Search results

Purpose: This chapter aims to examine machine learning (ML) models for predicting credit card fraud (CCF).

Need for the study: With the advance of technology, the world is increasingly relying on credit cards rather than cash in daily life. This creates a slew of new opportunities for fraudulent individuals to abuse these cards. As of December 2020, global card losses reached $28.65billion, up 2.9% from $27.85 billion in 2018, according to the Nilson 2019 research. To safeguard the safety of credit card users, the credit card issuer should include a service that protects customers from potential risks. CCF has become a severe threat as internet buying has grown. To this goal, various studies in the field of automatic and real-time fraud detection are required. Due to their advantageous properties, the most recent ones employ a variety of ML algorithms and techniques to construct a well-fitting model to detect fraudulent transactions. When it comes to recognising credit card risk is huge and high-dimensional data, feature selection (FS) is critical for improving classification accuracy and fraud detection.

Methodology/design/approach: The objectives of this chapter are to construct a new model for credit card fraud detection (CCFD) based on principal component analysis (PCA) for FS and using supervised ML techniques such as K-nearest neighbour (KNN), ridge classifier, gradient boosting, quadratic discriminant analysis, AdaBoost, and random forest for classification of fraudulent and legitimate transactions. When compared to earlier experiments, the suggested approach demonstrates a high capacity for detecting fraudulent transactions. To be more precise, our model’s resilience is constructed by integrating the power of PCA for determining the most useful predictive features. The experimental analysis was performed on German credit card and Taiwan credit card data sets.

Findings: The experimental findings revealed that the KNN achieved an accuracy of 96.29%, recall of 100%, and precision of 96.29%, which is the best performing model on the German data set. While the ridge classifier was the best performing model on Taiwan Credit data with an accuracy of 81.75%, recall of 34.89, and precision of 66.61%.

Practical implications: The poor performance of the models on the Taiwan data revealed that it is an imbalanced credit card data set. The comparison of our proposed models with state-of-the-art credit card ML models showed that our results were competitive.

The purpose of this paper is to investigate the risk-taking channel of monetary policy transmission in the Chinese banking industry. This study also investigates the role of various other factors in the risk-taking channel.

This study used panel data from 2000 to 2012, and a dynamic panel model (Difference GMM) was applied.

The empirical findings of this paper suggest that loose monetary policy rates increase bank risk-taking. Unlike previous studies, the results of this paper suggest that the bank-specific factors (size, liquidity and capitalization) do not significantly affect the risk-taking channel. However, the market structure does have a stabilizing effect on monetary policy transmission and the risk-taking channel. Higher market power weakens the risk-taking channel of monetary policy transmission.

Of significance to the policymakers' point of view is that loose monetary policy induces banks to take excessive risks. However, such effects can be mitigated by encouraging a proper level of market power in banking markets.

This study investigated the risk-taking channel of monetary policy transmission for the Chinese banking industry. Due to the unique features of the People's Bank of China (PBC, Central Bank of China) policy, this study also contributes to the literature by comparing price-based and quantity-based monetary policy tools and their effectiveness in financial stability and monetary policy transmission. Furthermore, the role of market structure is also investigated in the risk-taking channel.

This study investigated the impact of servant leadership on project success in nongovernment organizations (NGOs) working in a developing country like Pakistan. A moderated mediation design was employed, and the mediating role of employees' emotional intelligence (EI) and job stress (JS) was tested between servant leadership on project success. Moreover, the study also examined the moderating role of team effectiveness.

Data were collected from 441 project team members working on different developed projects. Data were analyzed using partial least square-structural equation modeling (PLS-SEM) technique.

Results revealed that servant leadership exerts a significant positive impact on project success. Also, it is noted that servant leadership significantly increases the employee's emotional intelligence that contributes to project success although it does not reduce JS. However, JS was found to be a significant mediator in the association between servant leadership on project success. The findings also revealed that team effect plays an imperative moderating role in ensuring project success.

The study is one of the very few studies conducted to assess the impact of servant leadership on project success in not-for-profit organizations. The study contributes to the literature and methodology by adopting a holistic approach to investigate the mediation of EI and JS along with the moderation of team effectiveness in the nexus of servant leadership and project success.

This paper aims to reveal whether there is a difference in perception of banking clients toward participation banks (PBs) and conventional banks (CBs) operated by the same bank.

The data were gathered with an online questionnaire from 254 participants. Questionnaire consisted of the Chaouch (2017) bank perception scale and the Koenig and Büssing (2010) religiosity scale. The data of the study were analyzed using the paired samples t-test and regression analysis.

The findings exhibit that Turkish bank clients, as a secular society, differently perceive financial activities of PBs and CBs that operate under the same roof in terms of compliance with Islamic laws. The findings also reveal that perceptions of the Turkish bank clients toward PBs' activities to compliance with the Islamic rules differs by the religiosity level. On the other hand, findings show that there is no difference in the perceptions of the CB's activities regarding compliance with Islamic rules by the clients’ religiosity level.

This study uses quantitative data. These type of data both can miss sometimes certain knowledge and restricts of participants thoughts on the study phenomena.

Based on the results of the study’s findings, beneficial suggestions are made for researchers and banking sector managers.

While many studies have been on Islamic banking, this study extends the role theory to compare perceptions of bank clients between PBs and CBs and provides an empirical evidence for bank clients' perceptions to dual banking in a developing and a secular country like Turkey.

Given the importance of environmental protection and the crucial role of manufacturing firms in environmental degradation, the purpose of this research is to investigate the impact of green intellectual capital (GIC) on firms' green performance (GP), mediating effects of ambidextrous green innovation (GI) and moderating role of technological turbulence (TT).

The study employed a quantitative research approach with the partial least square structural equation modeling (PLS-SEM) methodology to assess the proposed relationships among the constructs on a sample of 334 executives from 134 medium and large-sized manufacturing firms.

The findings show that GIC significantly impacts different aspects of GP, including green management, green process and green product performance. Moreover, exploitative and exploratory GI serves as mediators between GIC and firms' GP. Finally, the findings demonstrate that TT moderation enhanced the effects of GIC on exploratory GI, while decreasing the effects of GIC on exploitative GI.

The research offers valuable insights and a novel strategy for manufacturing firms and policymakers to mitigate environmental degradation and attain sustainable GP by stimulating ambidextrous GI through green intangible resources.

This research adds to the current GIC, GI and GP literature by focusing on green environmental issues using the resource-based view (RBV) theory. This research also provides a significant theoretical and practical justification for explaining the relationships by differentiating ambidextrous GI between exploitative and exploratory GI's mediating effects and TT's moderating effects.

This article offered two meshfree algorithms, namely the local radial basis functions-finite difference (LRBF-FD) approximation and local radial basis functions-differential quadrature method (LRBF-DQM) to simulate the multidimensional hyperbolic wave models and work is an extension of Jiwari (2015).

In the evolvement of the first algorithm, the time derivative is discretized by the forward FD scheme and the Crank-Nicolson scheme is used for the rest of the terms. After that, the LRBF-FD approximation is used for spatial discretization and quasi-linearization process for linearization of the problem. Finally, the obtained linear system is solved by the LU decomposition method. In the development of the second algorithm, semi-discretization in space is done via LRBF-DQM and then an explicit RK4 is used for fully discretization in time.

For simulation purposes, some 1D and 2D wave models are pondered to instigate the chastity and competence of the developed algorithms.

The developed algorithms are novel for the multidimensional hyperbolic wave models. Also, the stability analysis of the second algorithm is a new work for these types of model.

This study aims to assess the impact of personality traits, risk perception and perceived coronavirus disease 2019 (COVID-19) disruption on the investment behavior of individual investors in the Indian stock market.

This study adopts a survey approach. The sample comprises 315 active retail investors investing in the Indian stock exchange. Two-stage analysis technique regression and Artificial Neural Network (ANN) were used for data analysis. Study hypotheses were tested through regression and ANN was adopted to validate the regression results.

Two regression models were modeled to test the research hypotheses. Findings showed that risk perception and COVID-19 disruption have a significant positive and neuroticism has a significant negative impact on short-term investment decisions, while the role of conscientiousness in determining short-term investment decisions was not found significant. Results also showed a positive impact of neuroticism and conscientiousness and a negative impact of risk perception on long-term investment decisions. The role of COVID-19 disruption was found negative but insignificant in predicting long-term investment decisions.

This study has practical implications for many parties like retail investors, financial advisors and policymakers. This study will assist the investors to realize that they do not always take rational financial decisions. This study will suggest the financial advisors to use the knowledge of behavioral finance in making the advisors' advisory and wealth management decisions. This study will also assist the policymakers to outline behaviorally well-informed policy decisions to protect the interests of investors.

India is one of the fast-growing economies in the world. India has a vast population of active investors and determining investors' investment behavior adds novelty to this study as developed economies have remained the main focus of previous studies. The other novel feature of this study is that this study tries to assess the impact of COVID-19 disruption along with personality traits and risk perception on investment behavior. The other valuable factor of this study is the use of ANN to predict the relative importance of the exogenous variables.