RESUMEN
In recent years, there has been growing interest in the prediction of financial market trends, due to its potential applications in the real world. Unlike traditional investment avenues such as the stock market, the foreign exchange (Forex) market revolves around two primary types of orders that correspond with the market's direction: upward and downward. Consequently, forecasting the behaviour of the Forex behaviour market can be simplified into a binary classification problem to streamline its complexity. Despite the significant enhancements and improvements in performance seen in recent proposed predictive models for the forex market, driven by the advancement of deep learning in various domains, it remains imperative to approach these models with careful consideration of best practices and real-world applications. Currently, only a limited number of papers have been dedicated to this area. This article aims to bridge this gap by proposing a practical implementation of deep learning-based predictive models that perform well for real-world trading activities. These predictive mechanisms can help traders in minimising budget losses and anticipate future risks. Furthermore, the paper emphasises the importance of focussing on return profit as the evaluation metric, rather than accuracy. Extensive experimental studies conducted on realistic Yahoo Finance data sets validate the effectiveness of our implemented prediction mechanisms. Furthermore, empirical evidence suggests that employing the use of three-value labels yields superior accuracy performance compared to traditional two-value labels, as it helps reduce the number of orders placed.
RESUMEN
This paper analyzes the efficacy of microprudential (bank-level) capital requirements in mitigating failure cascades in a network of interconnected banks. In simulation exercises, microprudential capital requirements redistribute the troubled assets of undercapitalized banks more broadly within the network, reducing the immediate likelihood of individual bank failures but increasing the likelihood of large failure cascades. This effect is strongest for simulation parameters that mimic economic downturns. If banks increase leverage in response to weaker capital requirements, failure cascades increase only minimally. These results suggest that current microprudential capital requirements might be counterproductive to the goal of mitigating bank failure cascades.
RESUMEN
This paper has scrutinized the process of testing market efficiency, data generation process and the feasibility of market prediction with a detailed, coherent and statistical approach. Furthermore, attempts are made to extract knowledge from S&P 500 market data with an emphasize on feature engineering. As such, different data representations are provided through different procedures, and their performance in knowledge extraction is discussed. Amongst the neural networks, Long Short-Term Memory has not been adequately experimented. LSTM, because of its intrinsic, considers the long-term and short-term memory in its computations. Thus, in this paper LSTM is further examined in return prediction and different preprocessing methods are tested to improve its accuracy. This study is conducted on market data during September-2000 to February-2021. In order to extend the amount of knowledge extracted from financial time series, and to select the best input features, the advantage of Principal Component Analyze, Random Forest, Wavelet and the LSTM's own deep feature extraction procedure are taken, and 4 models are compiled. Subsequently, to validate the performance of the models, MAE, MSE, MAPE, CSP and CDCP are calculated. Results from Diebold Mariano test implied that although LSTM neural network has gained a lot of attention recently, it does not significantly perform better than the benchmark method in S&P 500 index return prediction. Yet, results from Wilcoxon signed rank test showed the significance of improvement in the predictions performed by the combination of Principal component analysis and LSTM.
RESUMEN
@#The use of child restraints such as car seats or booster seats inevitability increases with the implementation of laws mandating its use in the general public. This is of great importance to child health and injury prevention as child restraint use has been shown to reduce the risk of serious injury by 71% to 82% for children less than 1-year-old, and 45% for children aged 4 to 8 years old.2,3 In terms of averting death, child restraints were associated with 28% reduction in risk for death.4 It has been found that using ageand size-appropriate child restraints is the best way to save lives and reduce injuries in a crash.5 It is reasonable, therefore, that one study that investigated the association between child restraint law implementation and traffic injury rate among 4 to 6 years old children in New York State found that these children experienced an 18% reduction in traffic injury rate. (See full-text for continuation).