Enhancing COVID-19 Prediction: Optimized Random Forest Classifier with Feature Selection

Timely identification plays a crucial role in halting the dissemination of life-threatening diseases. COVID-19, a highly transmissible illness with various mutations, has sparked a worldwide epidemic necessitating prompt detection. As COVID-19 cases continue to surge, the volume of related data escalates daily, offering an opportunity for data mining to glean insights from this information. This paper employs a dataset encompassing COVID-19 symptoms and presence, leveraging feature selection method and several supervised machine learning techniques to forecast the presence of COVID-19 based on symptom analysis. Supervised machine learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbour (k-NN), Naive Bayes, Logistic Regression, and Random Forest were employed for accuracy and f1 score. In this investigation, Random forest classifier with feature selection outperformed all other classifier under analysis with 98% accuracy and 0.99 f1 score.