Present study intends to propose identification methodologies for multistorey shear buildings using powerful technique of artificial neural network models which can handle interval data. Identification with crisp data is known and neural network method has already been used by various researchers for this case. Here, the input and output data are handled in interval form. This is because, in general, we may not get the corresponding input and output values exactly (in crisp form), but we may have only the uncertain information of the data. These uncertain data are assumed in terms of interval and the corresponding problem of system identification is investigated. © 2014 Taylor & Francis.