本文選題：欺詐檢測(cè)　切入點(diǎn)：元胞自動(dòng)機(jī)　出處：《重慶大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：C2C平臺(tái)中存在不誠(chéng)實(shí)的用戶，他們通過產(chǎn)生大量的虛擬交易快速提高信用積分，然后在高信用度的掩護(hù)下實(shí)施欺詐性質(zhì)的交易，讓C2C電子商務(wù)遭遇了嚴(yán)重的信用危機(jī)。先刷信用積分再實(shí)施欺詐的行為通常由團(tuán)伙產(chǎn)生，團(tuán)伙由欺詐性賣家和虛假的買家同伙組成，他們相互掩護(hù)使得對(duì)他們的識(shí)別難度非常大。有效地對(duì)C2C平臺(tái)用戶可信性進(jìn)行重新評(píng)估并識(shí)別欺詐團(tuán)伙，能維持C2C公平的交易環(huán)境，緩解信用危機(jī)，也能給消費(fèi)者減少麻煩和損失，具有極大的研究意義。 目前對(duì)在線交易欺詐的研究主要集中在商品拍賣、股票和期貨市場(chǎng)，對(duì)一口價(jià)商品交易欺詐的研究非常少。我們仔細(xì)分析了國(guó)內(nèi)外欺詐檢測(cè)相關(guān)文獻(xiàn)，發(fā)現(xiàn)當(dāng)前使用的檢測(cè)方法存在著一些問題，在此基礎(chǔ)上，本文以發(fā)掘識(shí)別欺詐團(tuán)伙新途徑為目的，尋求一種既考慮用戶基本特征屬性又考慮用戶所處的局部交易網(wǎng)絡(luò)的全新的檢測(cè)模型。 元胞自動(dòng)機(jī)（CA）能以微觀個(gè)體簡(jiǎn)單的局部自組織行為表現(xiàn)系統(tǒng)整體復(fù)雜性，不規(guī)則元胞自動(dòng)機(jī)（ICA）是對(duì)標(biāo)準(zhǔn)CA的擴(kuò)展，能對(duì)復(fù)雜交易網(wǎng)絡(luò)進(jìn)行模擬，而學(xué)習(xí)自動(dòng)機(jī)（LA）能根據(jù)環(huán)境反饋?zhàn)詣?dòng)調(diào)整自身狀態(tài)，將它們結(jié)合在一起形成了一個(gè)具有強(qiáng)大適應(yīng)能力的能對(duì)復(fù)雜交易網(wǎng)中用戶狀態(tài)進(jìn)行判別的分類模型FD_ICLA。本文采用機(jī)器學(xué)習(xí)算法，基于用戶基本屬性及交易統(tǒng)計(jì)屬性挖掘產(chǎn)生本地規(guī)則。本地規(guī)則以鄰居相關(guān)信息和內(nèi)嵌LA選擇的動(dòng)作為輸入產(chǎn)生加強(qiáng)信號(hào)，內(nèi)嵌LA依據(jù)此信號(hào)調(diào)整元胞狀態(tài)。FD_ICLA模型采用“自下而上”的模擬方法，通過微觀上反復(fù)執(zhí)行的推理，實(shí)現(xiàn)對(duì)宏觀狀態(tài)的判定。 用單個(gè)FD_ICLA進(jìn)程對(duì)包含上百萬(wàn)個(gè)節(jié)點(diǎn)的交易網(wǎng)絡(luò)進(jìn)行分析是非常耗時(shí)的，考慮到元胞自動(dòng)機(jī)的局部依賴性，本文基于圖的K劃分算法，提出了并行FD_ICLA模型，，該改進(jìn)模型能有效地將計(jì)算壓力分散到多個(gè)的機(jī)器，增強(qiáng)了模型的擴(kuò)展能力。同時(shí)，本文基于Gephi實(shí)現(xiàn)了可視化原型系統(tǒng)能直觀展示模型分析結(jié)果。 最后，為了檢驗(yàn)?zāi)Ｐ蛯?duì)欺詐團(tuán)伙的識(shí)別效果及時(shí)間性能，本文從Kongfz平臺(tái)采集真實(shí)交易數(shù)據(jù)集，并組織多組對(duì)比實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明：1）相對(duì)S2C+SNA欺詐檢測(cè)算法及PeerGroup欺詐檢測(cè)算法，F(xiàn)D_ICLA模型能以更高的精確度對(duì)同盟進(jìn)行識(shí)別，而且能更有效的挖掘交易網(wǎng)中存在的欺詐團(tuán)伙；2）并行FD_ICLA模型能有效彌補(bǔ)單進(jìn)程模式高耗時(shí)缺陷。
[Abstract]:There are dishonest users in the C2C platform, who increase credit score quickly by generating a large number of virtual transactions, and then carry out fraudulent transactions under the cover of high credit degree. C2C e-commerce has suffered a serious credit crisis. Credit points are used before fraud is committed by gangs, which are made up of fraudulent sellers and false buyers. They cover each other and make it very difficult to identify them. Effectively reassessing the credibility of C2C platform users and identifying fraudulent gangs can maintain a fair trading environment for C2C and alleviate the credit crisis. Also can reduce the trouble and loss of consumers, has a great significance of research. At present, the research on online trading fraud is mainly focused on the commodity auction, stock and futures markets, and the research on the fraud of one price commodity trading is very few. We have carefully analyzed the domestic and foreign relevant documents on fraud detection. It is found that there are some problems in the current detection methods. On this basis, the purpose of this paper is to find new ways to identify fraudulent gangs. This paper seeks a new detection model which considers both the basic characteristics of the user and the local transaction network in which the user is located. Cellular automata (CAA) can represent the whole complexity of the system by the simple local self-organization behavior of micro-individuals. The irregular cellular automata (ICA) is an extension of the standard CA and can be used to simulate complex trading networks. Learning automata can automatically adjust their state according to environmental feedback. This paper combines them to form a powerful adaptive classification model FDS _ CLAs, which can judge the user's status in a complex trading network. In this paper, a machine learning algorithm is used. Local rules are generated based on user's basic attributes and transaction statistical attributes. Local rules generate reinforcement signals based on neighbor related information and embedded LA selected actions. Based on this signal, the embedded LA adjusts the cellular state. FDC _ ICLA model adopts the "bottom-up" simulation method, and realizes the judgment of macroscopic state by microcosmic repeated reasoning. It is time consuming to analyze a transaction network with millions of nodes by using a single FD_ICLA process. Considering the local dependence of cellular automata, this paper proposes a parallel FD_ICLA model based on the K partition algorithm of graph. The improved model can effectively disperse the computational pressure to multiple machines and enhance the expansion ability of the model. At the same time, this paper implements a visual prototype system based on Gephi, which can visually display the analysis results of the model. Finally, in order to test the effect and time performance of the model, we collect the real transaction data set from Kongfz platform. The experimental results show that compared with S2C SNA fraud detection algorithm and PeerGroup fraud detection algorithm, the model can identify the alliance with higher accuracy. Moreover, the parallel FD_ICLA model can effectively mine the fraud gang in the transaction network. The parallel FD_ICLA model can effectively compensate for the high time consuming defects of the single process pattern.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：F724.6;TP301.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 鄢勇,劉鍵;圖的最優(yōu)K劃分[J];計(jì)算機(jī)學(xué)報(bào);1990年03期

2 竇如靜;何成武;;學(xué)習(xí)自動(dòng)機(jī)概述[J];自動(dòng)化學(xué)報(bào);1984年04期

3 朱作付;徐超;錢俊;;基于信息論的圖K劃分方法[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年11期

4 羅平,杜清運(yùn),雷元新,王濤;地理特征元胞自動(dòng)機(jī)及城市土地利用演化研究[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2004年06期

本文編號(hào)：1611845