Polymer recycling is challenging due to practical classification difficulties. Even when the polymer matrix is identified, the presence of various polymeric composites complicates their accurate classification. In this study, Fourier-transform infrared spectroscopy (ATR-FTIR) was used in combination with artificial neural networks (ANNs) to quantitatively predict the mineral filler content in polypropylene (PP) composites. Calibration curves were developed to correlate ATR-FTIR spectral features (600–1700 cm⁻¹) with the concentration (wt.%) of three mineral fillers: talc (PP-Talc), calcium carbonate (PP-CaCO₃), and glass fiber (PP-GF). ANN models developed in MATLAB 2024a achieved prediction errors below 7.5% and regression coefficients (R²) above 0.98 for all filler types. The method was successfully applied to analyze a commercial recycled pellet, and its predictions were validated by X-ray fluorescence (XRF) and energy-dispersive X-ray spectroscopy (EDX). This approach provides a simple, rapid, and non-destructive tool for non-expert users to identify both the type and amount of mineral filler in recycled polymer materials, thereby reducing misclassification in their commercialization or quality control in industrial formulations.