Amir E. Khandani

TL;DR: This paper applied machine learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk, which significantly improved the classification rates of credit-card-holder delinquencies and defaults with linear regression R-squared's of forecasted/realized delinquencies of 85%.

TL;DR: The authors hypothesize that the losses were initiated by the rapid unwinding of one or more sizable quantitative equity market-neutral portfolios, possibly due to margin calls or a risk reduction, and that the main driver of the losses in August 2007 was the resale liquidation of similar portfolios that happened to be quantitatively constructed.

TL;DR: This article applied machine learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk, which significantly improved the classification rates of credit-card-holder delinquencies and defaults, with linear regression R2's of forecasted/realized delinquencies of 85%.

TL;DR: A dynamic-programming-based algorithm for finding the optimal route in an arbitrary network, as well as suboptimal algorithms with polynomial complexity are developed and shown that these algorithms can achieve average energy savings of about in random networks, as compared to the noncooperative schemes.

TL;DR: In this article, the authors find evidence that the unwinding of these portfolios began in July 2007 and continued until the end of 2007, suggesting that the Quant Meltdown of August 2007 was the combined effects of portfolio deleveraging throughout July and the first week of August, and a temporary withdrawal of marketmaking risk capital starting August 8th.