Improvement of decision tree classifier accuracy for healthcare insurance fraud prediction by using Extreme Gradient Boosting algorithm

Akbar, Nur Arifin; Sunyoto, Andi; Arief, M. Rudyanto; Caesarendra, Wahyu

doi:10.1109/icimcis51567.2020.9354286

Cited by 22 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automotive insurance is the most established type of insurance fraud because it originates from false accident claims (Anbarasi & Dhivya, 2017). Several studies have employed machine learning methods to detect fraudulent claims by health facility providers, e.g., the decision tree, Support Vector Machine (SVM), and Back Propagation Neural Network (BPNN) (Chen & Chen, 2020), also random forest and XGBoost (Akbar et al, 2020). Another study (Lavanya et al, 2021) reported the Multilayer Perceptron algorithm with the best accuracy compared to five other models (i.e., Logistic Regression, Random Forest, Support Vector Machine, Adaboost, and Gradient Boosting Trees).…”

Section: Related Workmentioning

confidence: 99%

Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim

Nugraha¹,

Pardede²,

Subekti³

2022

KJS publishes peer-review articles in Mathematics, Computer Sci

View full text Add to dashboard Cite

Fraud on health insurance impacts cost overruns and a quality decline in health services in the long term. The use of machine learning to detect fraud on health insurance is increasingly popular. However, one challenge in predicting health insurance fraud is the data imbalance. The data imbalance can cause a bias towards the majority class in many machine learning methods. Oversampling is a solution for data imbalance by augmenting new data based on the existing minority class data. Recently, there has been growing interest in employing deep learning for data augmentation. One of them is using Generative Adversarial Networks (GAN). This paper proposes using GAN as an oversampling method to generate additional data for minority classes. Since data for detecting health insurance fraud are tabular, we adopt Conditional Tabular GAN (CTGAN) architecture where the generator is conditioned to adjust the tabular data input and receive additional information to produce samples according to the specified class conditions. The new balanced data are used to train 17 classification algorithms. Our experiments showed that the proposed method performs better than other oversampling methods on several evaluation metrics, i.e., accuracy, precision score, F1-score, and ROC.

show abstract

Section: Related Workmentioning

confidence: 99%

Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim

Nugraha¹,

Pardede²,

Subekti³

2022

KJS publishes peer-review articles in Mathematics, Computer Sci

View full text Add to dashboard Cite

show abstract

“…Data mining (DM) and machine learning (ML) techniques are widely used for insurance cost prediction and medical fraud detection [15]. Using the Extreme Gradient Boosting algorithm, we improved the accuracy of a decision tree classifier for predicting healthcare insurance fraud [16].…”

Section: Related Workmentioning

confidence: 99%

A Computational Intelligence Approach for Predicting Medical Insurance Cost

Hassan

Iqbal

Hussain

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In the domains of computational and applied mathematics, soft computing, fuzzy logic, and machine learning (ML) are well-known research areas. ML is one of the computational intelligence aspects that may address diverse difficulties in a wide range of applications and systems when it comes to exploitation of historical data. Predicting medical insurance costs using ML approaches is still a problem in the healthcare industry that requires investigation and improvement. Using a series of machine learning algorithms, this study provides a computational intelligence approach for predicting healthcare insurance costs. The proposed research approach uses Linear Regression, Support Vector Regression, Ridge Regressor, Stochastic Gradient Boosting, XGBoost, Decision Tree, Random Forest Regressor, Multiple Linear Regression, and k-Nearest Neighbors A medical insurance cost dataset is acquired from the KAGGLE repository for this purpose, and machine learning methods are used to show how different regression models can forecast insurance costs and to compare the models’ accuracy. The results shows that the Stochastic Gradient Boosting (SGB) model outperforms the others with a cross-validation value of 0.0.858 and RMSE value of 0.340 and gives 86% accuracy.

show abstract

“…Since it is based on self-stabilizing failure detectors, this solution can provide self-stabilizing BFT with weaker synchrony requirements than when using, for example, clock synchronization. A preliminary evaluation of the protocol carried out by Niklasson and Petersson [31,32,33] validated the selfstabilizing property of the system. The evaluation also showed promising results for practical usage for certain types of state machines, further indicating that adding the self-stabilizing criteria to a system such as PBFT is practical and desirable.…”

Section: Self-stabilization Of Agreement Protocolsmentioning

confidence: 99%

Reducing Overhead of Self-Stabilizing Byzantine Agreement Protocols for Blockchain Using HTTP/3 Protocol: A Perspective View

Akbar¹,

Sunyoto²,

Arief³

et al. 2021

Sinergi

Self Cite

View full text Add to dashboard Cite

Today, there is a tendency to reduce the dependence on local computation in favor of cloud computing. However, this inadvertently increases the reliance upon distributed fault-tolerant systems. In a condition that forced to work together, these systems often need to reach an agreement on some state or task, and possibly even in the presence of some misbehaving Byzantine nodes. Although non-trivial, Byzantine Agreement (BA) protocols now exist that are resilient to these types of faults. However, there is still a risk for inconsistencies in the application state in practice, even if a BA protocol is used. A single transient fault may put a node into an illegal state, creating a need for new self-stabilizing BA protocols to recover from illegal states. As self-stabilization often comes with a cost, primarily in the form of communication overhead, a potential lowering of latency - the cost of each message - could significantly impact how fast the protocol behaves overall. Thereby, there is a need for new network protocols such as QUIC, which, among other things, aims to reduce latency. In this paper, we survey current state-of-the-art agreement protocols. Based on previous work, some researchers try to implement pseudocode like QUIC protocol for Ethereum blockchain to have a secure network, resulting in slightly slower performance than the IP-based blockchain. We focus on consensus in the context of blockchain as it has prompted the development and usage of new open-source BA solutions that are related to proof of stake. We also discuss extensions to some of these protocols, speciﬁcally the possibility of achieving self-stabilization and the potential integration of the QUIC protocol, such as PoS and PBFT. Finally, further challenges faced in the ﬁeld and how they might be overcome are discussed.

show abstract

Improvement of decision tree classifier accuracy for healthcare insurance fraud prediction by using Extreme Gradient Boosting algorithm

Cited by 22 publications

References 10 publications

Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim

Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim

A Computational Intelligence Approach for Predicting Medical Insurance Cost

Reducing Overhead of Self-Stabilizing Byzantine Agreement Protocols for Blockchain Using HTTP/3 Protocol: A Perspective View

Contact Info

Product

Resources

About