This study aims to compare the performance of the C4.5 algorithm and the K-Nearest Neighbor (KNN) method in predicting the nutritional needs of pregnant women. The research method involves six main stages: field data collection, dataset reading, basic data exploration, data preprocessing, predictive model development, and model evaluation using test data. The dataset was collected through a Google Form distributed to pregnant women in the Pandaan sub-district and then underwent a preprocessing phase to clean and prepare the data for further analysis. The C4.5 and KNN algorithms were built using the preprocessed data, and the complexity of each model was evaluated to determine their prediction accuracy. These methods were used to predict the nutritional requirements of pregnant women. The findings of the study indicate that the C4.5 algorithm achieved a higher accuracy rate of 95%, compared to 87.50% achieved by the KNN algorithm. Based on these results, it can be concluded that the C4.5 algorithm is more accurate and reliable for predicting the nutritional needs of pregnant women.