Predictive maintenance plays a major role in operational cost reduction in several industries and the railway industry is no exception. Predictive maintenance relies on real time data to predict and diagnose technical failures. Sensor data is usually utilized for this purpose, however it might not always be available. Events data are a potential substitute as a source of information which could be used to diagnose and predict failures. This thesis investigates the use of events data in the railway industry for failure diagnosis and prediction. The proposed approach turns this problem into a sequence classification task, where the data is transformed into a set of sequences which are used to train the machine learning algorithm. Long Short-Term Memory neural network is used as it has been successfully used in the past for sequence classification tasks. The prediction model is able to achieve high training accuracy, but it is at the moment unable to generalize the patterns and apply them on new sets of data. At the end of the thesis, the approach is evaluated and future steps are proposed to improve failure diagnosis and prediction.