Treatment of spectral information is an essential tool for the examination of various cultural heritage materials. Raman spectroscopy has become an everyday practice for compound identification due to its non-intrusive nature, but often it can be a complex operation. Spectral identification and analysis on artists’ materials is being done with the aid of already existing spectral databases and spectrum matching algorithms. We demonstrate that with a machine learning method called Extremely Randomised Trees, we can learn a model in a supervised learning fashion, able to accurately match an entire-spectrum range into its respective mineral. Our approach was tested and was found to outperform the state-of-the-art methods on the corrected RRUFF dataset, while maintaining low computational complexity and inherently supporting parallelisation.