請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/641
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳縕儂(Yun-Nung Chen) | |
dc.contributor.author | Jian-Jia Su | en |
dc.contributor.author | 蘇健嘉 | zh_TW |
dc.date.accessioned | 2021-05-11T04:51:51Z | - |
dc.date.available | 2019-08-20 | |
dc.date.available | 2021-05-11T04:51:51Z | - |
dc.date.copyright | 2019-08-20 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-15 | |
dc.identifier.citation | [1] J. Burez and D. Van den Poel, “Handling class imbalance in customer churn prediction,”Expert Systems with Applications, vol. 36, no. 3, pp. 4626–4636, 2009.
[2] C. Phua, D. Alahakoon, and V. Lee, “Minority report in fraud detection: classification of skewed data,” Acm sigkdd explorations newsletter, vol. 6, no. 1, pp. 50–59,2004. [3] M. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer,“Deep contextualized word representations,” in Proceedings of the 2018 Conferenceof the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, Volume 1 (Long Papers), pp. 2227–2237, 2018. [4] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019Conference of the North American Chapter of the Association for ComputationalLinguistics: Human Language Technologies, Volume 1 (Long Papers), 2019. [5] J. R. Firth, “A synopsis of linguistic theory 1930-55.,” in Studies in Linguistic Analysis (special volume of the Philological Society), vol. 1952-59, pp. 1–32, Oxford:The Philological Society, 1957. [6] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” Proceedings of Workshop at ICLR, 2013. [7] J. L. Elman, “Finding structure in time,” Cognitive science, vol. 14, no. 2, pp. 179–211, 1990. [8] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997. [9] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in neural information processing systems, pp. 5998–6008, 2017. [10] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,”in Proceedings of the IEEE conference on computer vision and pattern recognition,pp. 770–778, 2016. [11] J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,” arXiv preprint arXiv:1607.06450, 2016. [12] C.-H. Lee, “A network embedding on phone call graph,” Master’s thesis, National Taiwan University, 2018. [13] R. A. Becker, C. Volinsky, and A. R. Wilks, “Fraud detection in telecommunications: History and lessons learned,” Technometrics, vol. 52, no. 1, pp. 20–33, 2010. [14] M. Weatherford, “Mining for fraud,” IEEE Intelligent Systems, vol. 17, no. 4, pp. 4–6, 2002. [15] D. Olszewski, “A probabilistic approach to fraud detection in telecommunications,”Knowledge-Based Systems, vol. 26, pp. 246–258, 2012. [16] M. I. M. Yusoff, I. Mohamed, and M. R. A. Bakar, “Fraud detection in telecommunication industry using gaussian mixed model,” in 2013 International Conference on Research and Innovation in Information Systems (ICRIIS), pp. 27–32, IEEE, 2013. [17] S. Abu-El-Haija, B. Perozzi, and R. Al-Rfou, “Learning edge representations via low-rank asymmetric projections,” in Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 1787–1796, ACM, 2017. [18] S. Cao, W. Lu, and Q. Xu, “Deep neural networks for learning graph representations,” in Thirtieth AAAI Conference on Artificial Intelligence, 2016. [19] B. Perozzi, R. Al-Rfou, and S. Skiena, “Deepwalk: Online learning of social representations,” in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 701–710, ACM, 2014. [20] A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 855–864, ACM, 2016. [21] V. S. Tseng, J.-C. Ying, C.-W. Huang, Y. Kao, and K.-T. Chen, “Fraudetector: A graph-mining-based framework for fraudulent phone call detection,” in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2157–2166, ACM, 2015. [22] T. Saito and M. Rehmsmeier, “The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets,” PloS one, vol. 10, no. 3, p. e0118432, 2015. [23] A. Beutel, P. Covington, S. Jain, C. Xu, J. Li, V. Gatto, and E. H. Chi, “Latent cross: Making use of context in recurrent recommender systems,” in Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 46–54, ACM, 2018. [24] F. A. Gers, J. Schmidhuber, and F. Cummins, “Learning to forget: Continual prediction with lstm,” in Proceedings of the 1999 Ninth International Conference on Artificial Neural Networks ICANN 99. (Conf. Publ. No. 470), IET, 1999. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/handle/123456789/641 | - |
dc.description.abstract | 本篇論文主要目的在提出一個即時辨識電話號碼是否為詐騙電話的模型。在辨識電話號碼是否為詐騙電話時,有兩個問題需要處理,一個是訓練好的模型無法適用於新的資料,而另一方面,可以對新出現的電話號碼進行辨識的模型又準確率不高。
我們提出一個模組化的通話表徵與辨識模型,藉由兩階段的訓練,學習產生通話表徵以及用通話表徵進行辨識。第一階段的通話行為預測訓練讓模型學會產生含有豐富資訊的通話表徵,有了通話表徵,就可以訓練一個簡單的分類器進行辨識是否為詐騙集團。模型在實驗中表現遠高於隨機分類並擊敗對通話行為沒有建模的基準模型。 在未來工作方面,可以考慮同時對多個電話號碼建模,因為有些詐騙行為是同時運用多個電話號碼協作完成。 | zh_TW |
dc.description.abstract | The main purpose of this thesis is to propose a model that can detect whether a phone number is a fraud in real-time. There are two problems in detecting fraud. Some methods can only apply at the same time interval as training data. On the other hand, a model that can apply to a new phone number have low precision.
We propose a modularized call representation and detection model. By two-phases training, our model can generate call representations and uses the call representations to detect fraud. In the first phase, call behavior prediction training allows model generating call representation containing rich information. We then train a simple classifier to detect fraud based on the call representation. Our model outperforms the random baseline and beats baseline model which lacking the call behavior module. As for future work, multi phone number modeling can be used to detect complex fraud because Some fraud is cooperating between several phone numbers. | en |
dc.description.provenance | Made available in DSpace on 2021-05-11T04:51:51Z (GMT). No. of bitstreams: 1 ntu-108-R06922081-1.pdf: 2986795 bytes, checksum: 581db0bd872cf42f79f0baad9ef1d6a6 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | Contents
Acknowledgements iii 摘要 v Abstract vii 1 Introduction 1 1.1 Motivation 1 1.2 Problem Description 2 1.3 Main Contributions 2 1.4 Thesis Structure 2 2 Background 5 2.1 Representation Learning 5 2.2 Recurrent Neural Models 6 2.2.1 Recurrent Neural Network (RNN) 6 2.2.2 Long Short-Term Memory unit (LSTM) 6 2.3 Self Attention Model 7 2.3.1 Scaled Dot-Product Attention 8 2.3.2 Multi-Head Attention 9 3 Dataset 11 3.1 Dataset Overview 11 4 Related Work 15 4.1 Network Embedding 15 4.2 Real Time Analysis 16 4.3 Summary 17 5 Problem Formulation 19 5.1 Goal 19 5.2 Input 19 5.3 Output 20 5.4 Evaluation metrics 20 6 Model 23 6.1 Overview 23 6.2 Feature Fusion 25 6.3 Sequence Modeling 26 6.4 Embedding Aggregation 28 6.5 Fraud Detection 30 6.6 Training and Inference 30 7 Experiment 31 7.1 Setup 31 7.2 Result 32 7.3 Effectiveness of Features 33 7.4 Comparison of Aggregation Methods 34 7.5 Embedding Visualization 34 7.6 Tradeoff Between Performance and Time Lag 35 8 Conclusion and Future Work 37 Bibliography 39 | |
dc.language.iso | en | |
dc.title | 基於實時通話行為建模之詐騙電話偵測研究 | zh_TW |
dc.title | Modeling Real-Time Call Behaviors for Fraudulent Phone Call Detection | en |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 曹昱(Yu Tsao),古倫維(Lun-Wei Ku),黃挺豪(Ting-Hao Huang) | |
dc.subject.keyword | 神經網路,模型化序列,詐騙偵測,詞嵌入,表徵, | zh_TW |
dc.subject.keyword | neural networks,sequence modeling,fraud detection,embedding,representations, | en |
dc.relation.page | 41 | |
dc.identifier.doi | 10.6342/NTU201903398 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2019-08-15 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf | 2.92 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。