Time series prediction problems are a difficult type of predictive modeling problem. Unlike regression predictive modeling, time series also adds the complexity of a sequence dependence among the input variables. A powerful type of neural network designed to handle sequence dependence is called a recurrent neural network. The Long Short-Term Memory network or LSTM network is a type of recurrent ne
![Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras - MachineLearningMastery.com](https://cdn-ak-scissors.b.st-hatena.com/image/square/7ec4ea5741336dd42ee7d93bb880fc0a21baad12/height=288;version=1;width=512/https%3A%2F%2Fmachinelearningmastery.com%2Fwp-content%2Fuploads%2F2016%2F07%2FTime-Series-Prediction-with-LSTM-Recurrent-Neural-Networks-in-Python-with-Keras.jpg)