The invention relates to a method for training a model for predicting occurrence of an epileptic seizure, the method comprising performing a supervised training over a training dataset of a nonlinear binary classification model configured to receive as input the evaluation, by a patient, of the intensity of each prodromal symptom among a predefined set of prodromal symptoms, and to output a classification of said patient belonging either to a pre-ictal or inter-ictal state, and the training dataset comprises data inputs obtained from a plurality of epileptic patients, each data input comprising an evaluation, by a patient, of the intensity of each of the predefined set of prodromal symptoms, each data input being further associated to an indication of said patient belonging to a pre-ictal or inter-ictal state at the time of the evaluation. The invention also relates to a prediction model obtained accordingly, and a computing device for implementing said prediction model.