【摘要】：隨著互聯(lián)網(wǎng)金融及互聯(lián)網(wǎng)大數(shù)據(jù)在國內(nèi)迅速地發(fā)展,以及互聯(lián)網(wǎng)+時(shí)代的到來,興起了一大批的互聯(lián)網(wǎng)金融網(wǎng)貸企業(yè),與此同時(shí)用戶可能發(fā)生的欺詐風(fēng)險(xiǎn)成為互聯(lián)網(wǎng)金融的一個(gè)重要關(guān)注方面,如何有效地預(yù)見和識別潛在的用戶欺詐行為,成為目前互聯(lián)網(wǎng)金融的重要目標(biāo)之一。本文試圖根據(jù)某公司提供的關(guān)于社交方面和消費(fèi)方面的數(shù)據(jù),探索一個(gè)能夠比較準(zhǔn)確預(yù)測用戶欺詐行為的風(fēng)控模型,達(dá)到減少因欺詐帶來的損失的目的。本文首先對數(shù)據(jù)進(jìn)行觀察和清洗,然后把清洗后的數(shù)據(jù)進(jìn)行橫向合并;其次,為了了解消費(fèi)行為與欺詐的關(guān)系以及社交網(wǎng)絡(luò)與欺詐的關(guān)系,做了一些探索性的描述性統(tǒng)計(jì)分析,并且分析了消費(fèi)類型與用戶欺詐關(guān)系,消費(fèi)金額與用戶欺詐關(guān)系以及欺詐用戶緊密程度的影響,然后通過探索的結(jié)果選擇合適的變量;再結(jié)合目前數(shù)據(jù)挖掘的機(jī)器學(xué)習(xí)算法和現(xiàn)代化金融理論對上述變量訓(xùn)練模型;再對模型進(jìn)行對比并且對模型結(jié)果進(jìn)行評價(jià),根據(jù)評價(jià)結(jié)果再優(yōu)化我們的模型;最終通過ROC曲線得出較準(zhǔn)確的風(fēng)控模型。
[Abstract]:With the rapid development of Internet finance and Internet big data in China, and the arrival of Internet era, a large number of Internet finance and net loan enterprises have emerged. At the same time, the possible fraud risk of users has become an important concern in Internet finance. How to effectively foresee and identify potential user fraud has become one of the important targets of Internet finance. This paper attempts to explore a risk control model that can accurately predict user fraud based on the data on social and consumer aspects provided by a company in order to reduce the losses caused by fraud. Firstly, the data are observed and cleaned, and then the data after cleaning are combined horizontally. Secondly, in order to understand the relationship between consumer behavior and fraud and the relationship between social network and fraud, this paper makes some exploratory descriptive statistical analysis, and analyzes the relationship between consumption type and user fraud. The relationship between consumption amount and user fraud and the influence of the closeness of fraudulent users, and then the appropriate variables are selected through the results of exploration. Then combined with the current data mining machine learning algorithm and modern financial theory to the above variables training model, then compare the model and evaluate the results of the model, and then optimize our model according to the evaluation results. Finally, a more accurate risk control model is obtained by ROC curve.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：D924.35;F724.6;F832.4

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 孫淑萍;;互聯(lián)網(wǎng)金融風(fēng)險(xiǎn)控制[J];金融理論與實(shí)踐;2014年11期

2 高漢;;互聯(lián)網(wǎng)金融的發(fā)展及其法制監(jiān)管[J];中州學(xué)刊;2014年02期

3 宗瀟泳;;互聯(lián)網(wǎng)金融相關(guān)理論問題探析[J];經(jīng)營管理者;2014年05期

4 劉英;羅明雄;;互聯(lián)網(wǎng)金融模式及風(fēng)險(xiǎn)監(jiān)管思考[J];中國市場;2013年43期

5 謝平;鄒傳偉;;互聯(lián)網(wǎng)金融模式研究[J];金融研究;2012年12期

6 伍永鋒;;基于模糊支持向量機(jī)的電子商務(wù)交易安全風(fēng)險(xiǎn)評估方法[J];科技通報(bào);2012年09期

7 姚瀟;余樂安;;模糊近似支持向量機(jī)模型及其在信用風(fēng)險(xiǎn)評估中的應(yīng)用[J];系統(tǒng)工程理論與實(shí)踐;2012年03期

8 胡海青;張瑯;張道宏;陳亮;;基于支持向量機(jī)的供應(yīng)鏈金融信用風(fēng)險(xiǎn)評估研究[J];軟科學(xué);2011年05期

，

本文編號：2423385