This paper deals with the behavior of the crosslinked polyethylene (XLPE) used as high-voltage power cable insulation under ultraviolet (UV) radiations. For this, XLPE samples have been irradiated for 240 h using low-pressure vapor fluorescent lamps. Electrical (surface and volume resistivities), mechanical (tensile strength, elongation at break and surface hardness) and physical (weight loss, water absorption, work of water adhesion and contact angle) tests have been first carried out. Experimental results show that the XLPE characteristics are affected by UV radiation. Indeed, a decline in surface resistivity, mechanical properties, and contact angle, and an increase in the water retention amount and weight loss have been recorded. In order to predict and extrapolate some XLPE properties, a supervised artificial neural network (ANN) trained by Levenberg-Marquardt algorithm has been designed. The collected database is used to train and test the ANN performance. The obtained results show that the proposed ANN algorithm presents good estimation and prediction since the predicted output values agree with the experimental data.