└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # Stroke Prediction Based on Risk Factors
 2 | 
 3 | This project is a machine learning-based stroke prediction system developed using healthcare data. It was created as part of my Data Science Minor Project at Lovely Professional University.
 4 | 
 5 | The model predicts the likelihood of a stroke based on features like age, BMI, average glucose level, hypertension, heart disease, and lifestyle factors.
 6 | 
 7 | ## What I Did
 8 | 
 9 | - Cleaned and preprocessed the dataset (handled missing values, encoded categories, scaled features)
10 | - Applied SMOTE to balance the dataset
11 | - Trained two models: Logistic Regression (baseline) and Random Forest (after SMOTE)
12 | - Evaluated models using Accuracy, Recall, F1-score, ROC Curve, and Confusion Matrix
13 | 
14 | ## Key Takeaways
15 | 
16 | - SMOTE significantly improved stroke case detection
17 | - Random Forest outperformed Logistic Regression on the balanced data
18 | - Data preprocessing and class balancing are crucial for health predictions
19 | 
20 | ## Dataset
21 | 
22 | Kaggle Stroke Prediction Dataset  
23 | [Link to dataset](https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset)
24 | 
25 | ## Author
26 | 
27 | Bhavya  
28 | B.Tech CSE, Lovely Professional University
29 | 
30 | ---
31 | 
32 | This project is for academic learning and research purposes.
33 | 
34 | 


--------------------------------------------------------------------------------