The paper proposes an approach for predicting application upgrade time that is being upgraded from one version to another. The focus is primarily concentrated on applications with upgrades consisting mainly of upgrading the relational database. Chosen application databases have the same schema but the content of tables varies. Data from the upgrades are processed and the proposed solution predicting duration of upgrade for the database which is set to be upgraded provides an estimation whose accuracy is dependent on the number of performed upgrades. The solution is demonstrated on particular enterprise application.