Automated Machine Learning with Genetic Programming on Real Dataset of Tax Avoidance Classification Problem

Masrom, Suraya; Rahman, Rahayu Abdul; Baharun, Norhayati; Rahman, Abdullah Sani Abd

doi:10.1145/3383923.3383942

Cited by 3 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, 15 records from tax avoidance dataset were set for testing and the rest 60 records were used for training. Information about the tax avoidance dataset can be referred in our previous research reported in [15], [16].…”

Section: Datasetsmentioning

confidence: 99%

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rahman¹,

Masrom²,

Rahman³

et al. 2021

IJETAE

Self Cite

View full text Add to dashboard Cite

Reseachers have acknowledged that machine learning is useful to be utilized in many different domains of complex real life problem. However, to implement a complete machine learning model involves some technical hurdles such as the steep learning curve, the abundance of the programming skills, the complexities of hyper-parameters, and the lack of user friendly platform to be used for the implementation. This paper provides an insight of a rapid software framework for implementing machine learning. This paper also demonstrates the empirical research results of machine learning classification models from the rapid software framework. Additionally, this paper explains comparisons of results between two platforms of rapid software; the proposed software and Python program. The machine learning model in the two platforms were tested on breast cancer and tax avoidance datasets with Decision Tree algorithm. The results indicated that although the software framework is easier than the programming platform for implementing the machine learning model, the results from the software framework were highly accurate and reliable. Keywords- Software framework, rapid, implementation, machine learning

show abstract

Section: Datasetsmentioning

confidence: 99%

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rahman¹,

Masrom²,

Rahman³

et al. 2021

IJETAE

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is anticipated in this research that the PSO-GA hybridization [11], [12] can be very useful to be deployed for the application of machine learning, mainly for the problem that involved real cases dataset. The results of machine learning models from our previous studies in [13], [14] on the tax avoidance detection were undesirable due to the problem of very weak correlation among the dataset features. Although data engineering [15] exercises can be conducted to improve the knowledge extrapolations from the dataset it is expected that automating the features selection without original data manipulation can be more helpful.…”

Section: Introductionmentioning

confidence: 97%

“…This work was initially inspired by the machine learning tax avoidance prediction research conducted by [16] that used logistic regression, decision tree, and random forest machine learning algorithms. Based on our previous studies, using automated machine learning has given more advantages compared to manual machine learning configurations [14] but this approach only used genetic programming (GP) algorithm to optimize the features selections of the tax avoidance dataset. To get a research report on PSO with adaptive GA operators is difficult from the literature neither in tax avoidance nor in other machine learning applications.…”

Section: Introductionmentioning

confidence: 99%

Machine learning of tax avoidance detection based on hybrid metaheuristics algorithms

Masrom

Rahman²,

Mohamad³

et al. 2022

IJ-AI

Self Cite

View full text Add to dashboard Cite

This paper addresses the performances of machine learning classification models for the detection of tax avoidance problems. The machine learning models employed automated features selection with hybrid two metaheuristics algorithms namely particle swarm optimization (PSO) and genetic algorithm (GA). Dealing with a real dataset on the tax avoidance cases among companies in Malaysia, has created a stumbling block for the conventional machine learning models to achieve higher accuracy in the detection process as the associations among all of the features in the datasets are extremely low. This paper presents a hybrid meta-heuristic between PSO and adaptive GA operators for the optimization of features selection in the machine learning models. The hybrid PSO-GA has been designed to employ three adaptive GA operators hence three groups of features selection will be generated. The three groups of features selection were used in random forest (RF), k-nearest neighbor (k-NN), and support vector machine (SVM). The results showed that most models that used PSO-GA hybrids have achieved better accuracy than the conventional approach (using all features from the dataset). The most accurate machine learning model was SVM, which used a PSO-GA hybrid with adaptive GA mutation.

show abstract

“…Some machine learning techniques are regression, classification, clustering, dimensional reduction and reinforcement Int J Artif Intell ISSN: 2252-8938  learning. These techniques are commonly used as a tool for the solution of classification, forecasting and prediction problems [11].…”

Section: Introductionmentioning

confidence: 99%

Clustering algorithms for analysing electronic medical record: A mapping study

Shah

Rosli

2023

IJ-AI

View full text Add to dashboard Cite

<p>Electronic Medical Records (EMRs) contain patients’ history related to their medication, vaccine, test results and insurance information. EMRs need to be stored to facilitate the application of clinical treatment and prevention protocols. Clustering algorithms automate the process of information extraction and support health data management. Hence, in this mapping study, we systematically examine the literature on clustering algorithms used for analysing EMRs. We focus on studies published in 2016-2021 to present an overview of clustering techniques used in these studies to analyse medical data. We found 27 studies on clustering techniques, clustering technique problems and the evaluation parameters for analysing EMRs. However, although several studies have focused on this topic, only a few have taken the significant step of examining the clustering techniques used for analysing medical data particularly electronic medical record. Our results highlight that three clustering techniques have been used to analyse medical data, namely, the partitioning, the hierarchical and the density-based algorithms. We identified several clustering technique problems and 10 different evaluation parameters. The results suggest that researchers should focus on analysing medical data that will drive data-driven decision-making by management and promote a data-driven culture to ensure health care quality.</p>

show abstract

Automated Machine Learning with Genetic Programming on Real Dataset of Tax Avoidance Classification Problem

Cited by 3 publications

References 8 publications

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Machine learning of tax avoidance detection based on hybrid metaheuristics algorithms

Clustering algorithms for analysing electronic medical record: A mapping study

Contact Info

Product

Resources

About