Stroke Prediction Using Machine Learning

Built predictive models to identify individuals at risk of stroke using healthcare data. Implemented several classification techniques and ensemble methods to improve prediction accuracy.

Technologies

Python

Scikit-learn

Pandas

Matplotlib

Seaborn

Key Features

Data preprocessing and missing value handling.

Exploratory Data Analysis.

Feature encoding and scaling.

Applied Naive Bayes, Logistic Regression, KNN, SVM, Random Forest, and ensemble learning.

Performance comparison using classification metrics.

Results

Evaluated multiple models to determine the best-performing classifier.

Visualized feature relationships and model performance.