Search

Credit risk prediction heavily relies on historical data provided by financial institutions. The goal is to identify commonalities among defaulting users based on existing information. However, data on defaulters is often limited, leading to a concentration of credit data where positive samples (defaults) are significantly fewer than negative samples (nondefaults). It poses a serious challenge known as the class imbalance problem, which can substantially impact data quality and predictive model effectiveness. To address the problem, various resampling techniques have been proposed and studied extensively. However, despite ongoing research, there is no consensus on the most effective technique. The choice of resampling technique is closely related to the dataset size and imbalance ratio, and its effectiveness varies across different classifiers. Moreover, there is a notable gap in research concerning suitable techniques for extremely imbalanced datasets. Therefore, this study aims to compare popular resampling techniques across different datasets and classifiers while also proposing a novel hybrid sampling method tailored for extremely imbalanced datasets. Our experimental results demonstrate that this new technique significantly enhances classifier predictive performance, shedding light on effective strategies for managing the class imbalance problem in credit risk prediction. [ABSTRACT FROM AUTHOR]

The uniqueness of equilibrium in bargaining games with three or more players is a problem preventing bargaining theory from general real world applications. We study the uniqueness of bargaining equilibrium in a bargaining game of two sellers and two buyers, which has instances in real-world markets. Each seller (or buyer) wants to reach an agreement with a buyer (or seller) on the division of a pie in the bargaining game. A seller and a buyer will receive their agreed divisions if they can reach an agreement. Otherwise, they receive nothing. The bargaining game includes a finite number of rounds. In each round, a player can propose an offer or accept an offer. Each player has a constant discounting factor. Under the assumption of complete information, we prove that the equilibrium of this bargaining game is the same division of two pies. The ratio of division as a function of the discount factors of all players is also deduced. The result can be extended to a bargaining game of n-sellers and n-buyers, which reveals the relevance of bargaining equilibrium to the general equilibrium of a market. [ABSTRACT FROM AUTHOR]

The consumption-based capital asset pricing model (CCAPM) is an attractive research field in finance, and extant studies have examined the impacts of different factors towards traditional CCAPM, intending to improve the model from the practical perspective. In this paper, we comprehensively scrutinize the real economy effects on the CCAPM by comprising expenditure on durable, expenditure on non-durable goods, services, and real estate four factors. Our study pays great attention to the real economy effect on the CCAPM based on two types of portfolios. By employing both time-series and cross-sectional analysis, our empirical results suggest that the real economy factors can help traditional CCAPM to produce better asset pricing results. Particularly, incorporating the real estate component into the CCAPM model can improve its explanation power on the stock market risk. Our results are potentially useful for investors, portfolios managers and policy makers towards the CCAPM. [ABSTRACT FROM AUTHOR]