The objective of this study is to determine the surface characteristics such as surface roughness, wettability and surface free energy of medium density fibreboard (MDF) processed with CNC machine and to optimise CNC process parameters by using artificial neural network (ANN). In the study, the cutting tools with three different diameters (6 mm, 8 mm and 10 mm), four different spindle speed values (12,500 rpm, 15,000 rpm, 17,500 rpm and 20,000 rpm) and three different feed rate values (2 m/min, 6 m/min and 10 m/min) were used as CNC processing parameters. In order to determine the surface characteristics of the specimens, surface roughness and contact angle measurements were performed and surface free energy values were calculated according to one of the methods mentioned in the literature. The surface roughness and surface free energy data obtained from experimental studies were analysed with ANN and modelled. The prediction models with the best performance and acceptable deviations were determined by using statistical and graphical comparisons between the ex-perimental data and the prediction values obtained as a result of ANN analysis. By using these prediction models, the data was obtained according to the CNC parameters not used in the experimental study. According to the experimental results, the surface roughness values decreased with increasing the cutting tool diameter and feed rate while the values increased with increasing the spindle speed. Similarly, the highest surface free energy values were generally obtained from the high spindle speed, the low tool diameter and feed rate values. The optimum values of tool diameter, spindle speed and feed rate for the surface roughness values were determined as 6 mm, 20,000 rpm and 2 m/min whilst these values for the surface free energy values were determined as 6 mm, 16,500 rpm, 2 m/min, respectively. The findings of this study could be employed effectively to reduce time, energy and cost for experimental investigations in the interior decoration and furniture industry. (C) 2021 CIRP.