Advanced Machine Learning Group Project: Seahorse
Based on the Kaggle competition: (Driver Telematics Analysis)
Seahorse aim to come up with a telematic fingerprint capable of determining when a trip was driven by a given driver. The features of this driver fingerprint could help assess risk and form a crucial piece of a larger telematics puzzle. The main difficulties are feature extraction and feature representation which are tackled using various machine learning methods. The group considered multiple architectures and approaches including clustering algorithms, SVM and deep learning to assess the effectiveness of different methods and provide a final solution.