ANURATA PRABHA HRIDI
CS Faculty @UNL | CS PhD @NC State, CS MS @Clemson | Ex-ML Engineer Intern @Rocket Central | AI/ML Researcher | Educational Data Mining, Computer Science Education, Human-Computer Interaction
Embedded Files
Welcome!
Welcome!
My name is Anurata Hridi (pronounced OW-noo-raw-tow REE-dee) and my pronouns are she/her. I am an Assistant Professor of Practice at the University of Nebraska-Lincoln (UNL), with a joint appointment between the School of Computing and the Raikes School of Computer Science and Management. I completed my PhD in Computer Science (CS) at North Carolina State University (NC State) in Spring 2026. I also continue to serve as an Adjunct Lecturer at NC State Data Science and AI Academy.
Alongside teaching machine learning and data science courses, I am actively involved in research efforts. My current research focuses on machine learning, educational data mining and computer science education, with an emphasis on applying distributed ML approaches to educational data. My broader research goal is to generate privacy-preserved insights for instructors that can help them provide more personalized support to students in the classroom.
Prior to joining NC State, I completed my MS in CS at Clemson University in 2021 and BSc in Computer Science and Engineering at Bangladesh University of Engineering and Technology (BUET) in 2017. I was drawn to the realm of research with an exploration into autistic children's educational landscape in Bangladesh in 2019 and have been deeply passionate about research on education since then.
I have gathered experiences in academia and industry through classroom instructor and ML and software engineer positions. Outside work, I enjoy hiking, traveling, reciting poems and engaging in conversations with like-minded individuals. I am open to new experiences, cultures and ways of thinking. I look forward to building connections and exploring collaboration opportunities!
Research Interests
Research Interests
Education
Education
Distributed Machine Learning
Educational Data Mining
Computer Science Education
Applications of Artificial Intelligence in Education
Human-Computer Interaction
Fairness and Ethics in AI
North Carolina State University, Raleigh, NC, USA
PhD in Computer Science, May 2026Clemson University, Clemson, SC, USA
MS in Computer Science, May 2021Bangladesh University of Engineering & Technology, Dhaka, Bangladesh
BSc in Computer Science & Engineering, September 2017
Work Experience
Work Experience
Assistant Professor of Practice, School of Computing and Jeffrey S. Raikes School of Computer Science and Management, University of Nebraska-Lincoln. Aug 2026 – Present
Teach Introduction to Machine Learning, covering classification, regression, model evaluation, preprocessing, regularization, and applied machine learning workflows.
Supervise three senior capstone teams working with industry sponsors on real-world computing projects, guiding technical design, implementation, evaluation, and final delivery, and conduct research in privacy-preserving AI/ML applications, federated learning, learning analytics, and human-centered AI.
Adjunct Lecturer, NC State Data Science & AI Academy, North Carolina State University.
Teach Introduction to R/Python for Data Science, introducing students to programming, data manipulation, visualization, and data-analysis workflows.
Graduate Research Assistant, Computer Science, North Carolina State University. Jan 2024 – May 2026
LLMs in Educational Data Mining
• Applied LLMs, RAG, and few-shot prompting to evaluate AI-supported systems for personalized computing applications.
• Analyzed programming logs, student dialogue, and LLM interactions to identify patterns associated with collaboration and learning, which resulted in classroom-deployable frameworks presenting the relationship between a student pair & AI.
• Analyzed sequential programming and interaction behaviors to characterize how students plan, debug, revise code, evaluate AI responses, and incorporate generated suggestions. Results include creating heuristics to identify potential AI use.
Predictive Modeling & Federated Learning
• Developed and evaluated distributed predictive models using FedAvg, PerFedAvg, and FedALA, among other federated learning (FL) techniques across heterogeneous datasets, comparing performance against centralized modeling approaches.
• Built predictive models for future interactions and course performances, achieving up to a 19% improvement in AUC and a 68% reduction in EOD with fairness evaluation over baselines while maintaining decentralized data governance.
• Developed deployment-ready frameworks with respect to student coding performance and collaborative learning. Results included interpretable interventions to support data-driven decision making under privacy and fairness constraints. Benchmark comparison also reported robustness across heterogeneous populations with respect to model generalization and predictive performance.
Learning Analytics
• Applied self-regulated learning and multimodal data to identify student struggle points and behaviors associated with learning outcomes. Findings came from qualitative analysis of surveying and observing students.
Health Data Science
• Analyzed longitudinal electronic health record (EHR) data to develop Python-based methodological training materials for comparing predictive models.
Natural Language Processing and Deep Learning
• Developed a time-sensitive itinerary summarization tool that improved the BLEU score by approximately 20% over the baseline approach.
• Implemented a Vision Transformer for crop classification using spatio-temporal data, achieving 95% classification accuracy.
• Implemented deep reinforcement learning methods for autonomous left-turn decision making in conflicting traffic, with PPO achieving the highest evaluation performance. Colab
Data Science and User Experience
• Developed a Python pipeline to compare real-world observations with simulated trajectories, evaluating model fidelity using statistical analyses of prediction error. Identified systematic discrepancies between simulated and observed data. Code
• Built a Figma Prototype in collaboration with LexisNexis to aid jurors regarding virtual evidence viewing. Paper Presentation
• Designed software to persuade users to be more eco-friendly in their regular activities. Managed data collection process and performed thematic analysis to report how participants preferred the prototype.
Machine Learning Engineer Intern, Rocket Central, Detroit, Michigan, USA. May 2023 – Aug 2023
Mentor: Matthew Rutkowski Manager: Zachary Bloss
Developed MLOps and model-governance workflows in a fintech environment using MLflow, CircleCI, AWS Athena, Python, and cloud-based data pipelines.
Built automated workflows for model metadata tracking, reproducibility, validation, and deployment testing. Continuous integration reduced manual steps and deployment failures.
Documented data-drift detection processes to identify changes in production data distributions that could affect model reliability, which also served as an exposure to understanding financial data better.
Collaborated with data scientists, ML engineers, and Ethical AI stakeholders to translate model-development requirements into repeatable enterprise workflows.
Graduate Teaching Assistant, Computer Science, North Carolina State University and Clemson University. Jan 2019 – Dec 2023
Supported 150+ undergraduate and graduate students across courses in Object-Oriented Programming, Data Science, Algorithms, Machine Learning, and Software Engineering through office hours, labs and assessment activities.
Summer Instructor, Computer Science, North Carolina State University. May 2022 – Aug 2022
Taught a sophomore-level C programming course, including lectures, programming assignments, assessment, and student support, and managed teaching assistants.
Lecturer, Computer Science and Engineering, Southeast University, Dhaka, Bangladesh. May 2018 – Nov 2018
Taught undergraduate courses in Database Design, C Programming, and Software Engineering, and supervised theses.
Junior Software Engineer, REVE Systems, Dhaka, Bangladesh. Nov 2017 – May 2018
Team Lead: Mohammad Aftab Uddin
Supported end-to-end software development, including coding, testing, debugging, and database updates using Java, SpringBoot, SQL/relational databases, HTML, and CSS, contributing across backend, database, and frontend components.
Collaborated with clients and engineering teams to translate business requirements into technical tasks, document requirements, and track implementation through project plans.
Page updated
Google Sites
Report abuse