CreditPulse is based on the underlying principle that textual analysis offers better insights over number crunching. We employ Machine Learning techniques to carry out textual analysis of recent SEC filings with those of bankrupt companies just before their bankruptcy filing.
Our daily output then categorizes companies into either 'High Risk' or 'Low Risk' for the upcoming two to three quarters.
CreditPulse has been built and tested on 10 years of real market data and our model has given 90% plus accuracy on the test datasets.