Contributing to research projects focused on socially just interventions in education, technology, and labor markets at the AIRE Lab such as Artificial Intelligence in Education and Labor Market, Global and Mental Health.Conducting advanced statistical analysis using Python, including predictive analytics, longitudinal data analysis, and multilevel modeling, to extract actionable insights from large educational and employment datasets.Supporting AI-related research by contributing to projects that utilized machine learning techniques and LLMs, contributing to research in the intersection of AI, education, and labor markets.

Designed and seamlessly integrated a funnel field into the data pipeline using the PySpark library by deploying it across QA and Production environments which empowered Business Analysts and leadership to make well-informed marketing decisions, yielding impactful solutions.Utilized Apache Drill SQL to conduct comprehensive data analysis within the cluster, extracting invaluable insights to drive strategic decision-making.Refined existing test cases using a Test-Driven Development methodology within the PyTest framework resulting in the expansion of test coverage and strengthening validation of vital software components, and enhancing overall software reliability.Acquired a strong grasp of Agile (Scrum) principles through active engagement in an Agile development setting, nurturing collaborative and iterative development methodologies.

Collaborated with the RD/ICI- Intelligent Interior - Software Department on Occupant Monitoring System to design and implement mock components utilizing C++ and CMake to enhance system testability for Computer Vision systems within Smart Car applications.Implemented enhancements to existing test cases, driving an increase in test coverage and ensuring comprehensive validation of software components.Developed a solid understanding of Agile (Scrum) principles while actively participating in an Agile development environment, fostering collaborative and iterative development practices.

Abstract: The paper addresses the challenge of predicting Ovarian Cancer (OC), which is known for its high mortality rate and late-stage diagnosis. We propose a novel scoring system designed to improve the accuracy of distinguishing between benign and malignant ovarian tumors using ultrasonography and tumor markers. They compare their system with existing models like RMI, ROMA, and IOTA's Simple Rules. The new system incorporates demographic, clinical, and ultrasound features, and its performance is evaluated using various Machine Learning algorithms. Implemented SVM, LR, k-NN, DTC, and RFC Machine Learning algorithms and developed RMI Scoring System to process the Ovarian Cancer tumor dataset to categorize cases as benign, malignant, and borderline, and used Python in Google Collaboratory and Jupyter Notebook to predict the accuracy of the models.Applied preprocessing techniques to clean and enhance recorded data samples using libraries such as NumPy, Pandas, scikit-learn, and SMOTE. Employed Feature Selection methods to achieve an accuracy of over 85% with the help of SciPy and seaborn libraries.Evaluated the efficiency of the algorithms employed through Performance Metrics and visualized theirresults using AUC-ROC curve with the assistance of Matplotlib, Seaborn, and roccurve libraries.