Credit Rating Transistion using Financial & Text Analytics
BRIEF SYNOPSIS OF WORK ON CREDIT RATING TRANSISTION
The credit rating of financial instruments is one of the factors that play a significant role while making investment decisions. Credit rating companies provide information about the credit stability/ transitions (deterioration/ up gradation) of the debt instruments using financial parameters, industry parameters, and external environment at quarterly intervals. In the present scenario, investment managers have to wait for quite some time to know about the credit rating stability/ transition. We propose that incorporating the market news available from different sources in almost real time along with the usual financial parameters should be able to predict the rating stability/ transition well in advance. The present work focus on incorporating sentiment scores extracted from various news sources like new aggregators like Bloomberg, Reuters, Company Web sites, Blogs etc. Depending upon the source of news a weight will be given taking into consideration trust worthiness of the source, Location of the Company information in the body of the news, Frequency of appearance. Using deep learning weights are assigned to each source. A Composite Sentiment score is computed as weighed average of the various individual news sources. This composite score is additional Input along with other financial parameters about eleven to survival analysis which in turn will forecast credit events. Our results show that Return on Capital Employed ROCE and Interest cover ratio along with sentiment scores are the best predictor variables to predict the rating stability/ transition. We tested our methodology on about three hundred companies. Most of them are from mining & textile segment as majority of downgrades and rating transitions have happened in those sectors. Back testing results show that proposed model very well predicts the credit rating stability/ transition. Without using the sentiment score the prediction accuracy of a transition was about 45% on hold out Samples (About 30 of 300) and with Financial and sentiment score it went up to about 70%. This work will be very helpful from the regulatory point of view also as one has to compute the Future value of Loan portfolio ie Credit Risk VAR. This method computes the Credit Risk VAR much accurately compared to existing methods of Credit Risk Computation.
Other outcome of this work is to predict crossover of rating from a given threshold. As an example the current rating may be Baa . After what point in time it will cross over to Ba. This is different from what transition Matrix gives. It gives for a given duration say a Year what is probability of change where as our method can tell when the change will take place it need not be at year intervals.
We have filed a provincial patent for this work.
Prof S Chandrasekhar B.Tech,M.Tech(IIT-K),PhD(USA)
Sr Prof & Director - Business Analytics
IFIM Business School B :lore
What Problem we are trying to solve
Development of work
Help in early warning of Credit Risk
BRIEF PROFILE OF PROF. S.CHANDRASEKHAR
Prof S Chandrasekhar is Senior Prof & Director Business Analytic at IFIM Business School B “Lore since Nov 2013. He has about 40+ yrs of experience in Industry & academics out of which about 15+ years in Analytics.
He was chair Professor (July 1998-Feb 2013) & Director at FORE School of Management, New Delhi
Prior to this he worked at Indian Institute of Management, Lucknow for about ten years(1988-98) as Professor in the area of Computers & information Systems. Member Secretary of IIM L Governing Board for about three years.
He holds a Bachelor’s degree in Electrical Engineering, Master’s degree in Computer Science from IIT, Kanpur and Doctorate in Quantitative &Information Systems from University of Georgia, USA. Worked in India, USA and Canada in reputed organizations like TIFR, ISRO, NRSA, FORD Aerospace Corporation, National Research Council before joining IIM, Lucknow. Awarded UNDP fellowship for study in Advanced Computer Systems design. Worked in the area of Neural Network, Forecasting using Statistical Techniques, Mathematical Modeling, and Data Warehousing/Data Mining.
Professor Chandrasekhar is a Fellow of the Institution of Electronics & Telecommunication Engineers, Fellow of Institution of Engineers, and Fellow of Association for Information Systems and Senior Member of Computer Society of India. Published papers in National and International Journals and also presented papers at various International Conferences, Chaired sessions at Intl/National level conferences, Guided students for their Masters and Doctoral Work.
Consultant to various industries in the area of Business Intelligence, Predictive/Descriptive Analytics, Risk management