Forecasting with Deep Learning
This work addresses forecasting challenges for data analysts, but it is incremental as it applies existing deep learning methods without major innovations.
The paper tackles time series forecasting using deep learning, finding that networks can learn from single series with repeating patterns but perform no better than a naive baseline on unstructured data like stock prices.
This paper presents a method for time series forecasting with deep learning and its assessment on two datasets. The method starts with data preparation, followed by model training and evaluation. The final step is a visual inspection. Experimental work demonstrates that a single time series can be used to train deep learning networks if time series in a dataset contain patterns that repeat even with a certain variation. However, for less structured time series such as stock market closing prices, the networks perform just like a baseline that repeats the last observed value. The implementation of the method as well as the experiments are open-source.