We apply machine-learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk. By combining customer transactions and credit bureau data from January 2005 to ...April 2009 for a sample of a major commercial bank’s customers, we are able to construct out-of-sample forecasts that significantly improve the classification rates of credit-card-holder delinquencies and defaults, with linear regression
R
2’s of forecasted/realized delinquencies of 85%. Using conservative assumptions for the costs and benefits of cutting credit lines based on machine-learning forecasts, we estimate the cost savings to range from 6% to 25% of total losses. Moreover, the time-series patterns of estimated delinquency rates from this model over the course of the recent financial crisis suggest that aggregated consumer credit-risk analytics may have important applications in forecasting systemic risk.
Securities Trading of Concepts (STOC) DAHAN, ELY; KIM, ADLAR J.; LO, ANDREW W. ...
Journal of marketing research,
06/2011, Letnik:
48, Številka:
3
Journal Article
Recenzirano
Odprti dostop
Identifying winning new product concepts can be a challenging process that requires insight into private consumer preferences. To measure consumer preferences for new product concepts, the authors ...apply a "securities trading of concepts," or STOC, approach, in which new product concepts are traded as financial securities. The authors apply this method because market prices are known to efficiently collect and aggregate private information regarding the economic value of goods, services, and firms, particularly when trading financial securities. This research compares the STOC approach against stated-choice, conjoint, constant-sum, and longitudinal revealed-preference data. The authors also place STOC in the context of previous research on prediction markets and experimental economics. Across multiple product categories, the authors test whether STOC (1) is more cost efficient than other methods, (2) passes validity tests, (3) measures expectations of others, and (4) reveals individual preferences, not just those of the crowd. The results show that traders exhibit a self-preference bias when trading. Ultimately, STOC offers two key advantages over traditional market research methods: cost efficiency and scalability. For new product development teams deciding how to invest resources, this scalability may be especially important in the Web 2.0 world.
Stock markets employ specialized traders, market-makers, designed to provide liquidity and volume to the market by constantly supplying both supply and demand. In this paper, we demonstrate a novel ...method for modeling the market as a dynamic system and a reinforcement learning algorithm that learns profitable market-making strategies when run on this model. The sequence of buys and sells for a particular stock, the order flow, we model as an Input-Output Hidden Markov Model fit to historical data. When combined with the dynamics of the order book, this creates a highly non-linear and difficult dynamic system. Our reinforcement learning algorithm, based on likelihood ratios, is run on this partially-observable environment. We demonstrate learning results for two separate real stocks.