This study presents the manufacturing process of biocomposite materials using lignocellulosic fibers extracted from sugarcane bagasse combined with epoxy matrix and a comprehensive analysis to predict the strength using experimental, machine learning, and analytical frameworks. Chemical treatment of the sugarcane bagasse was performed using a 5% sodium hydroxide (NaOH) solution to enhance fiber-matrix adhesion by removing non-cellulosic components and reducing hydrophilicity. Biocomposites were manufactured using a rectangular mold of 19 in×15 in×0.7 in volume with a fiber volume fraction of 0.3, followed by hot pressing the suspension and controlled curing. Mechanical characterization, including tensile, flexural, and impact strength, was conducted in accordance with ASTM standards. Multiple analytical models, including Rule of Mixture (ROM), Inverse ROM, Modified ROM, Halpin-Tsai, and Hirsch model were employed to predict the modulus of elasticity (MoE) and strength. Supervised machine learning models such as linear regression (LR), decision tree regression (DTR), extreme gradient boosting (XGBoost), random forest regression (RFR), and support vector regression (SVR) were adopted to predict the MoE and strength. Finally, the mechanical properties predicted from the machine learning models were validated and verified using experimental and analytical results. The results demonstrate the significant potential of sugarcane bagasse as a sustainable reinforcement material.