Revenue Prediction for Malaysian Federal Government Using Machine Learning Technique

Noor, Nadzira; Sarlan, Aliza; Aziz, Norshakirah

doi:10.1145/3524304.3524337

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, Owens et al [14] detail how the recent developments in the application of predictive analytics can be utilised in the tax administrations of African countries. On the other hand, Noor et al [15] investigated its application in the context of Malaysia and discovered that machine learning techniques can be used to predict revenue for the federal government of Malaysia. In predictive analytics, the nodes make up a hierarchical structure, and as the process moves forward, the support vectors move up the hierarchy, with the most significant ones ending up at the very top and the least significant ones at the very bottom [16].…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Predictive Analytics Model for Tax-Based Operations

Musa,

Balarabe Junaidu,

Ismaeel Ahmad

et al. 2023

IJPCC

View full text Add to dashboard Cite

In order to meet its basic responsibilities of governance such as provision of infrastructure, governments world over require significant amount of funds. Consequently, citizens and businesses are required to pay certain legislated amounts as taxes and royalties. However, tax compliance and optimal revenue generation remains a major source of concern. Measures such as penalties and in the current times Data and Predictive Analytics have been devised to curb these issues. Such effective Analytics measures are absent in Bauchi State and Nigeria as a whole. Previous studies in Nigeria have done much in the area of tax compliance but have not implemented Data Analytics solutions to unearth the relationships which this study will cover. A Combined Sequential Minimal Optimisation (CSMO) model has been developed to analyse co-relation of Tax-payers, classification and predictive traits which uncovers trends on which to base overall decisions for the ultimate goal of revenue generation. Experimental validation demonstrates the advantages of CSMO in terms of classification, training time and prediction accuracy in comparison to Sequential Minimal Optimisation (SMO) and Parallel Sequential Minimal Optimisation (PSMO). CSMO recorded a Kappa Statistics measure of 0.916 which is 8% more than the SMO and 7.8% more than the PSMO; 99.74% correctly classified instances was compared to 98.28% in SMO and 98.35 in parallel SMO. Incorrectly classified instances of CSMO recorded a value of 0.25% which is better than 1.72% of SMO and 1.68% of PSMO. Training time of 223ms was recorded when compared to 378ms in SMO and 286ms in PSMO. A better value of 0.9981 for CSMO was achieved in the ROC Curve plot against 0.944 in SMO and 0.913 in PSMO. CSMO takes advantage of powerful Analytics techniques such as prediction and parallelisation in function-based classifiers to discover relationships that were initially non-existent

show abstract

Section: Related Workmentioning

confidence: 99%

An Enhanced Predictive Analytics Model for Tax-Based Operations

Musa,

Balarabe Junaidu,

Ismaeel Ahmad

et al. 2023

IJPCC

View full text Add to dashboard Cite

show abstract

Learning Model for Analytical Prediction of Tax Revenues from Tax Invoice Information

Mendonça,

Silva,

Coutinho

2024

Revista Científica Multidisciplinar Núcleo do Conhecimento

View full text Add to dashboard Cite

In Brazil, the tax on goods and services, known by the acronym ICMS, holds significant prominence in the revenue of the federative units, approximately 90%. Its value depends on economic activity, whose tax information the taxpayers record in electronic invoices issued to the tax agencies. This paper proposes a learning architecture to predict ICMS revenue through a dataset derived from tax information. The learning architecture uses a segmented approach that starts with splitting the training and validation datasets according to a given parameter. After that, the architecture fits several machine learning models for each split subset (segment). Finally, the architecture chooses the fit machine learning model (learning instance) that produces the best prediction result for each segment. These learning instances compose a hybrid instance set to predict the records of a test dataset. The proposed architecture reduced the error compared to the traditional non-segmented approaches tested (by 18.40%) and to the current methodology of the tax agency that supported this research (by 51.90%). The low prediction error suggests that the model holds promise in estimating revenue.

show abstract

Revenue Prediction for Malaysian Federal Government Using Machine Learning Technique

Cited by 2 publications

References 20 publications

An Enhanced Predictive Analytics Model for Tax-Based Operations

An Enhanced Predictive Analytics Model for Tax-Based Operations

Learning Model for Analytical Prediction of Tax Revenues from Tax Invoice Information

Contact Info

Product

Resources

About