News for hackers. Stuff that matters.

A comment on Using a Keras Long Short-Term Memory Model to Predict Stock Prices. Parent comment

Re:Using a Keras Long Short-Term Memory Model to Predict Sto... by vl on Friday November 09, 2018 @02:04PM (#18416952)
Even more so since test data can't be from the same time range: i.e. for time series you need to split train/test by date, not randomly, otherwise your model just memorizes the series.
[ Parent | on HN ]
Re:Using a Keras Long Short-Term Memory Model to Predict Sto... by goodside on Saturday November 10, 2018 @12:46AM (#18420141)
It's standard practice to validate forecasts on non-randomized test/validation splits of the same time series, since this simulates the conditions where the model will be deployed in reality: It will know everything there is to know about the past, and it will know nothing about the future.

See Hyndman's fpp2 — https://otexts.org/fpp2/accuracy.html

Also, his description of rolling window validation: https://robjhyndman.com/hyndsight/rolling-forecasts/

[ Parent | on HN ]
Re:Using a Keras Long Short-Term Memory Model to Predict Sto... by ipsa on Friday November 09, 2018 @04:24PM (#18418164)
The article splits in time, not randomly.
[ Parent | on HN ]