【摘要】：P2P網(wǎng)貸在爆發(fā)式增長的同時(shí),也面臨著重大的信用風(fēng)險(xiǎn),個(gè)人信用評估是降低信用風(fēng)險(xiǎn)的重要方法。根據(jù)P2P網(wǎng)貸自身的特點(diǎn),對影響P2P網(wǎng)貸借款人信用風(fēng)險(xiǎn)的因素進(jìn)行分析,引入互聯(lián)網(wǎng)信息領(lǐng)域特有的風(fēng)險(xiǎn)因素,建立了P2P網(wǎng)貸個(gè)人信用風(fēng)險(xiǎn)評估指標(biāo)體系�；谠撝笜�(biāo)體系,考慮P2P網(wǎng)貸中"軟信息"較多、"硬信息"缺失的特點(diǎn),提出了基于BP神經(jīng)網(wǎng)絡(luò)的信用評估模型。為了提高BP神經(jīng)網(wǎng)絡(luò)的收斂速度和精度,將改進(jìn)的果蠅優(yōu)化算法作為BP神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)算法,對神經(jīng)網(wǎng)絡(luò)的權(quán)重進(jìn)行訓(xùn)練。通過"人人貸"平臺收集的樣本數(shù)據(jù)進(jìn)行實(shí)驗(yàn)驗(yàn)證。結(jié)果表明:改進(jìn)果蠅神經(jīng)網(wǎng)絡(luò)評估模型比傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò)模型有更強(qiáng)的學(xué)習(xí)能力和預(yù)測能力,是P2P網(wǎng)貸個(gè)人信用風(fēng)險(xiǎn)評估的有效方法。
[Abstract]:P2P network loan is facing great credit risk while it is exploding. Personal credit evaluation is an important method to reduce credit risk. According to the characteristics of P2P network loan, this paper analyzes the factors that affect the credit risk of P2P network loan borrowers, introduces the unique risk factors in the field of Internet information, and establishes the evaluation index system of P2P network loan individual credit risk. Based on this index system, considering the characteristics of "soft information" and "hard information" in P2P network loan, a credit evaluation model based on BP neural network is proposed. In order to improve the convergence speed and accuracy of the BP neural network, the improved Drosophila optimization algorithm is used as the learning algorithm of the BP neural network, and the weight of the neural network is trained. Through the "everyone loan" platform collected sample data for experimental verification. The results show that the improved evaluation model of Drosophila neural network has stronger learning ability and prediction ability than the traditional BP neural network model, and it is an effective method to evaluate the credit risk of individuals in P2P network.
【作者單位】： 南京工業(yè)大學(xué)經(jīng)濟(jì)與管理學(xué)院;
【基金】：國家自然科學(xué)基金面上項(xiàng)目(71371097) 南京工業(yè)大學(xué)科研項(xiàng)目(ZKJ201531)
【分類號】：F724.6;F832.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 楊碩;許可;黃鵬;;基于SOM神經(jīng)網(wǎng)絡(luò)技術(shù)的卷煙零售客戶自組織分類[J];商場現(xiàn)代化;2009年04期

2 朱巖;;數(shù)字神經(jīng)向大智慧延伸——掃描神經(jīng)網(wǎng)絡(luò)技術(shù)的商業(yè)應(yīng)用[J];互聯(lián)網(wǎng)周刊;1999年17期

3 張世浩;;精準(zhǔn)廣告 再造P2P時(shí)代網(wǎng)絡(luò)盈利新模式[J];中國廣告;2006年10期

4 倪月娟;;我國P2P小額網(wǎng)絡(luò)信貸研究[J];現(xiàn)代商業(yè);2013年27期

5 余凡;余紅偉;許偉;;基于BP神經(jīng)網(wǎng)絡(luò)的消費(fèi)者網(wǎng)絡(luò)質(zhì)量安全信息預(yù)警實(shí)證研究[J];宏觀質(zhì)量研究;2014年01期

6 劉增明;陳運(yùn)非;蔣海青;;基于PCA-BP神經(jīng)網(wǎng)絡(luò)方法的供應(yīng)商選擇[J];工業(yè)工程與管理;2014年01期

7 ;P2P無線東京大登陸[J];網(wǎng)際商務(wù);2001年07期

8 張志強(qiáng);;當(dāng)前我國P2P信貸現(xiàn)狀及發(fā)展對策[J];華北金融;2013年07期

9 樊融杰;;P2P入侵外匯交易[J];英才;2014年03期

10 朱s，

本文編號：2397768