Artificial Intelligence (AI) has become an integral part of the industry. As an emerging technology, Quantum Computing has already delivered impressive results. In an earlier paper we compared Quantum Machine Learning (QML) to traditional machine learning algorithms, whereby QML unexpectedly delivered inferior results. In this study, we examine novel encoding methods that extend the feature space to improve the performance of QML algorithms. This work seeks to improve upon the results of the prior paper [9]. The outcomes can then be used to realize the potential of Quantum Machine Learning in industrial applications.