Rows contain stock symbols. Columns contain fundamental data and 1 year (2008 - 2014) of minute-by-minute price data for S&P 500 stocks or EOD data for all equities + up to 5 columns you can define, represented by keywords or concepts you choose. Dataset generation is based on public & private databases, an army of human curators and data triangulation.
Dataset production platforms:
What kind of things can be done with custom concept columns & features?
How do the concepts & trends correlate to crypto, stocks or ETFs?
Scores range from 0 to 1 and represent strength of known and hidden relationships between a concept and a stock, option or ETF. The score is calculated based on a series of algorithms that monitor data surrounding each company associated to the underlying security where each score is combined with scores from human curation teams. These concepts can then be factored or parameterized for exploring new signals or building new models. [Ref: Equity Correlations - J.P. Morgan]
Example use case:
Returns for Playstation, Helium, Korea, Shampoo, & Coffee in comparison to the S&P 500: (interactive)
Google Search Trends for Batteries, Bioengineering, Graphene, Blockchain & Machine Learning