o Collaborated with companies like RedHat and Huawei on innovative projects.o Experience working with large-scale tabular datasets. o Published 10 papers in competitive peer-reviewed venues.o Mentored multiple MSc students.o Wrote a funding proposal for a competitive grant to design an auto-encoder algorithm.o Presented in 4 conferences.Papers (5 of 11):o Embedding-Based Meta Model for Cross-project Defect Prediction. Empirical Software Engineering (2024) o A Survey on Transfer Learning for Cross-project. IEEE Access (2024)o Exploring design smells for smell-based defect prediction. Engineering Applications of Artificial Intelligence (2022)o Cross-project smell-based defect prediction. Soft Computing (2021)o Beirut: Repository mining for defect prediction. ISSRE (2021)

Code Embedding for Defect Prediction Meta-Learner:o Problem: Cross-project defect prediction was never reviewed under the transfer learning domain. o Results: survey categorizing defect prediction approaches on code-embedding-based meta-learning. o Accomplishments: Published a survey (2023) and submitted a paper for a meta-learner (2024).o Skills: Deep Learning, code embedding, and technical writing.

Transfer Learning for Defect Prediction:o Problem: Smells were not studied in the transfer learning domain of defect prediction. o Results: Implemented and evaluated several transfer learning techniques trained with code smells. o Accomplishments: Published paper for the evaluation (2021).o Skills: Transfer learning algorithms.

Code-Smells for Defects Classification:o Problem: Design smells were not studied for defect prediction. o Result: Created dataset extraction tool and trained supervised classifiers. o Accomplishments: Published paper for the dataset (2021) and classification (2022).

Auto-encoder for Imbalanced Defect Predictiono Problem: Defect prediction models suffer from extreme label imbalance. o Result: Developed an autoencoder for anomaly detection to identify defective software components.