Magnetic field assisted abrasive finishing process (MFAAF) is a new technique that uses magnetic field, mixture of abrasives and iron particles for finishing the workpieces with high level of surface quality. In the present work, the MFAAF of SS304L work material was investigated. The parameters chosen were voltage supplied to the electro magnet, machining gap, rotational speed of electro magnet and % Fe in magnetic abrasive particles. The selected parameters were utilised to construct the linear regression and Artificial Neural Network (ANN) models to predict the percentage improvement of surface roughness (%ΔRa). The results show that the ANN model fits the experimental data better than the linear regression model. The ANN model was used for analysing the effect of process parameters on %ΔRa. The %ΔRa values predicted by ANN model are in good agreement with the experimental values and the maximum deviation of 5.4% was obtained between the model and experiment. © Research India Publications.