<p>The paper focuses on the synthesis, characterization, and machine learning-based property prediction of a hybrid nanocomposite consisting of polymethyl methacrylate (PMMA), multi-walled carbon nanotubes (MWCNTs), and silver nanoparticles (AgNPs). The nanocomposite was synthesized by solution mixing, which resulted in uniform dispersion of fillers. Characterization techniques confirmed the properties of the material: X-ray diffraction (XRD) showed crystalline structures with sharp peaks for MWCNT at 2θ = 26.17° and Ag at 2θ = 37.7°, which confirmed the successful integration of the filler, while SEM showed uniform microstructure and effective micromachining. EDS analysis confirmed elemental homogeneity, with carbon, oxygen, and silver at 61.54 wt%, 34.44 wt%, and 4.02 wt%, respectively. The dielectric measurements showed specific trends. The dielectric constant was 6 at a low frequency of 20&#xa0;Hz for 0.1 wt.% Ag content, mainly due to interfacial polarization. The AC conductivity was highly increased with increased Ag content; the highest Ag content considered was 0.5 wt.%. This confirmed that charge mobility was improved. Machine learning models, including Extra Trees, XGBoost, and CatBoost, predicted dielectric properties with great accuracy; Extra Trees had R² = 0.9999 with mean squared error of zero and MAE of 0.0008. The results indicate a promising advanced material application for the PMMA/MWCNT/Ag nanocomposite. Nonetheless, its brittleness calls for further improvements in mechanical properties, further emphasizing the application of machine learning in optimizing material design.</p>