《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計應(yīng)用 > 集成機器學(xué)習(xí)模型在不平衡樣本財務(wù)預(yù)警中的應(yīng)用
集成機器學(xué)習(xí)模型在不平衡樣本財務(wù)預(yù)警中的應(yīng)用
2021年電子技術(shù)應(yīng)用第8期
張 露1,劉家鵬1,,江敏祺2
1.中國計量大學(xué) 經(jīng)濟與管理學(xué)院,,浙江 杭州310018,;2.上海財經(jīng)大學(xué) 信息管理與工程學(xué)院,上海200000
摘要: 基于上交所主板市場A股企業(yè)的財務(wù)指標(biāo)數(shù)據(jù)來預(yù)測企業(yè)的財務(wù)風(fēng)險,,樣本數(shù)據(jù)包括1 227家正常上市企業(yè)和42家被財務(wù)預(yù)警的企業(yè),,數(shù)據(jù)嚴(yán)重不平衡,通過重采樣技術(shù)解決了分類器在不平衡樣本中失效的問題,,運用Bagging思想的集成機器學(xué)習(xí)對預(yù)測模型進行提升與優(yōu)化,。正確挑選出有財務(wù)危機企業(yè)的概率最高達到92.86%,在此基礎(chǔ)上,樣本的整體準(zhǔn)確率在經(jīng)過模型的集成之后提高了5.4%,。集成模型提高了對上市企業(yè)的財務(wù)預(yù)警能力,,能為企業(yè)的正常經(jīng)營和投資者的安全投資提供一定的借鑒。
中圖分類號: TN99,;TP391
文獻標(biāo)識碼: A
DOI:10.16157/j.issn.0258-7998.201234
中文引用格式: 張露,,劉家鵬,江敏祺. 集成機器學(xué)習(xí)模型在不平衡樣本財務(wù)預(yù)警中的應(yīng)用[J].電子技術(shù)應(yīng)用,,2021,,47(8):34-38.
英文引用格式: Zhang Lu,Liu Jiapeng,,Jiang Minqi. The application of the integrated machine learning model in the financial crisis of imbalanced sample[J]. Application of Electronic Technique,,2021,47(8):34-38.
The application of the integrated machine learning model in the financial crisis of imbalanced sample
Zhang Lu1,,Liu Jiapeng1,,Jiang Minqi2
1.School of Economics and Management,China Jiliang University,,Hangzhou 310018,,China; 2.School of Information Management and Engineering,,Shanghai University of Finance and Economics,,Shanghai 200000,China
Abstract: This paper forecast the financial risk of enterprises based on the financial index data of A-share enterprises in the main board market of Shanghai Stock Exchange.The samples included 1227 normal listed enterprises and 42 enterprises which have been financial warning. The data was seriously unbalanced. The problem of classifier failure in unbalanced samples was solved by resampling technology in some certain.The integrated machine learning based on Bagging was used to improve and optimize the prediction model.The highest probability of correctly selecting enterprises with financial warning was 92.86%. On this basis, the overall accuracy of the sample was improved by 5.4% after the integration of the model. The integrated model improved the financial early warning ability of listed enterprises which could provide some reference for the normal operation of enterprises and the safety investment of investors.
Key words : financial early warning prediction,;integrated machine learning,;imbalanced sampling technology

0 引言

    進入大數(shù)據(jù)時代以來,對信息的敏感程度和預(yù)測能力變得尤為重要,,而對企業(yè)而言,,無論是在經(jīng)營活動還是投資活動中,財務(wù)危機預(yù)警一直是個問題和難題,。機器學(xué)習(xí)的興起為大數(shù)據(jù)的處理和應(yīng)用提供了新的方式,。

    目前,,許多學(xué)者將機器學(xué)習(xí)與金融危機預(yù)警相結(jié)合,取得了重大突破,。OHLSON J A[1]建議將邏輯回歸應(yīng)用于分類的后概率,,來估計公司的破產(chǎn)概率。Zou Hui和HASTIE T[2]提出了彈性網(wǎng)絡(luò),,克服了嶺回歸和Lasso的缺點[3],。決策樹學(xué)習(xí)是一種強大的分類器[4],在樹分類器的基礎(chǔ)上,,有學(xué)者提出了隨機森林[5]和XGBoost[6],,在計算機[7]、圖像分類[8]等領(lǐng)域被證明有效,。

    但在過去的研究中,,大多采用人工設(shè)定樣本量,而忽視了實際上財務(wù)預(yù)警企業(yè)與正常企業(yè)的數(shù)量對比的懸殊[9],。數(shù)據(jù)不平衡的問題是財務(wù)預(yù)警研究領(lǐng)域的難題[10]。VEGANZONES D和SEVERIN E[11]提出采樣技術(shù)可用于提高不平衡樣本預(yù)測的分類器性能,,隨機上采樣技術(shù)[12],、隨機下采樣技術(shù)[13]和人工合成少數(shù)抽樣技術(shù)(SMOTE)[14]的應(yīng)用解決了集成復(fù)雜分類器在不平衡的財務(wù)預(yù)警研究數(shù)據(jù)中失效的問題。而集成學(xué)習(xí)機制可以通過集成不同的模型來整合多種算法的優(yōu)點[15],,目前在個人信貸領(lǐng)域已經(jīng)有了一定的應(yīng)用[16],。




本文詳細(xì)內(nèi)容請下載:http://forexkbc.com/resource/share/2000003695



作者信息:

張  露1,,劉家鵬1,,江敏祺2

(1.中國計量大學(xué) 經(jīng)濟與管理學(xué)院,浙江 杭州310018,;2.上海財經(jīng)大學(xué) 信息管理與工程學(xué)院,,上海200000)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載,。