"Scientific research" Almanac

More titles

• 

  CURRENT TENDENCIES IN E-COMMERCE APPLICATION DEVELOPMENT

  In today’s competitive and dynamic business environment, companies need to transform their business in order to survive. There has been a steady trend for companies to engage in e-commerce and business based on online technologies, since it has become clear that unless they do so, they will drop out of the market. Although their presence on the ... In today’s competitive and dynamic business environment, companies need to transform their business in order to survive. There has been a steady trend for companies to engage in e-commerce and business based on online technologies, since it has become clear that unless they do so, they will drop out of the market. Although their presence on the internet offers new channels for the distribution of goods and services, it also poses a number of risks which companies need to be aware of so that they could analyse and adequately manage them. The aim of this study is to present the opportunities provided by different technological solutions for developing e-commerce applications. Those solutions, like any new technology, are viewed from different standpoints and provoke different reactions and assessments. It is therefore necessary to present their specific characteristics, as well as the impact of their implementation. The main thesis of the research is that business transformation requires the development of e-commerce apps with maximum efficiency according to the resources, which companies have at their disposal. The findings of the study indicate that teams engaged in the digitalisation of a business must be aware of current trends in developing e-commerce apps and the ability of a company to adjust to them. Hence, there are two major issues to be resolved in terms of digital transformation: first, designing and running the right online store (e-commerce website) and second, choosing the best approaches to accomplish that.

• 

  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.

• 

  EFFECTS OF GOVERNMENT BUDGET BALANCE ON ECONOMIC GROWTH

  The necessity of adequate use of public budget as a fiscal instrument for economic regulation is even more tangible in conditions of slow economic growth rate. The debate on whether the public budget can maintain a balance between economic stability and social equity has a long history. Another question is whether budget deficit or budget surplus ... The necessity of adequate use of public budget as a fiscal instrument for economic regulation is even more tangible in conditions of slow economic growth rate. The debate on whether the public budget can maintain a balance between economic stability and social equity has a long history. Another question is whether budget deficit or budget surplus would trigger higher economic growth. The main objective of the empiric analysis is to evaluate the budget deficit/ surplus impact on real economic growth rate by using econometric analysis and comparative analysis between Bulgaria and the other Member States of the European Union as well as the Balkan States (Cyprus, The Czech Republic, Estonia, Hungary, Latvia, Lithuania, Malta, Poland, Slovakia, Slovenia, Romania, Croatia, Greece, Serbia, Turkey and North Macedonia). The specific task is to justify the need to balance the public budget and reduce the budget deficit in order to achieve sustainable real economic growth. The thesis of the research is that balancing public budget and reducing distributive and redistributive government activities contribute to higher real economic growth rate in the analyzed Bulgarian and European economies. The main results of the research prove that reduction of budget deficit and balanced government budget have a positive effect on realized economic growth rate in the analyzed European countries over the period 2007 – 2018.