Consumer credit risk: Individual probability estimates using machine learning

Consumer credit scoring is often considered a classification task where clients receive either a good or a bad credit status. Default probabilities provide more detailed information about the creditworthiness of consumers, and they are usually estimated by logistic regression. Here, we present a general framework for estimating individual consumer credit risks by use of machine learning methods. Since a probability is an expected value, all nonparametric regression approaches which are consistent for the mean are consistent for the probability estimation problem. Among others, random forests (RF), k-nearest neighbors (kNN), and bagged k-nearest neighbors (bNN) belong to this class of consistent nonparametric regression approaches. We apply the machine learning methods and an optimized logistic regression to a large dataset of complete payment histories of short-termed installment credits. We demonstrate probability estimation in Random Jungle, an RF package written in C++ with a generalized framework for fast tree growing, probability estimation, and classification. We also describe an algorithm for tuning the terminal node size for probability estimation. We demonstrate that regression RF outperforms the optimized logistic regression model, kNN, and bNN on the test data of the short-term installment credits.     

Application of a new algorithm using Doppler information to retrieve complex wind fields over the Black Sea from ENVISAT SAR images

Several algorithms have been proposed to retrieve near-surface wind fields from C-band synthetic aperture radar (SAR) images acquired over the ocean. They mainly differ in the way they retrieve the wind direction. Conventionally, the wind direction is taken from atmospheric models or is extracted from the linear features sometimes visible in SAR images. Recently, a new wind retrieval algorithm has been proposed, which also includes the Doppler shift induced by motions of the sea surface. In this article, we apply three wind retrieval algorithms, including the one using Doppler information, to three complex wind events encountered over the Black Sea and compare the SAR-derived wind fields with model wind fields calculated using the high-resolution weather research and forecasting (WRF) model. It is shown that the new algorithm is very efficient in resolving the 180° ambiguity in the wind direction, which is often a problem in the streak-based wind retrieval algorithms. However, the Doppler-based algorithm only yields good results for wind directions that have a significant component in the look direction of the SAR antenna. Furthermore, it is dependent on good separation of the contributions to the Doppler shift induced by surface currents and wind-related effects (wind drift and wind-sea components of the ocean wave spectrum). We conclude that an optimum wind retrieval algorithm should consist of a combination of the algorithms based on linear features and Doppler information.     

Direct comparison between hot pressing and electric field-assisted sintering of submicron alumina

This study compares hot pressing (HP) and the electric field-assisted sintering technique (FAST) of two different electrically insulating Al₂O₃ submicron powders with median particle sizes of 150 and 500 nm. Sample geometry, heating schedule, applied pressure and atmosphere were identical for both sintering methods. The densification behavior and characterization of the microstructure revealed that FAST sintered samples reached a higher density compared with HP, in particular for the finer powder. It was found that an increase in dwell time was required to reach the same final density by HP. However, analysis of the sintering curves showed that the densification mechanism for both sintering methods was grain boundary diffusion. Increasing the heating rate up to 150 K min^?1 did not modify the densification mechanism. The sintering trajectory showed that the grain size was only dependent on density and was insensitive to the sintering method, in addition to showing a lack of preferential grain orientation.     

Vorwort der Herausgeber

Ohne Zusammenfassung     

Infrared Evidence for the Existence of Nitrate Species on Cu-ZSM5 During Isothermal Rate Oscillations in the Decomposition of N2O

Isothermal oscillations in the rate of decomposition of N₂O were studied on an over-exchanged Cu-ZSM-5 catalyst by mass spectroscopy and in situ transient FTIR. Oscillations in the production of O₂ and N₂ were observed to occur in a temperature range of 410–490°C at a total pressure of 1.0 Torr pure N₂O. FTIR has provided the first spectroscopic evidence that surface nitrate species are present under oscillatory conditions. This study confirmed a previously proposed model that predicts a slow build-up of surface nitrates, followed by a rapid nitrate decomposition coupled with an increase in the rate of N₂O decomposition. The IR signature of the surface nitrates suggests they are monodentate nitrate species bound to Cu²⁺ ions. Temperature-programmed desorption studies reveal a strong correlation between the stability of the surface nitrate species and the temperature range in which oscillations occur.     

Material property requirements for analysis and design of UHTC components in hypersonic applications

Analytical modeling of thermal and mechanical response is a fundamental step in the design process for ultra-high-temperature ceramic components, such as nose tips and wing leading edges for hypersonic applications. The purpose of the analyses is to understand the response of test articles to high-enthalpy flows in ground tests and to predict component performance in particular flight environments. Performing these analyses and evaluating the results require comprehensive and accurate physical, thermal, and mechanical properties. In this paper, we explain the nature of the analyses, highlight the essential material properties that are required and why they are important, and describe the impact of property accuracy and uncertainty on the design process.     

Personal self-regulation of development: Cross-sequential analyses of development-related control beliefs and emotions.

This study is part of a larger research project centering on personal self-regulation of development in adulthood. Cross-sectional, longitudinal, and correlational findings are presented for selected parameters of personal development (subjective developmental attainment, self-corrective tendency, personal control over development, depressive outlook on personal development, and perceived marital support) derived from questionnaire data. The findings highlight the importance of development-related control efforts and beliefs for achieving a subjectively favorable balance of developmental gains and losses and for maintaining an optimistic perspective in middle and later adulthood. Results are discussed with reference to a theoretical model of development-related control activities. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Influence of the suspension media on the thermal treatment of mesophilic lactococcal bacteriophages

The thermal resistances of the Lactococcus lactis phages P008 (a heat-sensitive wide-spread phage) and P680 (a heat-resistant phage) suspended in milk and in solutions supplemented with milk components were studied to elucidate the protective role of milk on phage inactivation. For both phages a decrease of inactivation was observed in casein solution. Furthermore, the inactivation kinetics of the phages in whey, in whey cream (3.5%, 20%, 30% fat) and in whey protein concentrate (0.7%, 5%, 10% protein) were tested. The inactivation experiments in whey cream and in whey protein concentrate having different concentrations of fat and protein revealed that fat had no influence on the inactivation, while, in contrast, the presence of protein had a protective effect.