Topological applications of multilayer perceptrons and support vector machines in financial decision support systems

Abstract

The heart of this study is particularly on risk assessment of financial decision support systems (FDSSs), to advance the model performance and improve classification accuracy. To conquer the downsides of the classical models, statistical intelligence (SI) technologies, for example, multilayer perceptrons (MLPs) and support vector machines (SVMs), have been deliberated in FDSS applications. Recently, the prestigiousness of SI approaches has been confronted by the latest prediction learners. Therefore, to ensure the competitive performance of SI mechanisms, the current investigation scrutinizes the topological applications of MLPs and SVMs over eight different databases with equivalent combinations in credit scoring and bankruptcy predictions example sets. The experimental results reveal that MLP5‐5 and MLP4‐4, that is, the sigmoid activation function with five and four hidden layers, are the feasible topologies for the MLP algorithm, and on all databases in all performance criterions, SVM trained with the linear kernel function (SVM‐1) achieves better prediction results. From the “Baseline” family, random forest learner brings significant improvements in financial decisions. Lastly, FDSSs are found to be correlated with the nature of databases and the performance criterions of the trained algorithms. The results of this study, however, have practical and managerial implications to make a range of financial and nonfinancial strategies. With these contributions, therefore, our study not only supplements earlier evidence but also enhances the predictive performance of SI algorithms for financial decision support applications.

Deep learning-based exchange rate prediction during the COVID-19 pandemic

“…The amount of data for the pre-COVID-19 time period (2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018)(2019) was 5216 daily observations for all the used currencies, and for the COVID-19 period 571 observations. The training set of the pre-COVID-19 dataset was cross validated tenfold to minimise the training error and enhance the generalizability of the forecasting outcome (Abedin et al, 2019).…”

An ensemble machine learning approach for forecasting credit risk of agricultural SMEs’ investments in agriculture 4.0 through supply chain finance

“…Furthermore, our model is perfect when dealing with small datasets. The use of RotF was found to be robust and stable than extreme ML, SVM, and neural networks, especially with small training sets (Abedin et al, 2019 ; Han et al, 2018 ). Thus, our model would be of great usefulness for SMEs that particularly deal with small datasets.…”

Loan default prediction of Chinese P2P market: a machine learning methodology

“…Abedin et al assessed the risk of financial decision support systems (FDSSs) and applied MLPs and SVMs in credit scoring and bankruptcy prediction. They confirmed that MLP5‐5 and MLP4‐4 are practicable topologies for the MLP algorithm, and the linear kernel function-trained SVM has better performance in prediction 47 .…”