Digital Financial Reporting

Imagine that you actually wanted to make use of XBRL-based information for analysis of the financial information of companies.  What exactly would you need to do?

First, you have to perhaps go to the RSS feed the SEC provides for filings.  You have to grab the filings you want to analyze.  You have to get the information from the filings.  You have to adjust for errors in the information. Etc.

Well, here is some data to play with.  This is for a set of 15 companies, about 8 years of machine readable information, all 15 entities use exactly the same reporting style, I picked companies where there is a minimal amount of errors in the reports so there is not a lot of adjustments needed for mistakes.

Here is a test set of filings that you can use.  I provide pointers to the filings.  I have tested the information to make sure there are not many errors.  The information is for 15 banks, each of their filings, 10-Qs and 10-Ks since the SEC started using XBRL:

1. List of reports in human readable form. (Just to visualize what is here)
2. Same list in machine readable RSS. (Computer can work with this)
3. Extraction/validation tool. (This shows you how to put the pieces together; however, the mappings, impute rules, and consistency checks are HARD CODED)
4. Metadata (mapping rules, impute rules, consistency checks) for all companies. (Allows you to dynamically map, impute, and test for consistency for any of the 76 reporting styles)
   1. Schema for rules for this specific reporting style.
   2. Mapping rules.
   3. Consistency checks and impute rules. (This is by network)

Let me know what you come up with.