B.Tech AI & Data Science coursework and project work emphasizing model output quality assessment
Don't disclose
Conducted AI/ML study activities focused on assessing and validating model outputs during coursework related to water potability classification. Practiced quality assessment and structured reasoning to compare results and identify inconsistencies in generated predictions. Applied evaluation concepts to judge output reliability and support downstream data labeling or annotation decision-making. • Used Python (NumPy, scikit-learn) and a Kaggle dataset as the basis for analysis and evaluation • Performed model evaluation and reviewed output quality metrics to judge performance • Checked predictions for inconsistencies to improve reliability of outcomes • Worked in Google Colab for iterative analysis and evaluation experiments
2026 - Present