Openly available data?

I’m currently working on some research that would apply artificial intelligence to data, trying to extract patterns. However, we need data to mine. I was wondering if anybody knows of a place where I could find openly available data.

It seems that some sources of data like at patientslikeme.com cost money, but this is for university use, not commercial use.

What kind of data are you looking for, QS-style data, or any data susceptible to machine learning? And how big a dataset are you looking for?

I have a 3,000 record, 400+ variable Excel SS data set. I need to relate the input variables (exercise, treatments, supplements, nutrition, & drugs) with cancer & bio-markers with a view determining what, if anything, of the input variables effects the changes in cancerousness.

So I would welcome your help in this.

Ian

See also this thread: http://forum.quantifiedself.com/thread-data-analysis-software

This is just what I’m looking for! If I email you my email address, could you send over your data. I am hoping our AI software will be able to extract patterns within your data.


I guess it would be data formatted like:

Input variables (exercise, amount of sleep, nutrition, etc.) and output variables to test for (biomarkers, etc.). Basically QS style data, tracking yourself each day and attempting to find whether certain variables affect you in different ways.

I think the bigger the dataset the better.