December 13–15, 2023.

  2. T. Balasuntharam, H. Davoudi, M. Ebrahimi, Preferential Proximal Policy Optimization, 2023 International Conference on Machine Learning and Applications (ICMLA 2023), Jacksonville, FL, USA, December 15–17, 2023.

  3. W. Chan, A. An, H. Davoudi, A Case Study on ChatGPT Question Generation, 2023 IEEE International Conference on Big Data (IEEE Big Data 2023), Sorrento, Italy, December 15–18, 2023.

  4. G. Babanejaddehaki, A. An, H. Davoudi, A Hybrid Outbreak Detection Using Ontology-Based Data Collection from Social Media, 2023 IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2023), Istanbul, Turkey, December 5–8, 2023.

  5. P. D. Nagy, H. Davoudi, Towards Deep Learning Models for Automatic Computer Program Grading, The 10th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2023), Thessaloniki, Greece, October 9–13, 2023.

  6. A. Naeiji, A. An, H. Davoudi, M. Delpisheh, M. Alzghool, Question Generation Using Sequence-to-Sequence Model with Semantic Role Labels, The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), Dubrovnik, Croatia, May 2–6, 2023.

2022

  1. H. Hajiyan, H. Davoudi, M. Ebrahimi, A Comparative Analysis of Local Explainability of Models for Sentiment Detection, Proceedings of the Future Technologies Conference, October 10–21, 2022.

  2. S. Bakos, H. Davoudi, Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios, 2022 IEEE Conference on Games (CoG'22), August 21–24, 2022.

2021

  1. J. Nemec, H. Davoudi, L. Golab, M. Kargar, Y. Lytvyn, P. Mierzejewski, J. Szlichta, M. Zihayat, RW-Team: Robust Team Formation Using Random Walk, The 30th ACM International Conference on Information and Knowledge Management (CIKM 2021), November 1–5, 2021.

2020

  1. N. Babanejad, H. Davoudi, A. An, M. Papagelis, Affective and Contextual Embedding for Sarcasm Detection, The 28th International Conference on Computational Linguistics (COLING'20), Online, December 8–13, 2020.

  2. A. Stoica, K. Q. Pu, H. Davoudi, NLP Relational Queries and Its Application, IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI'20), Las Vegas, NV, USA, 2020.

2019

  1. N. Babanejad, A. Agrawal, H. Davoudi, A. An, M. Papagelis, Leveraging Emotion Features in News Recommendations, Proceedings of the 7'th International Workshop on News Recommendation and Analytics (INRA'19) in conjunction with RecSys’19, Copenhagen, Denmark, September 16–20, 2019.

  2. H. Davoudi, P. Godfrey, L. Golab, M. Kargar, D. Srivastava, J. Szlichta, Bringing Order to Data, Proceedings of the 13'th Alberto Mendelzon International Workshop on Foundations of Data Management (AMW'19), Asuncion, Paraguay, June 3–7, 2019.

  3. H. Davoudi, A. An, G. Edall, Content-Based Dwell Time Engagement Prediction Model for News Articles, The 17'th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), Minneapolis, USA, June 2–7, 2019.

2018

  1. H. Davoudi, A. An, M. Zihayat, G. Edall, Adaptive Paywall Mechanism for Digital News Media, Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'18), London, U.K., August 19–23, 2018.

2017

  1. H. Davoudi, M. Zihayat, A. An, Time-Aware Subscription Prediction Model for User Acquisition in Digital News Media, Proceedings of SIAM International Conference on Data Mining (SDM'17), Houston, Texas, USA, April 27–29, 2017.

  2. Y. Chen, M. L.-Jing Yann, J. Choi, H. Davoudi, Aijun An, Z. Mei, Contrast-Based Collaborative Behavior Recommendation System for Life Improvement, Proceedings of the 21'st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'17), Jeju, South Korea, May 23–26, 2017.

2016

  1. M. Zihayat, H. Davoudi, A. An, Top-k Utility-Based Gene Regulation Sequential Pattern Discovery, Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM'16), Shenzhen, China, December 15–18, 2016.

  2. A. Agrawal, R. Sahdev, H. Davoudi, F. Khonsari, A. An, S. McGrath, Detecting the Magnitude of Events from News Articles, Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence (WI'16), Omaha, Nebraska, USA, October 13–16, 2016.

2015

  1. H. Davoudi, Aijun An, Ontology-Based Topic Labeling and Quality Prediction, Proceedings of the 22'nd International Symposium on Methodologies for Intelligent Systems, Lyon, France, October 21–23, 2015.

2014

  1. H. Davoudi, Xiaoli Li, M. N. Nguyen, S. P. Krishnaswamy, Human Activity Recognition Using Few Labeled Sample, Proceedings of the 18'th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'14), Taiwan, May 13–16, 2014.

Book Chapters

2025

  1. M. Abdollahi, A. Abedjooy, H. Davoudi, M. Ebrahimi, Image Inpainting Using GAN Transformer-Based Model, Imaging Science, Computer Vision, Image and Signal Processing, Pattern Recognition, De Gruyter, pp. 111—126, 2025.

  2. M. Abdollahi, H. Davoudi, M. Ebrahimi, Magnetic Resonance Image Re-parameterization on Real Data, Imaging Science, Computer Vision, Image and Signal Processing, Pattern Recognition, De Gruyter, pp. 3—16, 2025.

Teaching

Bronze search tree with a chess knight at the root and an amber solution path to a goal
CSCI 4610U — Artificial Intelligence

This course introduces the fundamental concepts and techniques of artificial intelligence, with an emphasis on problem-solving and intelligent decision-making. Topics include uninformed and informed search, adversarial search, constraint satisfaction, Markov decision processes, reinforcement learning, and Bayesian networks. Students learn to formulate search problems, compare solution strategies, and develop agents that learn from experience and reason under uncertainty.

  • Undergraduate course
  • Ontario Tech University
Bronze and ivory database with a magnifying glass revealing a chart and connected data points
CSCI 4150U — Data Mining

This course introduces the fundamental concepts and techniques of data mining, with an emphasis on extracting useful knowledge from raw data. Topics include data exploration and preprocessing, classification, clustering, anomaly detection, and association rule mining. Through hands-on laboratories, students learn to build and adapt data mining models, evaluate their performance, and apply the data mining pipeline to practical problems.

  • Undergraduate course
  • Ontario Tech University
Bronze and ivory divide-and-conquer diagram beside a chart comparing algorithm growth rates
CSCI 3070U — Analysis and Design of Algorithms

This course introduces fundamental techniques for designing efficient algorithms, proving their correctness, and analyzing their computational complexity. Topics include divide-and-conquer, dynamic programming, greedy methods, branch-and-bound, and graph algorithms for spanning trees, shortest paths, and maximum flow. Students learn to compare algorithmic approaches and examine the limits of efficient computation through P, NP, NP-completeness, and NP-hardness.

  • Undergraduate course
  • Ontario Tech University

Cite this publication

Citation source ↗