The Machine Learning Based Weather Prediction project aims to utilize historical weather data to classify and predict weather conditions accurately. With a dataset comprising 96,453 entries and 12 distinct features, this project leverages machine learning techniques to provide insights into five weather categories: Cloudy, Overcast, Sunny, Foggy, and Rain.  Existing approaches employ Logistic Regression for classification, while this project proposes the integration of advanced models like Support Vector Machine (SVM), Decision Tree Classifier, and Random Forest Classifier to enhance predictive accuracy. The dataset encompasses a combination of numerical features (e.g., temperature, humidity, pressure) and categorical features (e.g., precipitation type, weather summaries), providing a robust foundation for model training and evaluation. This project focuses on preprocessing the data, feature engineering to optimize model performance. The results are expected to contribute to weather forecasting applications, aiding decision-making in areas like agriculture, transportation, and event planning. By employing state-of-the-art machine learning algorithms, this project seeks to deliver a scalable and efficient solution for weather prediction challenges.

Keywords: Machine Learning, weather.