The aluminium Twitch fraction of a Belgian recycling facility could be further sorted by implementing Laser-Induced Breakdown Spectroscopy (LIBS). To achieve this goal, the presented research identifies commercially interesting output fractions and investigates machine learning methods to classify the post-consumer aluminium scrap samples based on the spectral data collected by the LIBS sensor for 834 aluminium scrap pieces. The classification performance is assessed with X-Ray Fluorescence (XRF) reference measurements of the investigated aluminium samples, and expressed in terms of accuracy, precision, recall, and f1 score. Finally, the influence of misclassifications on the composition of the desired output fractions is evaluated.