本文選題：客戶風(fēng)險(xiǎn) + 層次分析法��； 參考：《寧夏大學(xué)》2017年碩士論文

【摘要】：機(jī)動(dòng)車輛的迅猛發(fā)展,使人們出行方式發(fā)生巨大變化,人們對(duì)車輛的依賴性加重。其中,車險(xiǎn)作為一種保護(hù)類風(fēng)險(xiǎn)投資,以70%的業(yè)務(wù)量占財(cái)產(chǎn)險(xiǎn)公司的首位,更是受到保險(xiǎn)公司的關(guān)注。但是,在競(jìng)爭(zhēng)日益激烈的保險(xiǎn)公司中,整個(gè)車險(xiǎn)業(yè)務(wù)系統(tǒng)管理仍不完善,導(dǎo)致保險(xiǎn)公司對(duì)客戶的賠付過多,整個(gè)行業(yè)利潤(rùn)明顯下降。所以,在不斷增長(zhǎng)的車險(xiǎn)客戶歷史數(shù)據(jù)中,有效利用這些數(shù)據(jù)進(jìn)行車險(xiǎn)客戶風(fēng)險(xiǎn)等級(jí)評(píng)估模型的構(gòu)建,不僅可以及時(shí)識(shí)別投�？蛻舻臐撛陲L(fēng)險(xiǎn)、提供客戶投保建議;還可以為金融研究、社會(huì)管理提供有力的依據(jù),具有巨大的社會(huì)和商業(yè)價(jià)值。為此,本文展開如下研究工作:1.車險(xiǎn)客戶風(fēng)險(xiǎn)評(píng)估相關(guān)研究概述。概述風(fēng)險(xiǎn)管控的理論基礎(chǔ),強(qiáng)調(diào)風(fēng)險(xiǎn)管控的重要性,詳細(xì)分析車險(xiǎn)客戶風(fēng)險(xiǎn)評(píng)估指標(biāo)因素,包括車輛風(fēng)險(xiǎn)因素、駕駛?cè)孙L(fēng)險(xiǎn)因素、環(huán)境因素和投保特征因素,并結(jié)合定性和定量分析的層次分析法,對(duì)量化過的風(fēng)險(xiǎn)指標(biāo)數(shù)據(jù)進(jìn)行加權(quán)處理,搭建整個(gè)車險(xiǎn)客戶風(fēng)險(xiǎn)評(píng)估指標(biāo)體系,最后對(duì)車險(xiǎn)客戶風(fēng)險(xiǎn)評(píng)估的統(tǒng)計(jì)模型方法和人工智能方法進(jìn)行介紹。2.BP神經(jīng)網(wǎng)絡(luò)方法和粒子群算法分析研究。詳細(xì)介紹BP神經(jīng)網(wǎng)絡(luò)方法和粒子群算法(PSO)的原理基礎(chǔ),概括BP神經(jīng)網(wǎng)絡(luò)算法、粒子群優(yōu)化算法的實(shí)現(xiàn)思想和優(yōu)缺點(diǎn),分析粒子群算法的歷史發(fā)展進(jìn)程,提出一種可以克服PSO算法易陷入局部搜索、過早收斂的問題的改進(jìn)PSO算法,并通過標(biāo)準(zhǔn)函數(shù)測(cè)試,驗(yàn)證該改進(jìn)的PSO算法的有效性。3.基于改進(jìn)PSO-BP神經(jīng)網(wǎng)絡(luò)車險(xiǎn)客戶風(fēng)險(xiǎn)等級(jí)評(píng)估模型構(gòu)建。針對(duì)BP神經(jīng)網(wǎng)絡(luò)模型參數(shù)設(shè)置不足,分析具有全局尋優(yōu)功能的粒子群優(yōu)化算法對(duì)BP神經(jīng)網(wǎng)絡(luò)的優(yōu)化原理,并利用改進(jìn)的PSO算法確定BP神經(jīng)網(wǎng)絡(luò)的權(quán)值和閾值,構(gòu)建基于改進(jìn)PSO-BP神經(jīng)網(wǎng)絡(luò)算法的車客戶風(fēng)險(xiǎn)等級(jí)評(píng)估模型�；谝陨涎芯�,對(duì)某車險(xiǎn)行業(yè)客戶風(fēng)險(xiǎn)評(píng)估數(shù)據(jù)進(jìn)行了實(shí)例仿真,并把實(shí)驗(yàn)結(jié)果與BP模型和PSO-BP模型相比,分析得出PSO-BP車險(xiǎn)客戶風(fēng)險(xiǎn)等級(jí)評(píng)估模型在收斂速度和準(zhǔn)確度均有很大提升。
[Abstract]:With the rapid development of motor vehicles, great changes have taken place in people's travel mode and people's dependence on vehicles is becoming more and more serious. As a kind of protection risk investment, auto insurance accounts for the first place in property insurance companies with 70% of business volume, and is paid more attention by insurance companies. However, in the increasingly competitive insurance companies, the management of the whole auto insurance business system is still imperfect, which leads to the insurance companies pay too much to customers, and the profits of the whole industry decline obviously. Therefore, in the growing historical data of auto insurance customers, the effective use of these data to build a risk rating evaluation model of vehicle insurance customers, not only can identify the potential risks of insured customers in time, and provide customer insurance advice; It can also provide a powerful basis for financial research and social management, with great social and commercial value. Therefore, the following research work is carried out in this paper: 1. Summary of relevant research on risk assessment of auto insurance customers. This paper summarizes the theoretical basis of risk management, emphasizes the importance of risk control, and analyzes in detail the risk assessment index factors of vehicle insurance clients, including vehicle risk factors, driver risk factors, environmental factors and insurance characteristics. Combined with the analytic hierarchy process of qualitative and quantitative analysis, the quantitative risk index data are weighted to set up the whole risk evaluation index system of automobile insurance customers. Finally, the statistical model method and artificial intelligence method of vehicle insurance customer risk assessment are introduced. 2. BP neural network method and particle swarm optimization algorithm are analyzed and studied. The principle of BP neural network method and particle swarm optimization (PSO) is introduced in detail. The realization ideas, advantages and disadvantages of BP neural network algorithm and particle swarm optimization algorithm are summarized, and the historical development process of PSO algorithm is analyzed. An improved PSO algorithm is proposed to overcome the problem of local search and premature convergence of PSO algorithm, and the validity of the improved PSO algorithm is verified by the standard function test. Based on the improved PSO-BP neural network, the risk rating model of vehicle insurance customer is constructed. Aiming at the deficiency of BP neural network model parameter setting, this paper analyzes the optimization principle of BP neural network based on particle swarm optimization algorithm with global optimization function, and uses the improved PSO algorithm to determine the weight and threshold of BP neural network. Based on the improved PSO-BP neural network algorithm, the evaluation model of vehicle customer risk level is constructed. Based on the above research, the customer risk assessment data of a vehicle insurance industry are simulated, and the experimental results are compared with BP model and PSO-BP model. It is concluded that the convergent speed and accuracy of PSO-BP vehicle insurance customer risk rating model are greatly improved.
【學(xué)位授予單位】：寧夏大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：F842.634;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 談申申;孫思棟;阮凱欣;董又還;;“隨人”、“隨車”因素對(duì)車險(xiǎn)賠付支出影響的研究——基于微觀樣本調(diào)查對(duì)PAYD車險(xiǎn)定價(jià)模式的探討[J];財(cái)經(jīng)政法資訊;2015年02期

2 董志華;余洋;;車輛行駛里程對(duì)車險(xiǎn)賠付支出影響研究[J];統(tǒng)計(jì)與決策;2014年14期

3 趙志剛;黃樹運(yùn);王偉倩;;基于隨機(jī)慣性權(quán)重的簡(jiǎn)化粒子群優(yōu)化算法[J];計(jì)算機(jī)應(yīng)用研究;2014年02期

4 張連增;孫維偉;;車險(xiǎn)索賠概率影響因素的Logistic模型分析[J];保險(xiǎn)研究;2012年07期

5 趙志剛;張振文;張福剛;;自適應(yīng)擴(kuò)展的簡(jiǎn)化粒子群優(yōu)化算法[J];計(jì)算機(jī)工程與應(yīng)用;2011年18期

6 牛小梅;張銀玲;;層次分析法在電力客戶信用風(fēng)險(xiǎn)中的評(píng)價(jià)[J];計(jì)算機(jī)仿真;2011年05期

7 周敏;李太勇;;粒子群優(yōu)化算法中的慣性權(quán)值非線性調(diào)整策略[J];計(jì)算機(jī)工程;2011年05期

8 夏天;王新晴;梁升;黨瀟正;王建華;;帶自適應(yīng)遺傳算子的粒子群神經(jīng)網(wǎng)絡(luò)及其應(yīng)用[J];解放軍理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年01期

9 吳洪波;張蕾;;保險(xiǎn)業(yè)客戶態(tài)度忠誠(chéng)度模式分析[J];科技與管理;2010年02期

10 崔虹燕;水靜;;數(shù)據(jù)挖掘技術(shù)在汽車保險(xiǎn)風(fēng)險(xiǎn)分析中的應(yīng)用[J];科技信息;2009年29期

相關(guān)博士學(xué)位論文 前3條

1 涂娟娟;PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)算法的研究及其應(yīng)用[D];江蘇大學(xué);2013年

2 毛恒;粒子群優(yōu)化算法的改進(jìn)及應(yīng)用研究[D];華僑大學(xué);2008年

3 張貴清;信用風(fēng)險(xiǎn)評(píng)級(jí)與商業(yè)銀行信用風(fēng)險(xiǎn)管理[D];對(duì)外經(jīng)濟(jì)貿(mào)易大學(xué);2005年

相關(guān)碩士學(xué)位論文 前10條

1 葉惠珍;中小型產(chǎn)險(xiǎn)公司車險(xiǎn)索賠風(fēng)險(xiǎn)影響因素研究[D];浙江工商大學(xué);2016年

2 張路;車險(xiǎn)出險(xiǎn)客戶劃分及屬性關(guān)聯(lián)分析[D];中國(guó)科學(xué)院大學(xué)（工程管理與信息技術(shù)學(xué)院）;2014年

3 俞大凱;車險(xiǎn)客戶的風(fēng)險(xiǎn)特征及風(fēng)險(xiǎn)控制[D];寧波大學(xué);2012年

4 左杰;中國(guó)人民保險(xiǎn)公司車險(xiǎn)客戶風(fēng)險(xiǎn)評(píng)估建模研究及應(yīng)用[D];中南大學(xué);2011年

5 隨聰慧;粒子群算法的改進(jìn)方法研究[D];西南交通大學(xué);2010年

6 賈雪鳳;機(jī)動(dòng)車輛保險(xiǎn)賠付概率評(píng)估研究[D];山東大學(xué);2010年

7 陳琰;基于數(shù)據(jù)挖掘的保險(xiǎn)公司客戶評(píng)估與管理研究[D];哈爾濱理工大學(xué);2008年

8 譚浩;車險(xiǎn)經(jīng)驗(yàn)估費(fèi)中的客戶風(fēng)險(xiǎn)分級(jí)模型與算法設(shè)計(jì)[D];西南財(cái)經(jīng)大學(xué);2007年

9 崔兵;用GA優(yōu)化BP網(wǎng)絡(luò)權(quán)值的方法及其在個(gè)人信用評(píng)估中的應(yīng)用[D];吉林大學(xué);2006年

10 王世春;BP網(wǎng)絡(luò)在多元回歸分析中的應(yīng)用[D];合肥工業(yè)大學(xué);2003年

，

本文編號(hào)：1855063