The problem that you cant normalize data in 0–1 interval, and this work while you predict data on numbers that you now, but try to normalize your data on train set, and data for validation set independently and the check the result. Cause right now you have future biased data(you use future data to normalize current data)
--
Machine Learning and Computer Vision Researcher. Founder LearnML.Today
Love podcasts or audiobooks? Learn on the go with our new app.