<![CDATA[CV Prima Semesta Alam, an SME producing reptile leather crafts in Surabaya, faces challenges in expanding its market reach due to conventional marketing processes and unstructured stock management. General e-commerce platforms often fail to highlight the uniqueness of specific products like exotic leather, making it difficult for consumers to find relevant items. This study aims to build an Android-based digital marketing system integrated with a smart product recommendation feature using Term Frequency-Inverse Document Frequency (TF-IDF) and Cosine Similarity algorithms. The system was developed with a client-server architecture using Kotlin for the user interface and Golang as the backend. System testing showed that the recommendation algorithm was able to provide relevant product suggestions based on descriptive attribute similarities (material, color, function), with logic validation results demonstrating full consistency between manual calculations and system outputs. Usability evaluation using the System Usability Scale (SUS) yielded an average score of 76.16, placing the application in the Acceptable category with a Good rating.]]>
Copyrights © 2026
