Generation of a Synthetic Dataset for the Study of Fraud through Deep Learning Techniques

Sánchez, Marco; Olmedo, Verónica; Narvaez, C.; Hernández, Myriam A.; Urquiza-Aguiar, Luis

doi:10.18517/ijaseit.11.6.14345

Cited by 4 publications

(2 citation statements)

References 24 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Open questionnaires are generally used in qualitative research by qualitative analysis [21]- [22]. This is to maintain the researcher's intervention so that it interferes with the validity of the data.…”

Section: Resultsmentioning

confidence: 99%

Mental Action Way of Understanding (WoU) and Way of Thinking (WoT) Students in Statistics Learning in Higher Education

Lukman¹,

Wahyudin²,

Suryadi³

et al. 2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

This study aims to examine in depth the Mental Action Way of Understanding (WoU) and Way of Thinking (WoT) of students in learning Statistics in Higher Education and the relationship between WoU and WoT. This research is qualitative research using the Grounded Theory approach. The participants involved were 36 people in the city of Bandung, West Java, Indonesia. Validity and reliability using the Krippendorff content analysis method with the Inter-coder Agreement (ICA) test using Krippendorff alpha coefficients. The results showed that there was a significant relationship between students' mental action statistics and students' WoU and WoT in Statistical Understanding and Thinking. The relationship between WoU and WoT: (1) Students' WoU will build such a statistical framework. (2) Students' WoT affects how statistical modeling from their statistical knowledge. This relationship fits the philosophy of statistics and inductive inference. The statistical mental action of WoU students was to make models, analyze, calculate and generalize. The mental actions of Statistics students from WoT were interpreting, analyzing, predicting, reasoning, and inferring. The WoU and WoT mental action models developed the PPDC Cycle model and the Gal's statistical literacy model. the PPDAC Cycle model by Wild and Pfankuch, consists of five dimensions, and one of the dimensions was the PPDAC Cycle. The statistical literacy model by Gal consists of two dimensions, namely the dimensions of statistical knowledge and disposition. The novelty of this research was developing the PPDAC Cycle statistical thinking model by Wild and Pfankuch, and the statistical literacy model on the statistical knowledge dimension by Gal. This study's results can be considered in designing statistical learning in universities and measuring students' understanding and statistical thinking skills.

show abstract

Section: Resultsmentioning

confidence: 99%

Mental Action Way of Understanding (WoU) and Way of Thinking (WoT) Students in Statistics Learning in Higher Education

Lukman¹,

Wahyudin²,

Suryadi³

et al. 2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…Today, the data mining approach has developed rapidly. It has already been applied in more expansive fields [1], some of which are [2] and [3] used a data mining approach to the agriculture sector [4] in the health sector, [5], [6], and [7] in the biology sector, and [8] who applied a data mining approach in the financial industry. One of the data mining algorithms, which is often used, is a decision tree.…”

Section: Introductionmentioning

confidence: 99%

Efforts of Performance Optimization: The Experiment on Ten Accounting Datasets

Domas¹,

Rizkiawan²,

Rakhmadi

2022

LKJITI

View full text Add to dashboard Cite

In the big data and digitalization era, fast-accurate decision-making has become a basic need, so data mining has a crucial role. The decision tree algorithm is quite commonly applied for classification functions, but performance level must always be evaluated for optimizing accuracy rate. Several optimization methods to accommodate these objectives include GA-bagging, PSO-bagging, forward selection, backward elimination, SMOTE, under-sampling, GA-Adaboost, and ABSMOTE-WIGFS. The results of the decision tree experiment on ten types of accounting-finance datasets used in this study obtained results with an average accuracy of 83.46%, an average precision of 65.64%, and an average AUC of 71.9%, while the majority of various optimizations are proven in improving the performance of decision tree algorithm where the application of ABSMOTE-WIGFS method is proven in providing the best rate with an average accuracy 87.71%, an average precision 87.09%, and an average AUC 84.87%, so it can be concluded that various optimization efforts are worth to be applied in case of accounting-finance themes for increasing the performance rate. Furthermore, the next research can prove these methods in other fields outside of accounting cases.

show abstract

Comparative Analysis of the Performance of Machine Learning Techniques Applied to Real and Synthetic Fraud-Oriented Datasets

Sánchez-Aguayo

Urquiza-Aguiar

2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Generation of a Synthetic Dataset for the Study of Fraud through Deep Learning Techniques

Cited by 4 publications

References 24 publications

Mental Action Way of Understanding (WoU) and Way of Thinking (WoT) Students in Statistics Learning in Higher Education

Mental Action Way of Understanding (WoU) and Way of Thinking (WoT) Students in Statistics Learning in Higher Education

Efforts of Performance Optimization: The Experiment on Ten Accounting Datasets

Comparative Analysis of the Performance of Machine Learning Techniques Applied to Real and Synthetic Fraud-Oriented Datasets

Contact Info

Product

Resources

About