The identification of appropriate empirical relationships between cutting force coefficients and the uncut chip area is crucial for the successful implementation of mechanistic models in estimating cutting forces for flat-end milling operation. The derivation of empirical relationships necessitates machining experiments to record cutting force components under diverse conditions. The experimental data collected from force sensors (mainly dynamometers) contains outliers and noise that deteriorate the goodness of fit and thereby prediction accuracy of the model. This paper presents an application of the Gaussian approach to refine experimentally measured force data by systematically eliminating outliers and noise, followed by the use of pre-processed data to derive empirical relationships. The proposed methodology is implemented in the form of a computational tool to eliminate irrational data points automatically and obtain meaningful cutting force coefficients relationships using regression models. The outcomes of the study are substantiated further by conducting a set of experiments over a wide range of cutting conditions. The root mean square error (RMSE) of measured and predicted cutting forces is estimated for models with and without a data refining approach, which showed marked improvement in the prediction accuracy. Based on the outcomes of the present study, it can be concluded that the prediction ability of the mechanistic force model can be improved considerably with the augmentation of the Gaussian approach. © 2020, Springer-Verlag London Ltd., part of Springer Nature.