<![CDATA[Selecting the right mathematics learning application is crucial for supporting students' learning processes, but this is often hampered by a wide variety of choices without objective guidance, potentially leading to less effective selections. This descriptive quantitative study describes the implementation of the Multi-Attribute Utility Theory (MAUT) method to recommend mathematics learning applications that align with student needs. MAUT flexibly and comprehensively considers various weighted criteria, making it effective for decision-making with complex preferences. Eight criteria were used to evaluate ten mathematics learning applications: (1) user review count, (2) storage capacity, (3) rating, (4) user count, (5) application usage cost, (6) answer accuracy, (7) ease of use (UI/UX), and (8) step-by-step solutions. Data were collected through questionnaires distributed to 20 respondents. The calculation process in the MAUT method was carried out through several stages: determining the relative weights for each criterion, constructing a decision matrix, performing normalization on the decision matrix, and calculating the final utility value for each alternative. Based on the calculation results using the MAUT method, the recommended application order is as follows: Photomath, Question.AI, Cymath, QANDA, Gauthmath, Check Math, Symbolab, Mathos AI, Mathway, and Math Workout. This study is expected to provide a practical contribution by helping students and educational institutions choose the most optimal mathematics learning application, and to serve as a basis for the future development of a more structured recommendation system.]]>
