Residential property rental value forecasting has an impact on property investment decision. This necessitates the need for a study to forecast residential property rental value considering all associated variables including presence of cultural sites in the study area. Data for the study were gathered from the record of recent lettings in the study area. For the purpose of precision, this study adopted three artificial intelligence models. These are artificial neural network, logistic regression and support vector machine as models of classifying the rental value of residential property in Osogbo. The study considered relevant input variables among which are distance to cultural site, age of building, state of exterior/interior of building. Findings from the study revealed that the three adopted forecasting models had over 80% of the forecasted properties correctly classified thus making the residential property rental forecasting very reliable. Also, it was established that, in the study area, distance from cultural site is the property attribute with the highest negative impact on rental value.