A deep learning framework for financial time series using stacked autoencoders and long-short term memory
Most accurate machine deep learning model type?
This appears to use LSAM and SAE (long short term memory and stacked auto encoders) which appears to be more accurate than recurrent neural network (RNN). Do I sound like a machine learning experience here? Haha. I am way off it. This does show that this technique could be most accurate when it comes to forecasting financial time series.
Here are the links
Python code example https://github.com/dzitkowskik/StockPredictionRNN
FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!