This study was used to integrate the entropy and multi-objective optimization problems to produce the multiobjective entropy optimization model (MOEOM) for the agricultural product price recommendation problem (APPRP). The process was achieved by comparing several classical approaches. APPRP was used to determine the best selling price at the farm level such that a significantly high price would not allow the products to sell while a very low price could cause losses for farmers. This study was limited to the factors considered in APPRP including business profit/loss conditions, risk, business competition, production level, and product quality. The algorithm performance comparison results showed that the nondominated genetic sorting algorithm (NSGA- II) had the best performance based on the dominance of fitness value, number of iterations, execution time, percentage of feasible solutions, and level of precision of the solution. Meanwhile, based on the dominance of the solution on the objective function, the i-NSGA algorithm was observed to have a better solution than the NSGA-II despite its limited accuracy on the equation constraints. The i-NSGA was an improved version of NSGA with the inclusion of elitism and comparison of objective functions. Therefore, it was recommended that the smart reading algorithms, NSGA-II and i-NSGA, should be used to solve APPRP when accuracy is needed within the equation constraints. The implementation results also showed that the entropy optimization function produced price recommendations to farmers based on production and agricultural product quality. The entropy optimization function in the MOEOM significantly influenced the solutions produced through standard deviation and entropy, as well as the ANOVA test at a significance level of 0.05. This means it is possible to develop the MOEOM to determine optimal solutions in multiple objectives with uniformity (or diversity) in different fields.