<![CDATA[The Fuzzy Associative Memory (FAM) method is a combination of fuzzy logic and artificial neural networks. The combination of fuzzy logic and artificial neural networks in FAM has the advantage of applying human expertise, tolerant of errors, and can be applied in the real world. This study aims to determine the accuracy of the results of the implementation of the FAM method in estimating rainfall in Malang City. The problem that occurs is that the results of rainfall estimates are different from reality. Therefore, it is necessary to have a planning tool that can estimate rainfall for a particular location and time. The solution to overcome these problems is to use a combination of fuzzy logic and artificial neural networks, namely FAM. This method requires a process to determine the membership function. After the membership function is formed, input matrix and output matrix are formed where the elements of the matrix are the membership degree of the input variable for input matrix and the membership degree of the output variable for output matrix . After that, to form a FAM system, it is necessary to invert the input A and output B matrices. So, the number of system FAM rules is as much as the data used. Then data testing is carried out on the system FAM rules obtained and the maximum value in the new matrix B is the best solution. The variables used in this study are temperature, humidity, air pressure, and wind speed. The results of the rainfall forecast using FAM have a large MAPE percentage error of 15% which means the forecasting results are good. It is expected that using the FAM method can estimate rainfall sometime in the future.]]>
