The rapid depletion of fossil fuel resources and their detrimental impact on the environment necessitates the exploration of renewable energy alternatives. Biomass stands out as a reliable renewable source, especially in multigeneration systems. This study suggests a biomass-driven multigeneration configuration for the production of electricity, heating, hydrogen, and freshwater. The configuration is evaluated from thermodynamic and economic perspectives, utilizing an Artificial Neural Network to predict key outcomes. The system optimization process integrates Machine Learning with decision-making methods to achieve optimal conditions. The findings highlight that an anode-cathode gas recycling design is the most effective configuration for the Solid Oxide Fuel Cell unit, achieving a cycle efficiency of 67.68% and a product cost of $11.41/GJ. Municipal Solid Waste biomass and CO2 were identified as the most efficient fuel and gasification agents, respectively. The evaluations also determined that the integration of the multi-objective grey wolf optimizer and the CatBoost method is the most reliable machine learning model for optimization. Furthermore, by combining the Multi-Objective Harris Hawks Optimization algorithm with TOPSIS, LINMAP, and Fuzzy decision-making approaches, the system achieves optimal performance across multiple scenarios. In one scenario, the system reached an exergy efficiency of 67.68% and a hydrogen production rate of 22.34 kg/h. The optimum recycling ratios for the anode and cathode were determined to be 0.16 and 0.38, respectively. The study demonstrates the feasibility of the proposed configuration, offering significant potential for sustainable and cost-effective energy generation.