<![CDATA[The selection of rental housing is a multi-criteria decision-making problem involving factors such as price, location, facilities, security, and environment, making it difficult for prospective tenants to determine the option that best suits their needs. This study aims to develop a rental housing recommendation system model by integrating Multi-Criteria Decision Making (MCDM), Machine Learning, and Technology Acceptance Model (TAM). The Analytical Hierarchy Process (AHP) is used to determine the criteria weights. In contrast, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is used to rank rental housing alternatives. Furthermore, a Machine Learning approach using the Random Forest algorithm is applied to predict user preferences from historical data. System evaluation is carried out by comparing recommendation performance between AHP–TOPSIS and Simple Additive Weighting (SAW), testing the performance of the Machine Learning model, and analysing user acceptance using Structural Equation Modelling based on Partial Least Squares (SEM-PLS) within the Technology Acceptance Model framework. The results show that the AHP–TOPSIS model outperforms SAW in recommendation performance, achieving 89.4% compared to 84.7%. The Random Forest-based Machine Learning model also demonstrated good performance in predicting user preferences. The SEM results showed that perceived ease of use significantly influenced perceived usefulness and behavioural intention; perceived usefulness significantly influenced behavioural intention; and behavioural intention significantly influenced actual use, with p-values < 0.05. The R-square value of 0.67 indicated that the model had strong explanatory power for user acceptance. This study developed a rental housing recommendation system model that not only objectively provides the best alternative but also adjusts its recommendations to user preferences, achieving high acceptance. This model has the potential to be applied in the development of recommendation systems in the housing sector and artificial intelligence-based decision support systems.]]>
