Spices are parts of plants that have a strong aroma and are used in small amounts in foods as flavours, preservatives, and food coloring. Spices are usually used as medicines, natural dyes, and spices. As a kitchen spice, spices have a variety of types, but have almost the same shape and color. In this study, the Machine Learning algorithm was tested which is one of the Artificial Neural Network methods that is often used to predict data. The research data used are export data of medicinal, aromatic and spice plants in 2012-2020. Based on this data, a network architecture model will be determined, including 3-10-1, 3-15-1, 3-20-1, 3-25-1. From the five models, training and testing were carried out first and then obtained the results that the best architectural model was 3-10-1 with 0.01929300. So it can be concluded that the model can be used to predict the export data of medicinal, aromatic and spice plants