I wrote a scraper that downloads 10-Ks from the SEC and then built a simple analysis based on high dividends/stock buybacks and a discounted cash flows analysis. It found some pretty undervalued companies that ended up doing fairly well over the last year, but not as well as the tech stocks.
As others noted the datasets are not really standardized even with the SEC Edgar data so there is a lot of massaging you have to do.
As others noted the datasets are not really standardized even with the SEC Edgar data so there is a lot of massaging you have to do.