X-FDS : 게임 결제 로그 기반 XAI적용 이상 거래탐지 모델 연구
Why Should I Ban You! : X-FDS (Explainable FDS) Model Based on Online Game Payment Log
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
게임에 대한 결제 수단과 방식이 다양해지는 가운데, 관련된 금융사고가 이용자와 게임사에 심각한 문제를 야기하고 있다. 최근 게임 결제 시스템에 대해 게임사는 이상거래탐지시스템(FDS)을 도입하여 금융 사고를 방지하고 있다. 하지만, FDS는 지속적으로 탐지 패턴을 변경해야 하므로 효과적이지 않고 판단 결과에 따른 근거를 제시할 수 없다. 본 논문에서는 실제 게임회사의 결제 로그 데이터 중 이상거래를 분석하여 관련된 피처를 생성하였다. 비지도학습 모델중 하나인 오토인코더를 사용하여 이상거래를 탐지하는 모델을 구축하였으며, 그 결과 85% 이상의 정확도를 얻을 수 있었다. 이를 XAI-SHAP을 적용한 X-FDS를 사용하여 이상 거래탐지에 대한 영향력이 가장 높은 피처는 나라, 거래 금액과 거래 매체, 이용자의 나이임을 알 수 있었다. 이를 바탕으로 제시한 모델의 판단 결과에 편향성을 주는 피처에 가중치를 세부 조정하여 최종적으로 정확도 94%의 개선된 탐지 모델을 도출하였다.
Abstract
With the diversification of payment methods and games, related financial accidents are causing serious problems for users and game companies. Recently, game companies have introduced an Fraud Detection System (FDS) for game payment systems to prevent financial incident. However, FDS is ineffective and cannot provide major evidence based on judgment results, as it requires constant change of detection patterns. In this paper, we analyze abnormal transactions among payment log data of real game companies to generate related features. One of the unsupervised learning models, Autoencoder, was used to build a model to detect abnormal transactions, which resulted in over 85% accuracy. Using X-FDS (Explainable FDS) with XAI-SHAP, we could understand that the variables with the highest explanation for anomaly detection were the amount of transaction, transaction medium, and the age of users. Based on X-FDS, we derive an improved detection model with an accuracy of 94% was finally derived by fine-tuning the importance of features that adversely affect the proposed model.
참고문헌 (23)
- "Newzoo’s games trends to w atch in 2021"[URL]
- 김하나, "MMORPG 게임 내 계정도용 탐지 모델에 관한 연구", 정보보호학회논문지, 25(3), pp.627~637 (2015), 한국정보보호학회[DOI]
- W. Y. Moon, "Adaptive fraud detection framework for fintech based on machine learning", Advanced Science Letters, 23(10), pp.10167~10171 (2017)
- Ge, Dingling, "Credit card fraud detection using lightgbm model", 2020International Conference on E-Commerce and Internet Technology (ECIT), pp.232~236 (2020), IEEE
- C. V. Priscilla, "Influence of optimizing xgboost to handle class imbalance in credit card fraud detection", 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), pp.1309~1315 (2020), IEEE
- C. Liu, "Financial fraud detection model : Based on random forest", International journal of economics and finance, 7(7) (2015)
- S. Misra, "An autoencoder based model for detecting fraudulent credit card transaction", Procedia Computer Science, 167, pp.254~262 (2020)
- A. Agrawal, "Credit card fraud detection:A case study", 2015 2nd International Conference on Computing for Sustainable Global Development (INDIACom), pp.5~7 (2015), IEEE
- 정윤경, "클래스 불균형 데이터에 적합한 기계 학습 기반 침입 탐지 시스템", 정보보호학회논문지, 27(6), pp.1385~1395 (2017), 한국정보보호학회[DOI]
- C. Sun, "Abnormal group-based joint medical fraud detection", IEEE Access, 7, pp.13589~13596 (2018)
- A. Adadi, "Peeking inside the black-box : a survey on explainable artificial intelligence(xai)", IEEE access, 6, pp.52138~52160 (2018)
- A. B. Arrieta, "Explainable artificial intelligence(xai) : Concepts, taxonomies, opportunities and challenges toward re sponsible ai", Information Fusion, 58, pp.82~115 (2020)
- D. Gunning, "Darpa’s explainable artificial intelligence(xai)program", AI Magazine, 40(2), pp.44~58 (2019)
- G. E. Melo-Acosta, "Fraud detec tion in big data using supervised and semi-supervised learning techniques", 2017 IEEE Colombian conference on communications and computing (COLCOM), pp.1~6 (2017), IEEE
- Y. Bengio, "Greedy layer-wise training of deep networks", Advances in neural information processing systems, pp.153~160 (2007)
- S. Lange, "Deep auto-encoder neural networks in reinforce ment learning", The 2010International Joint Conference on Neural Networks (IJCNN), pp.1~8 (2010), IEEE
- F. Farahnakian, "A deep auto-encoder based approach for intrusion detection system", 201820th International Conference on Advanced Communication Technology (ICACT), pp.178~183 (2018), IEEE
- M. Al-Shabi, "Credit card fraud detection using autoencoder model in unbalanced datasets", Journal of Advances in Mathematics and Computer Science, pp.1~16 (2019)
- L. S. Shapley, "A value for n-person games" (1953), Published by Princeton University Press
- S. M. Lundberg, "A unified approach to interpreting model predictions", Proceedings of the 31st international conference on neural information processing systems, pp.4768~4777 (2017)
- 천지영, "데이터 3법 시대의 익명화된 데이터 활용에 대한 제언", 정보보호학회논문지, 30(3), pp.503~512 (2020), 한국정보보호학회[DOI]
- S. Arora, "An analysis of the t-sne algorithm for data visualization", Conference On Learning Theory. PMLR, pp.1455~1462 (2018)
- N. Kasa, "Improving credit card fraud detection by profiling and clustering accounts", 2019 Systems and Information Engineering Design Symposium (SIEDS), pp.1~6 (2019), IEEE