The electrochemical degradation of persistent organic pollutants such as chloroquine (CQ) is widely utilized to reduce the hazardous from wastewater. This research is concerned with the modeling of the electrochemical degradation of CQ by leveraging machine learning techniques, such as Artificial Neural Network (ANN). Specially, an ANN employing a central composite design (CCD) was developed to analyze the influence of key variables, including initial pH (pH0), current density (j), and volumetric flow rate (Q) on the degradation efficiency of CQ. The prediction model was successfully developed using the artificial neural network (ANN) method. The degradation efficiency of CQ was accurately forecasted through the ANN model, which was quantified as \(\eta_{i,pred} = \sum\limits_{j = 1}^{m} {u_{j} \tan h\left( {\sum\limits_{h = 1}^{H} {w_{h} x_{h} + \beta_{j} } } \right)} + \beta_{2}\) . The ANN model demonstrated high prediction accuracy, with an R2 value of 0.9960 and a low root mean square error (RMSE) of 0.88. Current density, contributing 55.46%, was identified as the most significant factor in the electrochemical degradation of CQ and the initial pH was the least influential factor, contributing 20.71%.