<p>This study investigates the dielectric properties of green synthesized ZnO and Ag-doped ZnO with different wt.% of Ag concentration in ZnO nanoparticles with epoxy polymer nanocomposites. To confirm their structural properties and chemical interactions with the neat epoxy, composite was characterized using X-ray Diffraction (XRD) and Fourier Transform Infrared Spectroscopy (FTIR). Scanning electron microscope (SEM) used to study the surface morphology of the prepared nanocomposites. The energy dispersive spectroscopy (EDS) measurement was carried out to determine the elemental composition in the samples. The LCR was used to study dielectric properties in the frequency range of 1&#xa0;k&#xa0;Hz to 2&#xa0;MHz The result shows that doping concentration and particle dispersion significantly influence dielectric properties. Among the Ag-doped ZnO epoxy composite, 2 wt.% exhibited the achieving high dielectric constant and low losses due to superior filler dispersion. AC conductivity trends aligned with dielectric measurements, confirming the critical role of doping and dispersion in tailoring dielectric behavior for advanced applications. This study also investigates machine learning techniques to predict the target variables ε′ and ε″ using Gradient Boosting, Extra Trees, and XGBoost. Gradient Boosting achieved the best performance with an R² of 0.9993 and MAE of 0.0101 for ε′, while the Ensemble model provided robust and consistent predictions, outperforming Extra Trees and XGBoost in specific metrics.</p>