Inventory management requires thousands or millions of individual transactions each year. Classification of the items influences the results of inventory management. Traditionally, this is usually classified with considering an annual dollar usage criterion but maybe other criterias such as lead time, criticality, perishability, inventory cost, and demand type can be affected on that classification. The objective of this study is to determine the multi-criteria inventory classification (MCIC) of the inventory items to minimize the total inventory cost and also dissimilarity of classes. Because of the two objectives is considered to solve with together, the maximization of satisfaction level is described to solve the multi-objective problem. This study introduces a Mixed Integer Nonlinear Programming (MINLP) model of the MCIC problem by giving two objectives. A Scatter Search Algorithm (SSA) is used to solve the MINLP model for obtaining high-quality solutions within reasonable computation times. Finally, we illustrate an example and compare our results with other studies in previous literature.