The negative effect of financial crimes on financial institutions has grown dramatically over the years. To detect crimes such as credit card fraud, several single and hybrid machine learning approaches have been used. However, these approaches have significant limitations as no further investigation on different hybrid algorithms for a given dataset were studied. This research proposes and investigates seven hybrid machine learning models to detect fraudulent activities with a real word dataset. The developed hybrid models consisted of two phases, state-of-the-art machine learning algorithms were used first to detect credit card fraud, then, hybrid methods were constructed based on the best single algorithm from the first phase. Our findings indicated that the hybrid model Adaboost + LGBM is the champion model as it displayed the highest performance. Future studies should focus on studying different types of hybridization and algorithms in the credit card domain.

Corporate governance practices have been a concerned issue by many Asian countries after the Asian Financial Crisis in 1997 including Malaysia. Due to the crisis, Malaysian Code of Corporate Governance (MCCG) has been introduced as part of the Bursa Malaysia (BMB) listing rules. This study hence focuses on corporate governance practices among Top 100 public listed companies in Bursa Malaysia and the relationship between corporate governance practices with firm performance. Two corporate governance's indicators (Board size and Board Independence) were chosen in testing the hypothesized relationship between corporate governance practices with firm performance, which was measured by return on asset (ROA) and return on equity (ROE). Descriptive and correlation analysis were used to examine the hypotheses in this study. The result showed that board size has significantly weak negative relationship with ROA but it was found to be insignificant to ROE. The other finding indicated that there was no relationship between board independence and firm performance. This study provide useful information for policy makers or regulators in improving the corporate governance policies in the future and also helps in increasing understanding on the relationship between corporate governance practices and firm's performance

With the spread of m-commerce usage around the globe, mobile commerce can become the primary approach for many users in transactions. Such a method is considered an innovative way for the financial wallet but with some encumbrances. Trust in mobile commerce is one of the challenges yet to receive in-depth studies regarding linear and non-compensatory relationships. This study aims to evaluate the determinants of trust in mobile commerce using hybrid three-stage Fuzzy Delphi-Structural Equation Modeling (SEM)-Artificial Neural Network (ANN) approach. A hybrid approach was performed on 344 users mobile-commerce activities. The results of this study provide valuable insights for mobile commerce firms to come up with effective plans that increase customer trust in mobile commerce. Practically, the relative importance of specific determinants of trust in mobile commerce contributes to providing deep insight into the factors of customer trust in mobile commerce. The proposed model predicts 94.80% trust in mobile commerce with social presence and social support theories. A novel perspective was provided in this study to encourage e-marketing among consumers to persuade customers to trust mobile commerce.

There are continued efforts to build on the performance of deep learning (DL) models in various fields of application. Developing new DL models continues to open unprecedented opportunities in diverse application areas despite the enormous resources required. Generally, the learning mechanism of DL models depends on the term "cost function" (CF) or "loss function" (LF), and DL models require varied hyperparameter settings and, precisely, parameters that can help the model to continually minimize the cost function until faster convergence, with better generalization over the data in the loss landscape, is assumed. The learning rate (LR) update seeks to find the optimal solution for DL models through relative cost function minimization. Therefore, selecting the appropriate LR is essential to the performance of DL models. The existing cosine annealing LR, despite its demonstration for fast model convergence, lacks complete loss landscape exploration of the flat minima, hence limiting its ability to model better generalization. To address this, the paper proposes a period-shift Cosine Annealing Learning Rate with warm-up epochs (ps-CALR) to perturb the LR update. Six different publicly available datasets were used to benchmark the proposed LR method by experimenting with custom DL (multilayer perceptron and convolutional neural networks) and pre-trained DL models. The proposed ps-CARL enhances model generalization and convergence, pushing the solution to notably better performance compared with fixed LR and the existing cosine annealing method.

Purpose: This study examines the effect of open-mindedness (OM) and humble behavior on innovation through the mediator role of learning.Design/methodology/approach: A quantitative design was adopted to collect data through a questionnaire-based survey distributed to 400 employees at international oil companies operating in Iraq.Findings: The results indicate a direct positive of learning on innovation. Hence, there is a natural and partial indirect effect of humble behavior on innovation and a full indirect impact of OM on innovation through learning.Research limitations/implications: The theoretical and practical implication of this study indicates that individual learning on innovation is vital when the workplace environment has a diversity of cultural backgrounds. Moreover, the implications of this study may contribute to determining the weakness of invention in such industries because of the effect of personal characteristics (i.e. OM and humble) on readiness to learn.Originality/value: In a culturally diverse work environment, the behavior of humble and OM will have a significant impact on the intensity of individual learning, which would increase innovation in the context of the oil industry. Therefore, the essence of originality in this study is to lead the managers to pay attention to the psychological aspects of the workplace environment that require learning and innovation.