Recurrent Neural Networks (RNNs) has over the years shown to have increasing relevance and importance in the industry. RNNs have gained huge popularity because of its ability to classify and predict sequential data. One example of such kind of data is ABC notated music. Using a dataset of songs, this project will present one possible solution to build a predictor using RNN. We will use Long short-term memory (LSTM), a well known RNN architecture, for this mission