May 2025 – Aug 2025 · 3 mos

• Published and presented Paper on predictive modeling and pattern mining for mental health disorders at the ACM KDD 2025
• Conducted research on predictive modeling and pattern mining for mental health disorders using a dataset of 290K+ records and 17 features.
• Explored multiple machine learning paradigms, including unsupervised learning, frequent pattern mining, and tree-based classifiers for interpretable prediction.
• Designed scalable algorithms for association rule mining, improving both efficiency and rule quality through vectorized computation and adaptive statistical thresholds.
• Engineered feature representations from mined patterns and clusters, integrating them into interpretable decision tree models that achieved 95.67% accuracy and 92.8% recall.
• Built a hybrid, human-centered analytics framework that combines dimensionality reduction, clustering, pattern mining, and classification to support early detection and intervention in mental health.
• Collaborated closely with mentors and co-authors across multiple institutions, contributing to methodology design, algorithm development, and research presentation.

Jul 2024 – Aug 2025 · 1 yr 1 mo

• Conducted an in-depth literature review on state-of-the-art data mining techniques, with a focus on
• vertical and horizontal approaches.
• Designed and implemented a novel Sorted Vertical Transaction Database (SVTDB) to enhance
• efficiency in frequent itemset generation, improving upon the traditional qViper algorithm.
• Developed an algorithm with a time complexity of O(nm
• Log(m)+3mn) that leverages support monotonicity and maximal support calculations to minimize
• redundant operations.
• Conducted extensive experiments using real-world datasets (e.g., click-stream, retail, UCI Machine
• Learning repository), demonstrating significant performance improvements in runtime and
• computational overhead compared to existing methods.
• Collaborated with co interns to optimize implementations and extend algorithmic improvements to
• higher-order quantitative patterns

Jun 2024 – Oct 2024 · 4 mos

• I developed advanced data visualization and visual analytics solutions to analyze large, complex
• datasets. Using data mining algorithms such as K-Means clustering, Apriori for association rule mining,
• and decision trees, I uncovered hidden patterns and extracted meaningful insights from raw data.
• Utilized Python, Tableau, and Power BI to create interactive dashboards and insightful visual
• representations.
• Conducted exploratory data analysis and statistical modeling to uncover trends and patterns.
• Applied machine learning algorithms to enhance data-driven decision-making processes.
• Leveraged Python libraries (Pandas, Matplotlib, Seaborn) to effectively communicate findings.
• Utilized statistical software (e.g., R, Python) to analyze complex datasets, presenting insights that
• informed decision-making and strategic direction in research outcomes.