Abstract— The efficiency of wireless systems is heavily dependent on the precision of the propagation channel model. Accurate prediction of signal path loss is an essential process in planning and optimizing radio networks. In this paper, a new indoor path loss prediction model – utilizing the Adaptive Neuro-Fuzzy Inference System (ANFIS) approach – is proposed. The proposed model takes into consideration the effect of different indoor barriers or wall types, in addition to other essential factors, on the propagation channel to obtain precise prediction in buildings with hybrid walls or partitions. On-site recorded WiFi data is used to build and verify the proposed model. To minimize modeling errors, a hybrid training method is employed, and the input membership functions of the model are optimized. The proposed ANFIS model is compared with the Cost-231 propagation model after it has been calibrated using a multilinear regression approach. The comparison indicates the superiority of the proposed model in terms of precision and accuracy. The obtained results show that the new model has a lower root mean square error and standard deviation with a higher correlation factor of 98%. The proposed ANFIS model produces precise indoor WiFi prediction and promotes accurate forecasting of other frequency bands – such as UMTS and GSM – in buildings with different interior structures.