Determining the propagation behavior of hydraulic fracture and the most important parameters that affect hydraulic fracturing propagation are important challenges in reservoirs with natural fractures. Hydraulic fracturing in the presence of natural fractures alters the way the induced fracture propagates through the rock and causes a complex network of fractures which can significantly influence the overall geometry and effectiveness of hydraulic fractures. Interaction of hydraulic fracture with natural fractures can lead to pre-mature screen-out, arrest of the fracture propagation, formation of multiple fractures and fracture offsets. In this study, hydraulic and natural fracture interaction in naturally fractured reservoirs has been investigated through an artificial intelligence method. So, a new feed-forward with back-propagation artificial neural network approach has been developed to predict hydraulic fracturing path due to interaction with natural fracture followed by forward selection sensitivity analysis to determine the most influential parameters. Effective parameters in hydraulic and natural fracture interaction such as horizontal differential stress, angle of approach, interfacial coefficient of friction, young’s modulus of the rock and flow rate of fracturing fluid are the inputs and hydraulic fracturing path (turning into/crossing natural fracture) when it encounters a natural fracture is the output of the developed artificial neural network. The results have shown high potentiality of the developed artificial neural network approach for real-time prediction of hydraulic fracturing path due to interaction with natural fracture. Also, the result of sensitivity analysis has shown that the angle of approach, horizontal differential stress and interfacial coefficient of friction are the macro-parameters and flow rate of fracturing fluid and young’s modulus of the rock are the micro-parameters affecting hydraulic fracture behaviour in naturally fractured reservoirs.