This paper aims to introduce a computer-based estimation and compensation method for diametral errors in cantilever bar turning without additional hardware requirements. In the error estimation method, the error characteristics of workpieces are determined experimentally depending on cutting speed, depth of cut, feed rate, workpiece diameter, length from the chuck and the geometric error sum of CNC lathe. An Artificial Neural Network (ANN) model is trained using these experimental error characteristics for estimation of the error. The ANN model estimated the workpiece dimensional errors with a good accuracy. Error correction is realised via turning of workpieces with a CNC part program which modified based on the estimated error profile. The dimensional errors are reduced approximately by 90% with the proposed method.