<![CDATA[The characteristics of land value is not linier and high multicolinierity, the methods of landassessment using MRA might resulting less accuracy,Therefore land ANN method to improve thepredicted value quality to be more accurate is required. ANN method could identify the patternsand relationships between linier and non linier independent variables to the dependent variablesthrough the learning process iteratif. The previous explanation encourage the authors tocomparison use MRA and ANN, when applied in Kelurahan Way Lunik, Ketapang and Way LagaBandar Lampung. The modelling results of MRA method is lin-log, while the modeling results ofANN is backpropagation. The influence of independent variables to the land value in ANN modelis better than MRA model. This can be seen in R2 value ANN model is 98.3% and the R2 valueMRA model is 90.1%. The accuracy of ANN model is higher than MRA model. This can be seen inCOV value ANN model is 10.1% and COV value MRA model is 50.2%. The dispersion of ANNmodel is higher than MRA model. This can be seen in COD value ANN method is 7.2% and valueCOD MRA method is 35.3%. The estimation land value of ANN model is closer to the actual valuethan estimation land value of MRA model. This can be seen in PRD value ANN method is 1.00 andthe value of PRD MRA model is 1.07. The comparison result of land value estimation using theMRA and JST shows that the ANN land value estimation is closer to the sample data.]]>
