Dataset Details - Githubissues

gmihaila / stock_risk_prediction

Stock risk prediction based on annual financial report (10K) risk factors section 1A

MIT License

2 stars 2 forks source link

Dataset Details #1

Closed gmihaila closed 4 years ago

gmihaila commented 4 years ago

Possible data source: 10-K parse files at https://sraf.nd.edu/data/ (#2 in the link)

It has elaborate description about how he cleaned the file.
Our sample will be all firms from 2005 -2018 that have filed their 10-K reports only.
Section 1A (risk section) of 10K is what we are interested in. * Section 1A reporting became mandatory from 2005.
Some of the firms in 2005 may not have section 1A in their 10K reports. You can skip those as well for now.
The firms have voluntarily disclosed the risk info before 2005 in Item 1: Business section but it is not that structured.

gmihaila commented 4 years ago

@Jagdish05 Dr. Albert suggested we could use the data from stock2vec, but unfortunately the link is not available anymore.

I looked at Quandl and found a way to download some csv's: https://blog.quandl.com/getting-started-with-the-quandl-api

I will do a little more research to figure out what would be the input - output of the model, where would we get the risk from.

Jagdish05 commented 4 years ago

sure I also try to find other dataset

gmihaila commented 4 years ago

@Jagdish05 Did you find any datasets? You said you will try to find other datasets. How did that work? Can you please share some findings with me? Maybe they are better.

gmihaila commented 4 years ago

My findings:

Main Dataset: S&P 500 stock data
Download detailes for each company: S&P 500 Companies with Financial Information

Jagdish05 commented 4 years ago

I tried to find dataset but i didn’t make out

On Sat, Apr 11, 2020 at 11:22 AM George Mihaila notifications@github.com wrote:

My findings:

-

Main Dataset: S&P 500 stock data https://www.kaggle.com/camnugent/sandp500

Download detailes for each company: S&P 500 Companies with Financial Information https://datahub.io/core/s-and-p-500-companies-financials#resource-s-and-p-500-companies-financials_zip

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/gmihaila/stock_risk_prediction/issues/1#issuecomment-612456883, or unsubscribe https://github.com/notifications/unsubscribe-auth/AE7HBLYHNJZUQOIP5XI6D2LRMCKKXANCNFSM4K4NRLEA .