This study evaluates the effectiveness of different artificial intelligence (AI) algorithms in forecasting the elastic modulus of recycled polypropylene-tea residue composites. The research seeks to determine the most precise algorithm for this predictive task, thus aiding in the advancement of sustainable materials. Composite samples were formulated utilizing residues from Thai and green tea, with different proportions of polypropylene-graft-maleic anhydride (PP-g-MA) and thermoplastic elastomer (TPE). The elastic modulus of these samples was experimentally determined. Five artificial intelligence algorithms were assessed: Generalized Linear Model, Decision Tree, Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN). Performance metrics, such as Root Mean Square Error (RMSE), Relative Error, R², and P-value, were employed for comparison. The results demonstrate that the ANN achieved the greatest prediction accuracy, evidenced by a R² value of 0.883 and the minimal relative error of 3.11% ± 0.47%. The Decision Tree and Random Forest algorithms exhibited commendable performance, whereas the SVM yielded the least accurate predictions. The research indicates that the correlation between composite formulation and elastic modulus is significantly non-linear, requiring advanced modeling methodologies. This study identifies the optimal AI algorithm for predicting the elastic modulus of these composites and elucidates the intricate interactions within the material system. The results have considerable implications for expediting the advancement and refinement of sustainable composite materials that incorporate recycled and natural elements.