Health_Disease_Prediction

Assignment 1-3 for CDS501 course (Principles & Practices of Data Science & Analytics) in USM

Models Accuracy

Weighted F1 Score is being used to evaluate due to the imbalance of the dataset.

Machine Learning Model	Weighted F1 Score
Logistic Regression	88.38%
Random Forest	88.07%
Decision Tree	88.06%
Naive Bayes	87.39%

Contributors and Part Contributed

1. Data Preparation - Alia Marliana
2. Exploratory Data Analysis 1: Do socio-demographic factors influence the health status of an individual? - Joyce
3. Exploratory Data Analysis 2: Are lifestyle factors linked to the presence of heart disease? -
4. Exploratory Data Analysis 3: How do individual health indicators collectively contribute to the prevalence of heart disease? -
5. Feature Selection - Alia Marliana
6. Model 1: Logistic Regression - Alia Marliana
7. Model 2: Random Forest -
8. Model 3: Decision Tree -
9. Model 4: Naive Bayes - Joyce