Time-series forecasting is one of the most popular applications in deep learning. MXNet enables machine learning enthusiasts to utilize its deep learning framework for various applications including time series forecasting. In this recipe, we will implement a one-to-one forecasting solution using an LSTM network to predict shampoo sales. At the time of writing this book, MXNet supported only two variants of the sequence prediction problem, one-to-one and many-to-one.

# Forecasting with MXNet

# Getting ready

In this recipe, we will use the shampoo sales dataset that contains the monthly sales of shampoo over a 3-year period. The original dataset is credited to Makridakis, Wheelwright, and Hyndman (1998). It is also available...