Secure and Efficient Federated Learning Framework for Advanced Credit Card Fraud Detection with Optimization (Published)
In recent years, credit card fraud has cost banks and customers a great deal of money. A strong Fraud Detection System (FDS) is therefore necessary to reduce losses for consumers and banks. Our analysis shows that the dataset of credit card transactions is extremely biased, with many fewer examples of fraudulent purchases than of genuine ones. In addition, banks are typically prohibited from sharing their transaction statistics because of concerns about data security and privacy. These issues make it challenging for FDS to identify fraud tendencies and to identify them. In this investigation, we offer a framework in which we label FFD (Federated learning for Fraud Detection) to train a fraud detection model utilizing behavior features with federated learning and convolutional neural networks (CNN) with Greylag Goose Optimization. In contrast to the conventional FDS trained on cloud-centralized data, FFD allows banks to use training data from their local databases to create fraud detection models. Subsequently, a shared fraud detection model is created by combining locally computed updates. Banks can profit collectively from a shared model without exchanging datasets to safeguard the cardholders’ sensitive information. In addition, an oversampling strategy is employed to counterbalance the skewed dataset. We use an extensive set of actual credit card transactions to assess the effectiveness of our credit card FDS system. The findings demonstrate the great accuracy with which each algorithm may be applied to the detection of credit card fraud.
Keywords: CNN, Credit Card Fraud Detection, Efficiency, Federated Learning, Graylag Goose Optimization, Security
Examination of the Public Sector Reform Programme Implementation in Zambia: The Efficacy of the Integrated Financial Management Information System (Published)
This study was to examine the Public Sector Reform Programme and implementation of the Efficacy of the Integrated Financial Management Information Systems (IFMIS) in Zambia. The focus is on the country’s central government with 1300 users of IFMIS in forty-four sites. The study used a quantitative research design to draw conclusions from a sample of 150 day-to-day users of IFMIS. Data was collected through a survey analysed using descriptive and causal-effect relationships. The system usage is far from satisfactory with misapplication of funds, and challenges in cooperating with partners. The public did not derive satisfaction in this outcome. However, IFMIS influences public resource management processes through ease of access to information, quick retrieval, easy tracking of documents and provision of an audit trail, among others. The system provides restricted access to the IFMIS system, creates the order of operations, defines and reduces the roles and duties of different users, which reduces the level of risk. Some users doubted the system’s ability to detect and report fraud cases. This study, therefore, recommends that IFMIS should be upgraded to protect documents from being attacked by viruses or getting lost, including stronger fraud detection, reporting and a broad application and use of IFMIS in all country departments with new features for fraud detection and reports to facilitate quick remedy. Lastly, the IFMIS should be decentralized to each department to ensure the processes of the supply chain are secured and efficient.
Citation: Gopal S., and Ngoma T. S. (2022) Examination of the Public Sector Reform Programme Implementation in Zambia: The Efficacy of the Integrated Financial Management Information System, International Journal of Management Technology, Vol.9, No 2, pp.12-33
Keywords: Efficiency, IFMIS, Zambia, public sector reform
Effects of Ergonomic Environment and Information and Communication Technology (ICT) On Secretarial Efficiencies in Tertiary Institutions in Ekiti State (Published)
Effects of ergonomic environment and information and communication technology (ICT) on secretarial efficiencies in tertiary institutions in Ekiti State were investigated. The population consisted of all secretarial staff and executives/directors in all tertiary institutions while the sample was 180 respondents randomly selected from three tertiary institutions. The research instrument was questionnaire, validated with a reliability co-efficient of 0.77. Data collected were analyzed using frequency counts and simple percentages for the research question while the hypothesis was tested using Pearson Moment Correlation Coefficient at 0.05 level of significance. Findings show that the physical environments of the institutions are conducive for work and some necessary facilities that could aid the efficiency of secretarial staff are provided but inadequate. It was concluded that good working environment is indispensable in today’s workplace for the efficiency and effectiveness of secretarial workers. It was recommended that efforts must be made to design jobs that help employees reduce and break up their sitting time, among others.
Keywords: Efficiency, ICT, Work Environment, ergonomics, secretaries