基于數(shù)據(jù)挖掘的異常交易檢測方法
發(fā)布時間:2018-08-31 11:12
【摘要】:提出一種基于數(shù)據(jù)挖掘的異常交易檢測方法,可以在業(yè)務(wù)層面和操作層面對交易中的異常進行檢測。當(dāng)一個用戶提交一筆新的消費交易時,采用貝葉斯信念網(wǎng)絡(luò)算法判斷當(dāng)前交易屬于正常交易的后驗概率,作為在業(yè)務(wù)層面的可信因子;然后提取該用戶在當(dāng)前交易之前的若干個操作,與當(dāng)前交易一起構(gòu)成一個固定長度的操作序列,并通過BLAST-SSAHA算法將其與該用戶正常操作序列和已知異常操作序列進行比對,得出在操作層面的可信因子。綜合考慮業(yè)務(wù)層面的可信因子和操作層面的可信因子,最終決定當(dāng)前交易是否為異常交易。
[Abstract]:An anomaly detection method based on data mining is proposed, which can detect anomalies in transactions at the operational and business levels. When a user submits a new consumer transaction, the Bayesian belief network algorithm is used to judge the posteriori probability of the current transaction as a trust factor at the business level. Then, several operations of the user before the current transaction are extracted, together with the current transaction, a fixed length sequence of operations is formed, and the sequence of normal operations and known abnormal operations of the user is compared by the BLAST-SSAHA algorithm. A confidence factor at the operational level is obtained. Considering the trust factor of business level and the credibility factor of operation level, whether the current transaction is abnormal or not is finally decided.
【作者單位】: 中國銀聯(lián)股份有限公司電子支付研究院;復(fù)旦大學(xué)計算機科學(xué)技術(shù)學(xué)院網(wǎng)絡(luò)與信息安全研究所;
【分類號】:TP393.08;TP311.13
本文編號:2214805
[Abstract]:An anomaly detection method based on data mining is proposed, which can detect anomalies in transactions at the operational and business levels. When a user submits a new consumer transaction, the Bayesian belief network algorithm is used to judge the posteriori probability of the current transaction as a trust factor at the business level. Then, several operations of the user before the current transaction are extracted, together with the current transaction, a fixed length sequence of operations is formed, and the sequence of normal operations and known abnormal operations of the user is compared by the BLAST-SSAHA algorithm. A confidence factor at the operational level is obtained. Considering the trust factor of business level and the credibility factor of operation level, whether the current transaction is abnormal or not is finally decided.
【作者單位】: 中國銀聯(lián)股份有限公司電子支付研究院;復(fù)旦大學(xué)計算機科學(xué)技術(shù)學(xué)院網(wǎng)絡(luò)與信息安全研究所;
【分類號】:TP393.08;TP311.13
【相似文獻】
相關(guān)會議論文 前1條
1 楊本良;;壓縮候選的貝葉斯信念網(wǎng)絡(luò)構(gòu)造算法[A];廣西計算機學(xué)會2005年學(xué)術(shù)年會論文集[C];2005年
相關(guān)碩士學(xué)位論文 前2條
1 黃丹梅;多分類器系統(tǒng)在蛋白質(zhì)功能預(yù)測方面的應(yīng)用[D];吉林大學(xué);2010年
2 馬達;基于貝葉斯的判別理論及其算法實現(xiàn)[D];中國地質(zhì)大學(xué)(北京);2011年
,本文編號:2214805
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2214805.html
最近更新
教材專著