AML Assignment 1 : Evaluating Classification Metrics using Logistic Regression and Random Forest

n this video, we explain our project “Evaluating Classification Metrics” as part of the Advanced Machine Learning (UE23AI3501) course at GM University, Davangere. The project focuses on understanding how to evaluate the performance of machine learning models beyond simple accuracy. We compare two models — Logistic Regression and Random Forest Classifier — using the Breast Cancer dataset from Scikit-learn. We discuss important evaluation metrics like: Confusion Matrix Precision Recall F1 Score ROC-AUC These metrics help us measure how well a model performs on both positive and negative classes, especially in imbalanced datasets. Key highlights of the project: ✅ Dataset preparation and normalization ✅ Model training using Logistic Regression and Random Forest ✅ Evaluation using multiple classification metrics ✅ Discussion on the importance of metrics beyond accuracy ✅ Use of oversampling (SMOTE) to improve minority class detection This presentation was completed under the guidance of Mrs. Akshata A M S, Assistant Professor, AIML Department, GM University.