An evaluation of deep learning models for chargeback Fraud detection in online games

Wei, Yu-Chih; Lai, You-Xin; Wu, Mu-En

doi:10.1007/s10586-022-03674-4

Cited by 6 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, innovative collaboration models and game design are crucial for achieving common development goals [42]. Additionally, Wei et al (2023) points out the differences in operation and profit models between online game companies and game studios. Online game companies mainly rely on the release and operation of large-scale online games to generate revenue, while game studios obtain profits through game sales, IP licensing, and customized development [43].…”

Section: Online Game Companies and Game Studiosmentioning

confidence: 99%

“…Additionally, Wei et al (2023) points out the differences in operation and profit models between online game companies and game studios. Online game companies mainly rely on the release and operation of large-scale online games to generate revenue, while game studios obtain profits through game sales, IP licensing, and customized development [43]. However, due to the differences in industry status, when game studios choose to ignore the "game rules" set by online game companies for their own interests, they may become targets for precautionary measures and retaliation by online game companies [44].…”

Section: Online Game Companies and Game Studiosmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary game analysis of online game studios and online game companies participating in the virtual economy of online games

Zhang,

2024

PLoS ONE

View full text Add to dashboard Cite

In the context of the new economic development in the post-pandemic era, "play" labor as an important component of digital work has become an inexhaustible driving force for the growth of the digital economy. Previous research has shown that "play" labor, as an emerging business model, can effectively promote the growth of the digital economy. However, there is a relative lack of research on the dynamic evolutionary game between "play" labor suppliers represented by game studios and online gaming companies. In this study, we applied the theoretical approach of dynamic evolutionary game theory to establish a game model depicting the evolution of both parties involved in the virtual economy of online gaming. The aim was to investigate the strategic selection mechanisms and influencing factors for game studios and online gaming companies participating in the virtual economy of online gaming. By analyzing the evolutionary game path, equilibrium points, and factors influencing the evolutionary game outcome, as well as conducting numerical simulation analysis using Matlab software, we found that the incremental gains and costs resulting from the strategic choices of online gaming companies and game studios in engaging in the virtual economy of online gaming affect the evolutionary outcomes. In addition, for the probability ratio of online game studios and online game companies choosing to participate in the virtual economy of online games, whether it is online game studios or online game companies, the larger the initialization ratio, the more likely the evolution result is to develop in a mutually beneficial direction. After an in-depth analysis and discussion of the evolutionary game results, relevant policy recommendations were proposed. We hope to provide a reference for promoting online game companies to strengthen the adequate supervision of online game studios’ participation in the virtual economy of online games and optimize and improve the virtual economic environment.

show abstract

Section: Online Game Companies and Game Studiosmentioning

confidence: 99%

Section: Online Game Companies and Game Studiosmentioning

confidence: 99%

Evolutionary game analysis of online game studios and online game companies participating in the virtual economy of online games

Zhang,

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Meanwhile, simple RNNbased models are prone to the vanishing gradient problem, a situation where the RNN is unable to propagate relevant gradient information from the model's output end back to the layers near the input end [22]. However, LSTM and GRUbased RNNs were proposed to solve the vanishing gradient problem and have shown good performances in different sequence classification tasks [8], [23], [24].…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

Mienye

Sun

2023

IEEE Access

View full text Add to dashboard Cite

Credit cards play an essential role in today's digital economy, and their usage has recently grown tremendously, accompanied by a corresponding increase in credit card fraud. Machine learning (ML) algorithms have been utilized for credit card fraud detection. However, the dynamic shopping patterns of credit card holders and the class imbalance problem have made it difficult for ML classifiers to achieve optimal performance. In order to solve this problem, this paper proposes a robust deep-learning approach that consists of long short-term memory (LSTM) and gated recurrent unit (GRU) neural networks as base learners in a stacking ensemble framework, with a multilayer perceptron (MLP) as the meta-learner. Meanwhile, the hybrid synthetic minority oversampling technique and edited nearest neighbor (SMOTE-ENN) method is employed to balance the class distribution in the dataset. The experimental results showed that combining the proposed deep learning ensemble with the SMOTE-ENN method achieved a sensitivity and specificity of 1.000 and 0.997, respectively, which is superior to other widely used ML classifiers and methods in the literature.

show abstract

“…In recent years, artificial intelligence technology (mainly after deep learning introduces) has been applied to many applications, including ASR (Audio Sound Recognition) [1], [2] image or scene classification [3], [4], video analysis [5], games [6], [7] autonomous vehicle [8], [9] and financial sector [10]. Person re-identification is introduced as an image-based person search in a closed environment, such as a mall or building.…”

Section: Introductionmentioning

confidence: 99%

Lightweight pyramid residual features with attention for person re-identification

Rachmadi

Purnama²,

Nugroho³

2023

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

Person re-identification is one of the problems in the computer vision field that aims to retrieve similar human images in some image collections (or galleries). It is very useful for people searching or tracking in a closed environment (like a mall or building). One of the highlighted things on person re-identification problems is that the model is usually designed only for performance instead of performance and computing power consideration, which is applicable for devices with limited computing power. In this paper, we proposed a lightweight residual network with pyramid attention for person re-identification problems. The lightweight residual network adopted from the residual network (ResNet) model used for CIFAR dataset experiments consists of not more than two million parameters. An additional pyramid features extraction network and attention module are added to the network to improve the classifier's performance. We use CPFE (Context-aware Pyramid Features Extraction) network that utilizes atrous convolution with different dilation rates to extract the pyramid features. In addition, two different attention networks are used for the classifier: channel-wise and spatial-based attention networks. The proposed classifier is tested using widely use Market-1501 and DukeMTMC-reID person re-identification datasets. Experiments on Market-1501 and DukeMTMC-reID datasets show that our proposed classifier can perform well and outperform the classifier without CPFE and attention networks. Further investigation and ablation study shows that our proposed classifier has higher information density compared with other person re-identification methods.

show abstract

An evaluation of deep learning models for chargeback Fraud detection in online games

Cited by 6 publications

References 25 publications

Evolutionary game analysis of online game studios and online game companies participating in the virtual economy of online games

Evolutionary game analysis of online game studios and online game companies participating in the virtual economy of online games

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

Lightweight pyramid residual features with attention for person re-identification

Contact Info

Product

Resources

About