I preliminarily did the same thing as in this article a while back (with crypto data, since it's easily accessible), just as a way to learn keras.

Somehow my network always learned to output a delay of the input no matter how hard I tried to shape it. I've searched through literature briefly and some examples. Some blog posts even claimed they had good time series prediction when I clearly saw they were having the same problem.

What I mean to say is, be critical of what you find online, and be critical of your results. This is definitely not an easy problem, and some argue that it's unsolvable all together :)