Fraud Detection on Bulk Tax Data Using Business Intelligence Data Mining Tool: A Case of Zambia Revenue Authority

Mwanza, Memorie

doi:10.17148/ijarcce.2016.53191

Cited by 7 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy, precision, recall, and F value show that the performance of the improved BP neural network has been improved [9]. Mwanza and Phiri used intelligent mining algorithm in the research of tax data to realize the outlier algorithm of fraud detection, continuous monitoring based on distance and outlier query based on distance, which improved the accuracy of abnormal data analysis [10]. Miller used KH coder's data mining technology to model individual tax behavior and used unsupervised machine learning text mining and modeling technology to help conduct large-scale analysis of tax behavior methods and find the problems of avoidance and tax evasion in time [11].…”

Section: State Of the Artmentioning

confidence: 99%

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Xin

2022

Journal of Function Spaces

View full text Add to dashboard Cite

Tax forecast has an important impact on financial budget and tax plan. The amount of tax data is greatly increased, the difficulty of tax forecast is improved, and the accuracy is always difficult to keep up with the development demand. Analyze the application of optimized support vector machine model in tax prediction system. Based on the simple analysis of the research situation of tax prediction and the research status of data mining algorithm in tax data classification and prediction, this paper constructs a tax prediction model. Aiming at the problem of too many influencing factors of tax prediction, this paper puts forward the use of principal component analysis to extract the main factors, reduce the dimension of tax data, and reduce the difficulty of analysis. Support vector machine is used to realize tax prediction, aiming at the problem of parameter optimization proposed to optimize the parameters. Finally, the prediction accuracy is evaluated by comparing the error between tax prediction value and real value. The results show that the algorithm used in this paper can optimize the parameters of support vector machine. The tax prediction results show that the predicted value is similar to the real value curve. After grid search optimization, the introduction of principal component analysis reduces the redundancy and improves the prediction accuracy.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Xin

2022

Journal of Function Spaces

View full text Add to dashboard Cite

show abstract

“…The objective of information security is to ensure data confidentiality, integrity and availability at any given point including during data entry, processing, storage and transmission (Kabuya et al, 2012). This process cannot be overlooked due to the fact that technology has become a critical component of business operations in every organization (Agbinya et al, 2011;Mwanza and Phiri, 2016). Today Zambia's public organizations are reliant on technological infrastructure for handling, processing and transmission of all the business data and its related activities (Hunker and Probst, 2010;Chinyemba and Phiri, 2018a).…”

Section: Introductionmentioning

confidence: 99%

An Investigation into Information Security Threats from Insiders and how to Mitigate them: A Case Study of Zambian Public Sector

Chinyemba¹,

Phiri²

2018

Journal of Computer Science

Self Cite

View full text Add to dashboard Cite

Insider attacks are security breaches posed by an existing or former organizational stakeholder with unrestricted access rights to the resources who, with or without intent, compromises the confidentiality, integrity and availability of organizational data. Zambian public organizations are vulnerable to insider attacks due to a number of factors that include; technology complexity, understaffing, financial gains, lack of security policies and procedures, lack of adoption and implementation of international security frameworks and standards such as ISO 27000 and COBIT. Insider threats can be categorized into three dimensions namely; Information Technology (IT) Sabotage, Financial Fraud and Intellectual Property (IP) theft. This paper reports the results from three targeted public organizations in Zambia. These are among the few that seem to recognised cyber threats and have partially adopted some parts of security base practices and international information security standards such as COBIT 5.0 and ISO 27001 standard. The study aimed at assessing the security GAPs using ISO 27001:2013 Information Security Management System (ISMS) standard. The study approach used was quantitative and qualitative with survey questionnaires and interviews as assessment tools for empirical data collection. The study shows that Zambian public sector has related challenges in mitigation of insider attacks that calls for considered efforts in developing measures for mitigation of these challenges in order to ensure national cyber security readiness and enhancing data privacy. The study reviewed that majority of the organizations assessed lack insider security deterring policies such as access control, non-disclosure agreements (NDA), pre-employment screening and unacceptable use. Additionally, the findings indicated that majority of public organizations have not made any efforts towards cyber security readiness, while only about 33% have adopted some security base practices. Further, using Actor Network Theory (ANT) and Theory of Planned Behavior (TPB), the study proposed an expedient insider mitigation model with an emphasis on user awareness and access control considering that it is difficult to model human behavior.

show abstract

“…They identified BI as a technique that can be used to detect tax frauds, non-fillers and non-compliant tax payers. They further alluded that data mining is a significant technique that can be used to overcome the challenges of fraud detection and anomalies that arise in tax administration [23].…”

Section: Related Workmentioning

confidence: 99%

Digital Certificate Exchange of Agricultural Products using SOAP Web Services

Chilikwela¹,

Phiri²

2019

IJACSA

Self Cite

View full text Add to dashboard Cite

Developing countries have continued to experience a number of challenges in managing import and export certificate for various goods. In this paper, we are proposing a model for digital certificate exchange in an effort to improve the security levels of data exchange among the government organizations and the business community. With the increase of various information systems being used in many organizations, data exchange between systems has become critical. The model developed uses SOAP web services for data exchange and RSA encryption for secure data exchange. Ministry of Agriculture is responsible for the issuance of import and export certificates in Zambia while Zambia Revenue Authority is responsible for ensuring that goods imported or exported out of the country have a valid certificate that is authentic. The results show that the model provides a secure and timely exchange of information between the ministries and the government agencies.

show abstract

Fraud Detection on Bulk Tax Data Using Business Intelligence Data Mining Tool: A Case of Zambia Revenue Authority

Cited by 7 publications

References 21 publications

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Application of Optimized Support Vector Machine Model in Tax Forecasting System

An Investigation into Information Security Threats from Insiders and how to Mitigate them: A Case Study of Zambian Public Sector

Digital Certificate Exchange of Agricultural Products using SOAP Web Services

Contact Info

Product

Resources

About