This article presents the results of empirical research dedicated to default prediction among Russian commercial banks. The data used in the study include monthly balance sheet information on Russian banks in post-crisis period from 1 January 2010 until 31 December 2011. Factors characterizing theф financial stability of banks were obtained using binary logistic regression. With the help of these factors it becomes possible to identify problem banks 5 months prior to their failure.
In this article Russian stock market information efficiency is analyzed. The quantitative measure of the analysis is the indicator of Shannon entropy. On the basis of logit model the relation between the level of information efficiency and financial crisis probability is investigated.