資通訊科技發展為人類生活帶來極大便利，但也伴隨而來不良的影響。資通技術濫用於詐騙犯罪情形遍及世界各地，嚴重衝擊被害者日常生活。其中，大眾營銷詐欺是一種橫跨多國的詐欺手法，運用大眾傳播媒體，鎖定多數不特定年齡、社會各階層人士進行詐騙，以獲取錢財或有價物品。

大眾營銷詐欺起源於地區性犯罪，但因高報酬低風險特性，迅速蔓延並襲捲全球。據內政部警政署統計，2019年全臺灣發生34,482件詐欺案件，多數與大眾營銷詐欺相關，也導致約新臺幣30餘億元的財產損失。儘管有關部門致力於預防並打擊大眾營銷詐欺犯罪，威脅仍舊存在且未見減弱跡象。

本研究目的在發展全球性大眾營銷電信詐欺之在地解決方案。決策所使用之資料來自個別犯嫌詢問筆錄中擷取之屬性資料，並與客觀資料交互驗證以力求真實。受限於犯嫌所述主觀資料精準度不一及部分客觀資料因法律保障而有缺漏情形，故應用約略集合理論方法，分析2018-2019年臺灣北部詐欺集團提領車手組196名成員之七個條件屬性，進而分類出掌握關鍵金流車手頭並驗證2020年臺灣北部詐欺集團27名成員資料，以協助執法機關根除詐欺集團洗錢金流並壓制集團組織運作，萃取規則之結果並可作為檢警調等執法機關在偵查戰略與預防策略面上之思考，期能以數據科學角度打擊詐欺犯罪。

The rapid growth of telecommunication technology brings convenience to our daily life. However, there are side effects such as the technology being misused on fraudulent crime and significantly impacted people’s lives worldwide. Mass-marketing fraud related to fraud schemes that use mass-communications media, targeting individuals of all ages and walks of life to solicit and obtain money or other items of value from multiple victims in one or more jurisdictions.

Mass-marketing telecommunication fraud soon evolved from a regional crime problem into a pervasive global criminal threat due to its high profit with low risk. According to the National Police Administration in Taiwan, 34,482 cases of fraud occurred in 2019. Most cases were related to mass-marketing telecommunication fraud and caused approximately 3 billion NTD of property loss. Despite the government’s effort to prevent mass-marketing telecommunication fraud from happening, the threat still exist and shows no sign of perishing.

This study aims to develop an effective approach to classify money-withdrawing group leaders in fraudulent crime operations and combat mass-marketing telecommunication fraud. Domain experts select 7 types of conditional attributes related to money-withdrawing group suspects in Northern Taiwan from 2018 to 2020. After cross validating suspects’ subjective interrogation with direct evidence and circumstantial evidence, the data are extracted and divided into training and testing dataset of 196 suspects from 2018 to 2019, and validating dataset of 27 suspects from 2020.

The study employs Rough Set Theory for prediction due to the inconsistent of accuracy from the extracted subjective and uncertain data. Therefore, helping law enforcement to locate money-withdrawing group leaders who control the critical money flow for money-laundering process of mass-marketing telecommunication fraud operations. The research can generate effective rules to support related decision on combating and preventing local fraudulent crime, eventually crack down the whole structure of global mass-marketing telecommunication fraud.

Chapter 1 Introduction 1
1.1 Background and Motivation 1
1.2 Research Objectives 2
1.3 Thesis Organization 3
Chapter 2 Literature Review 4
2.1 Mass-marketing telecommunication fraud detection 4
2.2 Rough set theory 5
2.3 UNISON framework 6
Chapter 3 Research Framework 9
3.1 Understand and Define the Right Problem 9
3.2 Niche exploration 10
3.3 Influence relationships structuring 10
3.4 Sense and describe the results 11
3.5 Overall judgments for subjective assessments 12
3.6 make appropriate decisioN 18
Chapter 4 An Empirical Study 19
4.1 Understand and Define the Right Problem 19
4.2 Niche exploration 20
4.3 Influence relationships structuring 22
4.4 Sense and describe the results 22
4.5 Overall judgments for subjective assessments 24
4.6 make appropriate decisioN 29
Chapter 5 Conclusion and future research directions 30
5.1 Conclusion 30
5.2 Future research directions 31
Reference 32

吳宗穎 (2016) 從情境犯罪預防觀點探究國內詐欺犯罪之利益與風險－詐欺犯罪人的自我陳述，國立中正大學犯罪防治學系研究所碩士論文。
林耿徽 (2013) 電信詐欺犯罪偵查管理之研究，中央警察大學刑事警察研究所碩士論文。
紀延熹 (2014) 海峽兩岸跨境電信詐欺犯罪歷程之研究-以假冒機構詐欺集團犯罪模式為例，國立臺北大學犯罪學研究所碩士論文。
許華孚、吳宗穎、劉育偉 (2018) 本土化電信詐欺犯罪利益及風險之實證研究，公共事務評論，第 17 卷，第 2 期，頁25。
張鴻昌 (2001) 以機器學習分析自設非法電信平台詐欺電話之通聯紀錄，中央警察大學刑事警察研究所碩士論文。
曾雅芬 (2016)行騙天下：臺灣跨境電信詐欺犯罪網絡之分析，國立政治大學國家發展研究所博士論文。
潘育華 (2019) 電信詐騙提款犯罪熱點之環境特性分析-以新竹市為例，國立清華大學環境與文化資源學系社區與社會學習領域碩士在職專班論文。
劉家妤 (2012) 跨境電話詐欺集團特徵之研究，國立臺北大學犯罪學研究所碩士論文。
謝浚鋒 (2009) 電信詐欺犯罪模式與偵查之研究，國立臺北大學犯罪學研究所碩士論文。
簡禎富（2005），決策分析與管理，雙葉書廊，台北。
簡禎富（2019），紫式決策工具全書，雙葉書廊，台北。
Ahn, B. S., Cho, S. S. & Kim, C. Y. (2000), The integrated methodology of rough set theory and artificial neural network for business failure prediction, Expert Systems with Applications, 18(2), 65-74.
Andrzej J.& Lala S.-R.(2019), Package ‘RoughSets’. Data Analysis Using Rough Set and Fuzzy Rough Set Theories. Ver. 1.3-7.
Barbagallo, S., Consoli, S., Pappalardo, N., Greco, S. & Zimbone, S. M. (2006), “Discovering reservoir operating rules by a Rough Set approach,” Water Resources Management, 20(1), 19-36.
Chien, C.-F. & Chen, L.-F. (2007), “Using Rough Set Theory to Recruit and Retain High-Potential Talents for Semiconductor Manufacturing,” IEEE Transactions on Semiconductor Manufacturing, Vol.20, No.4, pp.528-541.
Chien, C.-F., Wang, H., & Wang, M. (2007), “A UNISON framework for analyzing alternative strategies of IC fnal testing for enhancing overall operational effectiveness,” International Journal of Production Economics, 107(1), 20–30.
Chien, C.-F., & Hsu, C.-Y. (2011), “UNISON analysis to model and reduce step-and-scan overlay errors for semiconductor manufacturing,” Journal of Intelligent Manufacturing, 22(3), 399–412.
Chien, C.-F., Kerh, R., Lin, K.-Y., Yu, A. P.-I (2016), “Data-driven innovation to capture user-experience product design: An empirical study for notebook visual aesthetics design,” Computers & Industrial Engineering, 99, 162–173.
Fu, W.-H., & Chien, C.-F. (2019), “UNISON data-driven intermittent demand forecast framework to empower supply chain resilience and an empirical study in electronics distribution,” Computers & Industrial Engineering, 135, 940-949.
Hu, Y.-F., Hou, J.-L., & Chien, C.-F. (2019), “A UNISON framework for knowledge management of university-industry collaboration and an illustration,” Computers & Industrial Engineering, 129, 31–43.
Keeney, R.L., Raiffa, H. (1993), “Decisions with multiple objectives: preferences and value tradeoffs,” Cambridge University Press, New York.
Laimek, R. & Kaothanthong, N.,(2018), “ATM Fraud Detection using Behavior Model,” Asian Conference on Defense Technology, Oct.25-26, Hanoi.
Lin, K.-Y., Chien, C.-F., & Kerh, R. (2016), “UNISON framework of data-driven innovation for extracting user experience of product design of wearable devices,” Computers & Industrial Engineering, 99, 487–502.
Linoff, G. S., & Berry, M. J. A. (2011), "Data mining techniques: For marketing, sales and customer relationship management”, 3rd ed.
Lin, Y.-H., Chien, C.-F., & Yu, C.-M. (2015), “UNISON decision analysis framework for workforce planning for semiconductor fabs and an empirical study.” International Journal of Industrial Engineering: Theory, Applications and Practice, 22(5), 631–644.
Pawlak, Z. (1982), “Rough sets,” International Journal of Computer and Information Sciences.
Pawlak, Z. (1997), “Rough set approach to knowledge-based decision support,” European Journal of Operational Research, 99(1), 48–57.
Peng, J.-T. Chien, C.-F. & Tseng, T.-L.B.(2004), “Rough set theory for data mining for fault diagnosis on distribution feeder,” IEE Proceedings - Generation, Transmission and Distribution, Vol.151, No.6, November.
Robin, X.(2020), Package ‘pROC’, Display and Analyze ROC Curves, Ver.1.17.0.1
Shalabi, L.-A.(2017), “Perceptions of crime behavior and Relationships: Rough Set
Based Approach,” International Journal of Computer Science and Information Security, Vol.15, No.3, March.
Su, C.-T. & Hsu, J.-H. (2006), Precision parameter in the variable precision rough sets model: an application. Omega-International Journal of Management Science, 34(2), 149-157.
Xu, W., Pang, Y., Ma, J., Wang, S.-Y., Hao, G., Zeng, S.& Qian, Y.-H. (2008), “Fraud Detection in Telecommunication: A Rough Fuzzy Set Based Approach,” International Conference on Machine Learning and Cybernetics, July 12-15.
Zhou, C.& Lin, Z. (2018), “Study on Fraud Detection of Telecom Industry Based on Rough Set,” IEEE 8th Annual Computing and Communication Workshop and Conference, Jan. 8-10.