Predictive Modelling for Lighthouse Locations with Classical and Quantum Approaches

This repository showcases a comprehensive data analysis and predictive modeling project aimed at optimizing site management and reliability in lighthouse operations. The dataset comprises 60,000 observations across 17 lighthouse locations, and advanced preprocessing techniques, feature extraction, and analysis were employed to identify influential factors. Classical machine learning algorithms were utilized to develop a robust model with an exceptional accuracy rate of 92%. Additionally, the project explores the cutting-edge realm of quantum computing by implementing a Variational Quantum Classifier (VQC) on AWS Braket, resulting in a significant accuracy improvement of 55%. The project's hypothesis revolves around leveraging historical data and quantum feature mapping to revolutionize the prediction and management of sensor malfunctions in lighthouse operations. Join us in exploring the potential of quantum computing and its applications in this exciting field.