search

borisbanushev / stockpredictionai

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.
4.07k stars 1.65k forks source link

Fundamental analysis using BERT #9

Open dukeng96 opened 5 years ago

dukeng96 commented 5 years ago

Hi Boris,

I really appreciate your amazing work. I am very interested in seeing how you apply BERT into sentiment analysis of news. Could you share how you get the daily news data from 2010? It would be great if you could create a new repo only for BERT.

Thanks! Duke

chillwinston commented 3 years ago

Hi Marvin - we are also trying to understand the data format for the input file for Boris' work, and as you've likely seen - he doesn't seem to supply even the headings / column names, which naturally makes the problem somewhat more laborious than it should be.

Do you have sense of the likely headings for the dataset ?

Some headings are obvious from the code but others are simply missing. Bert is loaded but never appears to be used. We're happy to collaborate somewhat on sourcing data and getting it to run, which will lower the effort overall. Cheers - Alys

suphero commented 3 years ago

I am trying to replicate this work on my repo. I have created a notebook file. I think we should find the missing codes / data on our own. If you are interested my repo path: https://github.com/suphero/stock-prediction-ai