"Scientific research" Almanac

More titles

• 

  THE ROLE OF INTERNAL AND EXTERNAL AUDITORS FOR IDENTIFYING FRAUDS IN ORGANIZATIONS

  The variety of ways and approaches to fraud necessitates the updating of measures and mechanisms to identify and limit them. By properly implementing these mechanisms and approaches, the risk assessment and the display of indicators signalling misconduct contribute to reducing them and improving the effectiveness of the control impact. The ... The variety of ways and approaches to fraud necessitates the updating of measures and mechanisms to identify and limit them. By properly implementing these mechanisms and approaches, the risk assessment and the display of indicators signalling misconduct contribute to reducing them and improving the effectiveness of the control impact. The relevance of the study is due to the growing threat of spreading fraud and the need for adequate and timely measures to limit them. The purpose of the research study is to outline the possible actions to curb fraud, applied by internal and external auditors, as well as to examine the methodology used in the preparation of fraud risk assessments. The tasks are as follows: to clarify the role of internal audit in combating fraud; examining methodological guidelines for fraud risk assessment; implementation of anti-fraud management measures and adequate audit procedures. The thesis being defended is that fraud is a complex phenomenon and the role of internal and external auditors is essential for detecting and limiting it by applying innovative and adequate methods. The study substantiates the relationship between management actions and the ability to prevent and detect fraud, as well as the conditionality of audit procedures, performed by external auditors on the type and nature of possible fraudulent financial reporting schemes.

• 

  IMPACT OF DIGITAL MARKETING CHANNELS ON CUSTOMER LOYALTY IN THE BANKING SECTOR

  Globally, digital sales in the personal banking sector are increasing, as well as the investment of banking institutions in digitalization. Being inspired by these trends, the objective of this study, set by the authors, is to explore the potential of digital marketing channels to influence customer loyalty in the banking sector, creating ... Globally, digital sales in the personal banking sector are increasing, as well as the investment of banking institutions in digitalization. Being inspired by these trends, the objective of this study, set by the authors, is to explore the potential of digital marketing channels to influence customer loyalty in the banking sector, creating additional benefits for the customer. It is argued that the use of digital marketing channels in retail banking can have a positive effect on customer loyalty. Three main benefits of using digital marketing channels in the banking sector have been outlined - saving money, saving time and convenience in managing banking products. These benefits are included in a conceptual model that implies direct influence of perceived benefits from digital banking to customer loyalty, as well as indirect effect through customer satisfaction. The validity of the model is tested by using a structural equation modelling method and non-parametric procedures are applied for parameter estimation. It has been found that the perceived benefits of using digital innovations in banks' marketing channels have an indirect effect on customer loyalty by influencing customer satisfaction. Satisfaction with the use of digital channels, in turn, promotes loyal customer behaviour. The verified model is valid both for clients using the services of only one bank and for clients of more than one bank.

• 

  DEEP NEURAL NETWORKS FOR DETECTION OF CREDIT CARD FRAUD

  This publication presents research on the possibility of using Deep Neural Net-works (DNNs) for detection of credit card fraud. The research is based on an open da-taset and aims to determine how the varying number of hidden layers and other archi-tectural parameters (width of each layer, activation functions) affects training and predictive ... This publication presents research on the possibility of using Deep Neural Net-works (DNNs) for detection of credit card fraud. The research is based on an open da-taset and aims to determine how the varying number of hidden layers and other archi-tectural parameters (width of each layer, activation functions) affects training and predictive potential of the network. It also aims to determine how to use generative-adversarial approach efficiently in order to overcome the problem with the imbalance between legitimate and fraudulent transactions, which is crucial characteristic of the datasets related to detection of credit card fraud. The publication presents the results of various experiments, conducted to achieve the stated goals. A number of experiments have been carried out combining network training of various depth of the network and with different parameters of the learning process, for example, activation function and dropout values. The experiments focus on using generative-adversarial approach as a method for oversampling, in par-ticular. The results indicate that deep neural networks with moderate hidden layers, combined with methods for oversampling are performing much better in identifying fraudulent transactions than the classical neural networks, consisting of only one hid-den layer. The results also indicate that using generative-adversarial approach as a method for oversampling is comparable in efficiency to other widely used techniques.