Open anwar11235 opened 3 years ago
I am trying to run this notebook as is with latest IBM stock price data but the model ends up predicting the same flat-line
Per the author, this is expected:
https://towardsdatascience.com/stock-predictions-with-state-of-the-art-transformer-and-time-embeddings-3a4485237de6#03a4
Reportedly, a linear model is the best that the approach can produce given the limited price/volume data of a single stock:
I am trying to run this notebook as is with latest IBM stock price data but the model ends up predicting the same flat-line