<p>Artificial Intelligence techniques, including machine learning and artificial neural networks (ANN) are commonly employed to address various difficulties in Engineering. This research involved the creation of hybrid polymer by reinforcing polymer composite with natural fibers derived from Calotropis gigantea and Nano TiO₂. A chemical treatment with a sodium hydroxide (NaOH) solution in acetone (C3H6O) was performed to change surface characteristics of the fibers, enhancing their adhesion and interaction with the polymeric matrix. ANN model were initially trained and employed to forecast and enhance tensile strength of resulting CGF/nano TiO₂ hybrid nanocomposite (CGFN). The employed model was single-layer perceptron architecture configured as 3-5-1, featuring a hidden comprising 5 neurons. The CCD was employed to systematically investigate influence of various variables at tensile strength. SEM analyses demonstrated significant impact of NaOH alteration on fiber-matrix, affecting mechanical characteristics of composite. Results of mechanical testing conducted by ANOVA demonstrated that the primary determinants significantly influenced tensile strength, while the model exhibited an excellent fit with a coefficient of determination R² = 0.9479. ANN-CCD model predicted an optimal TS of 47.15&#xa0;MPa, closely aligning with the experimentally obtained value of 47.33&#xa0;MPa, resulting in an accuracy of approximately 98.45% in the model’s prediction. This research highlights the efficacy of employing Artificial Neural Networks (ANN) in conjunction with Central Composite Design (CCD) to swiftly obtain dependable estimations of mechanical characteristics, so conserving experimental design time, production costs and resources in the development of composite materials. The utilization of calotropis gigantea fiber in conjunction with nano TiO₂ fosters a sustainable methodology by improving material efficacy while advancing development objectives at materials engineering.</p>