TWI759620B - Method and apparatus for determining user's financial default risk and computer-readable storage medium and computing device - Google Patents
Method and apparatus for determining user's financial default risk and computer-readable storage medium and computing device Download PDFInfo
- Publication number
- TWI759620B TWI759620B TW108128019A TW108128019A TWI759620B TW I759620 B TWI759620 B TW I759620B TW 108128019 A TW108128019 A TW 108128019A TW 108128019 A TW108128019 A TW 108128019A TW I759620 B TWI759620 B TW I759620B
- Authority
- TW
- Taiwan
- Prior art keywords
- user
- evaluated
- credit
- term
- model
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Computer Security & Cryptography (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
本說明書的實施例提供一種確定用戶金融違約風險的方法和裝置,根據該方法的一個實施方式,分別利用基於循環神經網路的不同模型處理用戶的短期操作序列、長期行為資料集序列,來對用戶進行風險評估,並至少將兩種不同的處理結果進行綜合處理,以得到用戶金融違約風險結果。這樣,一方面,利用更加深度的時序資料,另一方面,藉由多個模型的輸出結果進行綜合確定最終結果。該實施方式可以提高確定用戶金融違約風險的有效性。 The embodiments of this specification provide a method and device for determining a user's financial default risk. According to an embodiment of the method, different models based on a recurrent neural network are used to process the user's short-term operation sequence and long-term behavior data set sequence, respectively. The user conducts risk assessment and comprehensively processes at least two different processing results to obtain the user's financial default risk result. In this way, on the one hand, more in-depth time series data is used, and on the other hand, the final result is determined by synthesizing the output results of multiple models. This implementation can improve the effectiveness of determining the user's financial default risk.
Description
本說明書的一個或多個實施例涉及電腦技術領域,尤其涉及藉由電腦確定用戶金融違約風險的方法和裝置。 One or more embodiments of this specification relate to the field of computer technology, and in particular, to a method and apparatus for determining a user's risk of financial default by means of a computer.
隨著電腦和互聯網技術的發展,越來越多的業務透過計算平臺來實現,例如商品交易、錢款支付、金融借貸、保險理賠等等。然而,在許多業務的執行和處理中,有一些用戶操作行為對金融平臺或其他用戶而言有一定的金融風險,例如請求先享後付類服務,採用花唄、白條等透支服務,申請借貸等。這就需要對用戶的金融違約風險預先進行評估和判斷。 With the development of computer and Internet technology, more and more businesses are realized through computing platforms, such as commodity trading, money payment, financial lending, insurance claims and so on. However, in the execution and processing of many businesses, there are some user operations that pose certain financial risks to financial platforms or other users, such as requesting first-pay-after-pay services, using Huabei, Baitiao and other overdraft services, applying for loans Wait. This requires pre-assessment and judgment of the user's financial default risk.
常規技術中,為了防止和降低上述風險,往往透過用戶的身份、歷史交易行為等資訊對用戶的信用進行評估。然而,這些資訊通常是靜態資訊,無法體現用戶行為等資訊之間的關聯關係,並且對於新用戶,可能無法獲取相應資訊,從而無法確定信用風險。因此,需要更有效的方式,利用更多的網路資料以及更有效的評測方式,對用戶進行全面分析,提高對用戶金融違約風險評估的有效性。 In the conventional technology, in order to prevent and reduce the above risks, the user's credit is often evaluated through information such as the user's identity and historical transaction behavior. However, these information are usually static information, which cannot reflect the relationship between user behavior and other information, and for new users, it may not be possible to obtain the corresponding information, so that the credit risk cannot be determined. Therefore, a more effective method is needed, using more network data and more effective evaluation methods, to conduct a comprehensive analysis of users, and to improve the effectiveness of user financial default risk assessment.
本說明書的一個或多個實施例描述了一種確定用戶金融違約風險的方法和裝置,可以更有效地對用戶的信用風險進行分析和評估。 One or more embodiments of this specification describe a method and apparatus for determining a user's financial default risk, which can more effectively analyze and evaluate the user's credit risk.
根據第一方面,提供了一種確定用戶金融違約風險的方法,包括:獲取待評測用戶在第一時間段內的短期操作序列,以及第二時間段內的長期行為資料集序列,所述第二時間段大於所述第一時間段,所述短期操作序列包括按照時間順序排列之與所述待評測用戶的操作行為相關的多條操作資訊,所述長期行為資料集序列包括按照時間順序排列的多個行為資料集,各行為資料集分別對應預設的第三時間段,所述行為資料集包括與所述待評測用戶的交易行為相關的行為資訊;利用基於循環神經網路的第一模型來處理所述短期操作序列,以獲得第一輸出結果;利用基於循環神經網路的第二模型來處理所述長期行為資料集序列,以獲得第二輸出結果;至少對所述第一輸出結果和所述第二輸出結果進行預定處理,並根據處理結果來確定所述待評測用戶的金融違約風險。 According to a first aspect, a method for determining a user's financial default risk is provided, comprising: acquiring a short-term operation sequence of a user to be evaluated in a first time period, and a long-term behavior data set sequence in a second time period, the second The time period is greater than the first time period, the short-term operation sequence includes a plurality of pieces of operation information related to the operation behavior of the user to be evaluated, arranged in chronological order, and the long-term behavior data set sequence includes chronological order. a plurality of behavior data sets, each behavior data set corresponds to a preset third time period respectively, and the behavior data set includes behavior information related to the transaction behavior of the user to be evaluated; using the first model based on the recurrent neural network to process the short-term operation sequence to obtain a first output result; use a second model based on a recurrent neural network to process the long-term behavior data set sequence to obtain a second output result; at least for the first output result Predetermined processing is performed with the second output result, and the financial default risk of the user to be evaluated is determined according to the processing result.
在一些實施例中,所述操作資訊包括以下至少一項:瀏覽資訊、點擊資訊、登入的應用程式、登入的設備、地理位置資訊。 In some embodiments, the operation information includes at least one of the following: browsing information, click information, logged-in application, logged-in device, and geographic location information.
在一些實施例中,所述交易行為資訊包括以下至少一項:交易時間、交易對象、交易金額。 In some embodiments, the transaction behavior information includes at least one of the following: transaction time, transaction object, and transaction amount.
在一些實施例中,所述方法還包括:獲取所述待評測 用戶的屬性資訊;利用預測模型來處理所述屬性資訊,以得到第三輸出結果;以及所述至少對所述第一輸出結果和所述第二輸出結果進行預定處理,並根據處理結果來確定所述待評測用戶的金融違約風險包括:對所述第一輸出結果、所述第二輸出結果和所述第三輸出結果進行所述預定處理,並根據處理結果來確定所述待評測用戶的金融違約風險。 In some embodiments, the method further includes: obtaining the to-be-evaluated attribute information of the user; processing the attribute information using a prediction model to obtain a third output result; and performing predetermined processing on at least the first output result and the second output result, and determining according to the processing result The financial default risk of the user to be evaluated includes: performing the predetermined processing on the first output result, the second output result and the third output result, and determining the user to be evaluated according to the processing result. financial default risk.
在一些實施例中,所述預定處理包括以下至少一項:求平均值;取最大值;作為特徵輸入預設的邏輯回歸模型,以得到邏輯回歸結果。 In some embodiments, the predetermined processing includes at least one of the following: averaging; taking a maximum value; inputting a preset logistic regression model as a feature to obtain a logistic regression result.
在一些實施例中,所述第一模型/所述第二模型包括多層疊加的長短期記憶模型LSTM。 In some embodiments, the first model/the second model comprises a multi-layer stacked long short term memory model LSTM.
在一些實施例中,所述第一模型/所述第二模型的訓練樣本包括多個標注用戶,所述標注用戶至少具有預先標注的信用標籤。 In some embodiments, the training samples of the first model/the second model include a plurality of labeled users, and the labeled users have at least pre-labeled credit labels.
在一些實施例中,所述多個標注用戶包括第一標注用戶,所述第一標注用戶對應的第一信用標籤藉由以下方式確定:獲取所述第一標注用戶在預定時間段內的信用記錄;基於所述信用記錄來確定所述第一信用標籤。 In some embodiments, the plurality of tagging users include a first tagging user, and the first credit tag corresponding to the first tagging user is determined by obtaining the credit of the first tagging user within a predetermined period of time. record; determining the first credit tag based on the credit record.
在一些實施例中,所述基於所述信用記錄來確定所述第一信用標籤包括:從所述信用記錄中確定所述第一標注用戶的守信次數和失信次數;在所述失信次數和所述守信次數的比例超過預設比例閾值的情況下,確定所述第一信用標籤為失信用戶。 In some embodiments, the determining the first credit label based on the credit record comprises: determining from the credit record the number of times of trustworthiness and the number of times of untrustworthiness of the first marked user; In the case that the ratio of the times of keeping promises exceeds a preset ratio threshold, it is determined that the first credit tag is a dishonest user.
在一些實施例中,所述基於所述信用記錄來確定所述第一信用標籤包括:檢測所述第一標注用戶的失信次數是否為零;在所述失信次數非零的情況下,確定所述第一信用標籤為失信用戶。 In some embodiments, the determining the first credit label based on the credit record includes: detecting whether the number of untrustworthy users of the first marking user is zero; in the case that the number of untrustworthy times is non-zero, determining the The first credit label is described as a dishonest user.
根據第二方面,提供一種確定用戶金融違約風險的裝置,包括:獲取單元,其被配置為獲取待評測用戶在第一時間段內的短期操作序列,以及第二時間段內的長期行為資料集序列,所述第二時間段大於所述第一時間段,所述短期操作序列包括按照時間順序排列之與所述待評測用戶的操作行為相關的多條操作資訊,所述長期行為資料集序列包括按照時間順序排列的多個行為資料集,各行為資料集分別對應預設的第三時間段,所述行為資料集包括與所述待評測用戶的交易行為相關的行為資訊;第一處理單元,其被配置為利用基於循環神經網路的第一模型來處理所述短期操作序列,以獲得第一輸出結果;第二處理單元,其被配置為利用基於循環神經網路的第二模型來處理所述長期行為資料集序列,以獲得第二輸出結果;確定單元,其被配置為至少對所述第一輸出結果和所述第二輸出結果進行預定處理,並根據處理結果來確定所述待評測用戶的金融違約風險。 According to a second aspect, an apparatus for determining a user's financial default risk is provided, comprising: an acquisition unit configured to acquire a short-term operation sequence of a user to be evaluated in a first time period, and a long-term behavior data set in a second time period sequence, the second time period is longer than the first time period, the short-term operation sequence includes a plurality of pieces of operation information related to the operation behavior of the user to be evaluated arranged in time sequence, and the long-term behavior data set sequence It includes a plurality of behavior data sets arranged in chronological order, each behavior data set corresponds to a preset third time period, and the behavior data set includes behavior information related to the transaction behavior of the user to be evaluated; the first processing unit , which is configured to process the short-term sequence of operations using a first model based on a recurrent neural network to obtain a first output result; a second processing unit is configured to use a second model based on a recurrent neural network to process the short-term operation sequence; processing the long-term behavior data set sequence to obtain a second output result; a determining unit configured to perform predetermined processing on at least the first output result and the second output result, and determine the The financial default risk of the user to be evaluated.
根據第三方面,提供了一種電腦可讀儲存媒體,其上儲存有電腦程式,當所述電腦程式在電腦中執行時,令電腦執行第一方面的方法。 According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed in a computer, the computer is caused to execute the method of the first aspect.
根據第四方面,提供了一種計算設備,包括記憶體和處理器,其特徵在於,所述記憶體中儲存有可執行的程式碼,所述處理器執行所述可執行的程式碼時,實現第一方面的方法。 透過本說明書的實施例提供的確定用戶的金融違約風險的方法和裝置,分別利用基於循環神經網路的不同模型來處理用戶的短期操作序列、長期行為資料集序列,對用戶進行風險評估,並至少將兩種不同的處理結果進行綜合處理,以得到用戶金融違約風險結果。這樣,一方面,利用更加深度的時序資料,另一方面,透過多個模型的輸出結果進行綜合來確定最終結果。因而,可以提高確定用戶金融違約風險的有效性。According to a fourth aspect, a computing device is provided, including a memory and a processor, wherein the memory stores executable program codes, and when the processor executes the executable program codes, it realizes method of the first aspect. Through the method and device for determining a user's financial default risk provided by the embodiments of this specification, different models based on the recurrent neural network are used to process the user's short-term operation sequence and long-term behavior data set sequence, and perform risk assessment on the user. At least two different processing results are comprehensively processed to obtain the user's financial default risk result. In this way, on the one hand, more in-depth time series data is used, and on the other hand, the final result is determined by synthesizing the output results of multiple models. Thus, the effectiveness of determining the user's financial default risk can be improved.
下面結合附圖,對本說明書提供的方案進行描述。
圖1為本說明書揭露的一個實施例的實施場景示意圖。如圖1所示,用戶可以透過終端機(terminal)進行各種操作,例如瀏覽網頁,點擊頁面上的超連結等,還有可能透過網路,與後臺伺服器進行各種交流互動,例如進行多種與借貸相關的行為,如申請借款、還款、申請延期還款等。相應地,終端機可以透過日誌等來記錄用戶的操作資訊,後臺伺服器也可以記錄用戶進行的與後臺伺服器提供的服務相關的行為。例如,用戶透過支付寶下的“螞蟻花唄”申請了一筆借款,然後每月還款,這時網路平臺即為支付寶平臺,後臺伺服器就可以是支付寶平臺伺服器。可以理解的是,後臺伺服器可以是集中的伺服器,也可以分散式伺服器,還可以是互相完全獨立的多個伺服器,在此不做限定。
為了對用戶的信用風險進行評估,計算平臺可以從各個借貸平臺或終端機獲取相應的用戶資料,由計算平臺進行綜合分析,確定出用戶的金融違約風險。在說明書揭露的實施例中,計算平臺獲取相關用戶資料之後,可以利用機器學習和循環神經網路,採用多個神經網路模型相結合的構架,對這些資料進行全面分析,進而對金融風險進行評估。上述計算平臺可以是任何具有計算、處理能力的裝置、設備和系統,例如可以是伺服器,它既可以作為獨立的計算平臺,也可以集成到為某些服務(如借貸)提供支援的後臺伺服器中。
更具體地,計算平臺一方面可以獲取用戶短期(如24個小時)內的各種操作形成的操作序列,透過基於循環神經網路的第一模型來進行處理,以挖掘用戶短期操作行為對用戶信用的影響,得到第一輸出結果。另一方面,計算平臺還可以獲取用戶在若干個週期(例如1天)內的行為資料集,每個行為資料集可以包括用戶在相應週期內的行為統計結果,計算平臺可以利用基於循環神經網路的第二模型對這些行為資料集按照時間順序排列成的長期行為資料集序列進行處理,得到第二輸出結果。進一步地,計算平臺還可以至少對第一輸出結果和第二輸出結果進行綜合處理,從而進行最終的金融風險評估。下面描述計算平臺評估金融違約風險的具體過程。
圖2示出根據一個實施例的確定用戶金融違約風險的方法流程圖。該方法的執行主體可以是任何具有計算、處理能力的系統、設備、裝置、平臺或伺服器,例如圖1所示的計算平臺等。更具體地,例如可以是為借貸服務提供支援的借貸伺服器等。
如圖2示,該方法包括以下步驟:步驟21,獲取待評測用戶在第一時間段內的短期操作序列,以及第二時間段內的長期行為資料集序列,其中,第二時間段大於第一時間段,短期操作序列包括按照時間順序排列之與待評測用戶的操作行為相關的多條操作資訊,長期行為資料集序列包括按照時間順序排列的多個行為資料集,各行為資料集分別對應預設的第三時間段,每個行為資料集包括與待評測用戶的交易行為相關的行為資訊;步驟22,利用基於循環神經網路的第一模型來處理短期操作序列,以獲得第一輸出結果;步驟23,利用基於循環神經網路的第二模型來處理長期行為資料集序列,以獲得第二輸出結果;步驟24,至少對第一輸出結果和第二輸出結果進行預定處理,並根據處理結果來確定待評測用戶的金融違約風險。
首先,在步驟21,獲取待評測用戶在第一時間段內的短期操作序列,以及第二時間段內的長期行為資料集序列。這裡,第一時間段可以是相對較短的一個時間段,例如1天(24小時)、12個小時等。第二時間段可以是相對較長的一個時間段,例如1個月、3個月、1年等等。第二時間段可以遠大於第一時間段。如此,為了描述方便,可以將第一時間段對應短期,第二時間段對應長期。
短期操作序列可以包括按照時間順序排列之與待評測用戶的操作行為相關的多條操作資訊。操作資訊可以包括但不限於瀏覽資訊、點擊資訊、登入的應用程式、登入的設備、地理位置資訊、交易資訊等等中的一項或多項。瀏覽資訊例如可以包括瀏覽的頁面、頁面網址、網站功能變數名稱等。點擊資訊例如可以包括點擊的超連結、所點擊超連結對應的頁面、提交表單所點擊的按鈕等等。登入的設備例如可以是桌上型電腦、筆記型電腦、平板電腦、智慧手機等等。地理位置資訊可以根據登入的設備的定位資訊確定。例如,設備的定位資訊可以根據智慧手機上的SIM卡當前距離最近的通信基站、電腦接入網路的IP位址、設備上的軟/硬體定位裝置(如GPS定位系統)等等來確定。在一個實施中,上述操作資訊可以從用戶當前登入的設備的操作日誌中獲取。在另一個實施中,上述操作資訊還可以透過相同用戶ID登入的不同設備,在用戶ID登入期間的操作日誌獲取。在有一些實施中,上述操作資訊還可以透過根據大數據確定的相似用戶(或同一用戶)在不同平臺的用戶ID,在登入相應平臺期間的操作日誌獲取。在此不做限定。
短期操作序列可以將第一時間段內的各條操作資訊按照發生的時間順序排列。請參考表1,假設從操作日誌中獲取了如下操作資訊:
表1 操作日誌示意
在LSTM模型中,藉由設置讓資訊選擇性透過的“遺忘門”來丟棄某些不再需要的資訊,如此對輸入的不必要的干擾資訊進行判斷和遮罩,進而更好地對資料序列進行分析處理。 In the LSTM model, some information that is no longer needed is discarded by setting a "forgetting gate" that allows information to selectively pass through, so as to judge and mask the input unnecessary interference information, so as to better understand the data sequence. Perform analytical processing.
請參考圖3,對於LSTM中的某個神經元A,用Xt-1、Xt、Xt+1分別表示t-1時刻、t時刻和t+1時刻的輸入,St-1、St、St+1分別表示t-1時刻、t時刻和t+1時刻該神經元的狀態,而Ct-1、Ct、Ct+1分別表示t-1時刻、t時刻和t+1時刻的輸出,其中:St=g(U*Xt+W*Ct-1+bs);Ct=f(V*St-1+bc);St+1=g(U*Xt+W*Ct+bs);Ct+1=f(V*St+bc);其中,U、W、V為權重。
Please refer to Figure 3, for a neuron A in LSTM, X t-1 , X t , X t+1 represent the input at time t-1, time t and time t+1 respectively, S t-1 , S t and S t+1 represent the state of the neuron at time t-1, time t and
可以看出的是,在LSTM模型中,每個神經元A的當前狀態由當前時刻的輸入和前一時刻的輸出共同決定,每個神經元A的當前輸出和前一時刻的狀態相關。透過LSTM模型對資料序列進行分析,可以有選擇地記憶資訊,挖掘出長距離的資料依賴。 It can be seen that in the LSTM model, the current state of each neuron A is jointly determined by the input at the current moment and the output at the previous moment, and the current output of each neuron A is related to the state at the previous moment. By analyzing the data sequence through the LSTM model, information can be selectively memorized and long-distance data dependencies can be mined.
在一個實施例中,還可以採用多層疊加的LSTM模型來處理多條資料按照時序構成的序列。 In one embodiment, a multi-layer superimposed LSTM model may also be used to process a sequence composed of multiple pieces of data according to time series.
在圖2示出的實施例中,藉由步驟22和步驟23分別對上述短期操作序列和長期行為資料集序列進行處理。可以
理解的是,步驟22和步驟23可以並存執行,也可以調換循序執行,本說明書實施例對此不做限定。
In the embodiment shown in FIG. 2 , the above-mentioned short-term operation sequence and long-term behavior data set sequence are processed through
具體地,在步驟22中,利用第一循環神經網路來處理上述短期操作序列,獲得第一輸出結果。對於短期操作序列的各條資料,依次輸入LSTM模型。對每條資料而言,各個元素分別對應輸入層的各個神經元,每個神經元的當前輸出影響下一條資料登入該神經元後的輸出。
Specifically, in
圖4示出根據一個實施例的利用循環神經網路的處理短期操作序列的示意圖。如圖4所示,用序號1、2、3、4、5、6、7……表示短期操作序列的各條資料,例如序號1對應第1條操作資訊:瀏覽購物頁面a,序號2對應第2條操作資訊:付款30元,等等。在圖4的示例中,循環神經網路包括多層疊加的LSTM模型。作為示意,圖4僅示出了多層疊加的LSTM模型在t-1、t、t+1時刻的時序。在圖4中,t-1時刻,多層疊加的LSTM模型接受序號為3的一條操作資訊。該條操作資訊經過LSTM模型的處理,每層的輸出被記錄。在t時刻,LSTM模型接受序號為4的一條操作資訊。LSTM模型處理該條操作資訊時,同時考慮各層中t-1時刻的輸出記錄。以此類推,直至上述短期操作序列被完全處理。
Figure 4 shows a schematic diagram of processing a short-term sequence of operations using a recurrent neural network, according to one embodiment. As shown in Figure 4,
經過多層循環神經網路的處理,可以獲得第一輸出結果。該第一輸出結果是與短期操作序列中的各條操作資訊及其產生順序相關的一個中間結果。在一個實施例中,該第一輸出結果可以是一個用戶信用/風險分數。
此時,用於處理上述短期操作序列的循環神經網路可以以多個標注用戶作為樣本進行訓練。這多個標注用戶分別對應有歷史短期操作序列和預先標注的信用標籤。
其中,標注用戶的歷史短期操作序列和上述短期操作序列可以具有一致的時間切入點。這裡的時間切入點,可以理解為藉由本實施例的確定用戶的金融違約風險的時機。例如,對於某個借貸平臺(如“花唄”),上述短期操作序列是用戶在該平臺開通服務前24小時內的操作資訊按照時序排列得到的序列,則標注用戶可以是在該平臺已經開通服務的用戶,標注用戶的歷史短期操作序列是相應用戶在該平臺開通服務前24小時內的操作資訊按照時序排列得到的序列。該例子中的時間切入點是用戶在該平臺開通服務。
而標注用戶對應的信用標籤,可以是根據用戶在該平臺或其他平臺的信用情況標注的。可以獲取相應用戶在預定時間段內的信用記錄,並基於信用記錄確定相應的信用標籤。這裡的預定時間段例如可以是在相應平臺開通服務後的3個月、6個月、1年等。
可以理解的是,對用戶的標注資訊可以包括諸如“失信用戶”、“守信用戶”之類的標籤,該標籤也可以透過數值(如1、0)進行表示。用戶的標注資訊可以透人工確定,也可以透過電腦進行。
在一個實施例中,可以從用戶的信用記錄中確定該用戶的守信次數和失信次數,並在失信次數和守信次數的比例超過預設比例閾值(如1:1)的情況下,確定相應用戶的信用標籤為“失信用戶”。否則,確定相應用戶的信用標籤為“守信用戶”。
在另一個實施例中,可以檢測用戶的失信次數是否為零,在失信次數非零的情況下,確定相應用戶的信用標籤為“失信用戶”。否則,確定相應用戶的信用標籤為“守信用戶”。
值得說明的是,在本說明書實施例中,雖然可以透過電腦確定作為樣本的用戶的標注資訊,但卻不能直接利用該標注方法對用戶金融違約風險進行評測。這是因為,確定用戶標注資訊的方法簡單、粗略,往往對應兩個結果中的一個,來表示用戶的金融違約風險偏向,而本說明書實施例旨在提供一種確定用戶金融違約風險的方案,這種方案,具有普適性,可以較準確地進行風險評估,對於沒有信用記錄的新用戶、信用記錄較少的老用戶等,都可以給出較準確的風險度估計,而這是上述確定用戶標注資訊的方法不能實現的。
為了區分,將以上訓練的循環神經網路稱為第一循環神經網路。透過該步驟,可以挖掘出待評估用戶的短期操作資訊對用戶風險的影響。除了利用第一循環神經網路來處理待評測用戶的短期操作序列之外,另一方面,還透過步驟23,利用第二循環神經網路來處理長期行為資料集序列,獲得第二輸出結果。對於長期行為資料集序列中的各個行為資料集,可以依次輸入LSTM模型。對一個行為資料集而言,各個元素分別對應輸入層的各個神經元,每個神經元的當前輸出影響下一條資料登入該神經元後的輸出。
圖5示出根據一個實施例的利用第二循環神經網路來處理長期行為資料集序列的示意圖。如圖5所示,用序號按照日期3號、4號……表示各個短週期內的行為資料集,例如3號對應3號這天的行為資料集,4號對應4號這天的行為資料集,等等。作為示意,圖5僅示出了多層疊加的LSTM模型在t-1、t、t+1時刻的時序。在圖5中,t-1時刻,多層疊加的LSTM模型接受3號這天的行為資料集。該行為資料集經過LSTM模型的處理,每層的輸出被記錄。在t時刻,LSTM模型接受4號這天的行為資料集。LSTM模型處理該行為資料集時,同時考慮各層中t-1時刻的輸出記錄。以此類推,直至上述長期行為資料集序列被完全處理。
經過第二循環神經網路的處理,可以獲得第二輸出結果。該第二輸出結果是與長期行為資料集序列的各個行為資料集的時序相關的一個中間結果。在一個實施例中,該第二輸出結果可以是另一個用戶信用/風險分數。
可以理解的是,處理上述長期行為資料集序列的循環神經網路也可以用多個標注用戶來作為樣本進行訓練。這多個標注用戶分別對應有歷史長期行為資料集序列和預先標注的信用標籤。其中,標注用戶的歷史長期行為資料集序列和待評估用戶的長期行為資料集序列,也具有一致的時間切入點。例如,對於某個借貸平臺(如“花唄”),上述長期行為資料集序列是用戶在該平臺開通服務前1個月內的行為資訊,按照時序排列得到的序列,則標注用戶可以是在該平臺已經開通服務的用戶,標注用戶的歷史長期行為資料集序列是相應用戶在該平臺開通服務前1個月內的行為資訊按照時序排列得到的序列。這裡的時間切入點是用戶在該平臺開通服務。標注用戶對應的信用標籤的標注方法和步驟22中的標注方法一致,在此不再贅述。
藉由該步驟,可以挖掘出待評估用戶的長期行為資訊對用戶風險的影響。
進一步地,在步驟22、步驟23的基礎上,藉由步驟24,至少基於對第一輸出結果和第二輸出結果的預定處理,以根據處理結果確定待評測用戶的金融違約風險。可以理解的是,預定處理是預先儲存的處理方法。如圖6所示。金融違約風險可以透過分數、小數、類別、偏向等來表示,在此不做限定。
在一個實施例中,該處理方法可以是簡單規則,例如求和、求平均值、求最大值,等等。以求平均值為例,可以將第一輸出結果和第二輸出結果的平均值作為待評測用戶的金融違約風險的量值。可選地,還可以先判斷進行處理的結果(如第一輸出結果和第二輸出結果)是否包括異常值(如超出預定範圍,或者為空等),如果包括異常值,則排除異常值,取另一個值。如此,在待評測用戶的短期操作序列或者長期行為序列中的一個無法獲取等情況下,仍然可以得到待評測用戶的金融違約風險。
在一個實施例中,該處理方法還可以包括將上述輸出結果作為特徵輸入邏輯回歸模型(如LR模型),藉由該邏輯回歸模型在對第一輸出結果、第二輸出結果進行線性回歸的基礎上,進行一個邏輯運算,使得模型的輸出值落入預設區間(如0-1之間)。該邏輯回歸模型可以是預先訓練的模型,也可以是預先設定的模型,在此不做限定。其中,預先設定的模型可以是認為確定計算方法和參數的模型。
可以理解的是,短期操作資訊和長期行為資訊都是用戶獨特的縱向特徵,透過這種獨特的縱向特徵,對用戶金融違約風險的評價更加精准。同時,由於透過多個模型分別處理多種時序資料,對多個評估結果進行綜合,可避免單面評估,或一種資料無效對評估結果的影響。
根據一個可能的設計,上述方法還可以包括:獲取待評測用戶的屬性資訊,利用預先訓練的預測模型來處理該屬性資訊,得到第三輸出結果。這裡,屬性資訊可以是用於表示用戶屬性的資訊,例如性別、年齡、職業、收入、財產狀況等等。預測模型的訓練樣本可以包括多個標注用戶。這些標注用戶分別對應有屬性資訊資料集,以及信用標籤,在此不再贅述。其中,信用標籤的確定方法同前,在此不再贅述。該預測模型可以是透過梯度提升決策樹(GBDT)、全連接神經網路等等訓練的模型。以該預測模型是透過全連接神經網路訓練的模型為例,請參考圖7。利用全連接神經網路來處理該屬性資訊的過程如圖7所示,將一個待評測用戶的屬性資訊輸入全連接神經網路,全連接神經網路的每個隱含層的輸出與前一層的各個神經元的輸出有關。
此時,在步驟24,還可以對第一輸出結果、第二輸出結果和第三輸出結果一起進行上述預定處理,以根據處理結果確定待評測用戶的金融違約風險。由於用戶的屬性資訊具有比較泛化的特徵,可以對橫向評估用戶的信用度,評價角度更廣。
回顧以上過程,在對用戶進行金融違約風險評估時,針對用戶的縱向資料,分別利用不同的循環神經網路來處理用戶的短期操作序列,以及長期行為資料集序列,對用戶進行風險評估,並至少將兩種不同的處理結果進行綜合處理。這樣,一方面,利用更加深度的資料,另一方面,即使一個結果異常,也能透過另一個結果確定最終結果。因而,可以提高確定用戶金融違約風險的有效性。此外,還可以透過用戶的屬性資訊作為橫向資訊,對用戶的風險度進行評估,利用更多資料,進行全面分析,提高評估結果的準確度。
根據另一方面的實施例,還提供一種確定用戶的金融違約風險的裝置。圖8示出根據一個實施例的確定用戶的金融違約風險的裝置的示意性方塊圖。如圖8所示,針對確定用戶的金融違約風險的裝置800包括:獲取單元81,其被配置為獲取待評測用戶在第一時間段內的短期操作序列,以及第二時間段內的長期行為資料集序列,第二時間段大於所述第一時間段,短期操作序列包括按照時間順序排列之與待評測用戶的操作行為相關的多條操作資訊,長期行為資料集序列包括按照時間順序排列的多個行為資料集,各行為資料集分別對應預設的第三時間段,行為資料集包括與待評測用戶的交易行為相關的行為資訊;第一處理單元82,其被配置為利用基於循環神經網路的第一模型來處理短期操作序列,以獲得第一輸出結果;第二處理單元83,其被配置為利用基於循環神經網路的第二模型來處理長期行為資料集序列,以獲得第二輸出結果;確定單元84,其被配置為至少對第一輸出結果和第二輸出結果進行預定處理,並根據處理結果確定待評測用戶的金融違約風險。
在一個實施例中,上述操作資訊包括以下至少一項:瀏覽資訊、點擊資訊、登入的應用程式、登入的設備、地理位置資訊。
在一個實施例中,上述行為資訊包括以下至少一項:交易時間、交易對象、交易金額。
根據一個可能的設計,裝置800還可以包括第三處理單元(未示出),其被配置為:
獲取待評測用戶的屬性資訊;
利用預測模型來處理上述屬性資訊,以得到第三輸出結果。
此時,確定單元84進一步還可以被配置為:
對第一輸出結果、第二輸出結果和第三輸出結果進行上述預定處理,並根據處理結果來確定待評測用戶的金融違約風險。
在一個實施例中,上述預定處理可以包括以下至少一項:
求平均值;
取最大值;
作為特徵輸入預設的邏輯回歸模型,以得到邏輯回歸結果。
根據一種實施方式,第一模型/第二模型包括多層疊加的長短期記憶模型LSTM。
在一個實施例中,第一模型/第二模型的訓練樣本包括多個標注用戶,標注用戶至少具有預先標注的信用標籤。該信用標籤可以透過人工確定,也可以透過裝置800確定。
該信用標籤透過裝置800確定時,裝置800還可以包括標注單元(未示出)。為了描述方便,將多個標注用戶中的任一個標注用戶稱為第一標注用戶,標注單元可以透過以下方式確定第一標注用戶對應的第一信用標籤:
獲取第一標注用戶在預定時間段內的信用記錄;
基於信用記錄確定第一信用標籤。
在一個進一步的實施例中,標注單元可以從上述信用記錄中確定第一標注用戶的守信次數和失信次數;在失信次數和守信次數的比例超過預設比例閾值的情況下,確定第一信用標籤為失信用戶。The first output result can be obtained through the processing of the multi-layer recurrent neural network. The first output result is an intermediate result related to each piece of operation information in the short-term operation sequence and its generation order. In one embodiment, the first output may be a user credit/risk score.
At this time, the recurrent neural network for processing the above-mentioned short-term operation sequence can be trained with multiple labeled users as samples. These multiple labeled users correspond to historical short-term operation sequences and pre-labeled credit labels, respectively.
Wherein, the historical short-term operation sequence of the marked user and the above-mentioned short-term operation sequence may have a consistent time entry point. The time entry point here can be understood as the timing for determining the user's financial default risk in this embodiment. For example, for a lending platform (such as "Huabei"), the above short-term operation sequence is the sequence obtained by the user's operation information within 24 hours before the platform's service is activated. For users of the service, the historical short-term operation sequence of the marked user is the sequence obtained by the corresponding user's operation information within 24 hours before the service is activated on the platform. The time entry point in this example is that the user activates the service on the platform.
The credit label corresponding to the marked user may be marked according to the user's credit status on the platform or other platforms. The credit records of the corresponding users within a predetermined period of time may be acquired, and the corresponding credit tags may be determined based on the credit records. The predetermined time period here may be, for example, 3 months, 6 months, 1 year, etc. after the corresponding platform starts the service.
It can be understood that the labeling information for users may include labels such as "untrustworthy users" and "trustworthy users", and the labels may also be represented by numerical values (eg, 1, 0). The user's annotation information can be determined manually or through a computer.
In one embodiment, the number of times of trustworthiness and the number of times of untrustworthiness of the user may be determined from the user's credit record, and when the ratio of the number of times of untrustworthiness to the number of times of trustworthiness exceeds a preset ratio threshold (eg 1:1), determine the corresponding user 's credit label is "Untrustworthy User". Otherwise, determine the credit label of the corresponding user as "trustworthy user".
In another embodiment, it may be detected whether the number of times of untrustworthiness of the user is zero, and if the number of untrustworthy times of the user is non-zero, it is determined that the credit label of the corresponding user is "untrustworthy user". Otherwise, determine the credit label of the corresponding user as "trustworthy user".
It is worth noting that, in the embodiment of this specification, although the labeling information of the user as the sample can be determined through a computer, the user's financial default risk cannot be evaluated directly by using this labeling method. This is because the method for determining the user's annotation information is simple and rough, and often corresponds to one of two results to represent the user's financial default risk bias, and the embodiments of this specification aim to provide a solution for determining the user's financial default risk. This scheme is universal and can conduct risk assessment more accurately. For new users without credit records, old users with less credit records, etc., more accurate risk estimates can be given. Information methods cannot be achieved.
For distinction, the recurrent neural network trained above is referred to as the first recurrent neural network. Through this step, the impact of the short-term operation information of the user to be evaluated on the user's risk can be mined. In addition to using the first recurrent neural network to process the short-term operation sequence of the user to be evaluated, on the other hand, through
在另一個進一步的實施例中,標注單元可以檢測第一標注用戶的失信次數是否為零;在失信次數非零的情況下,確定第一信用標籤為失信用戶。 In another further embodiment, the labeling unit may detect whether the untrustworthy count of the first labeling user is zero; if the untrustworthy count is non-zero, determine that the first credit label is the untrustworthy user.
值得說明的是,圖8所示的裝置800是與圖2示出的方法實施例相對應的裝置實施例,圖2示出的方法實施例中的相應描述同樣適用於裝置800,在此不再贅述。
It should be noted that the
藉由以上裝置,充分利用用戶短期和長期操作的時序資料,藉由多個模型的輸出結果進行綜合確定最終結果。因而,可以提高確定用戶金融違約風險的有效性。 With the above device, the time series data of the user's short-term and long-term operations are fully utilized, and the final result is determined by synthesizing the output results of multiple models. Thus, the effectiveness of determining the user's financial default risk can be improved.
根據另一方面的實施例,還提供一種電腦可讀儲存媒體,其上儲存有電腦程式,當所述電腦程式在電腦中執行時,令電腦執行結合圖2所描述的方法。 According to another embodiment, there is also provided a computer-readable storage medium on which a computer program is stored, when the computer program is executed in a computer, the computer is caused to perform the method described in conjunction with FIG. 2 .
根據再一方面的實施例,還提供一種計算設備,包括記憶體和處理器,所述記憶體中儲存有可執行的程式碼,所述處理器執行所述可執行的程式碼時,實現結合圖2所述的方法。 According to yet another embodiment, a computing device is also provided, including a memory and a processor, wherein executable program codes are stored in the memory, and when the processor executes the executable program codes, a combination of The method described in Figure 2.
本領域技術人員應該可以意識到的是,在上述一個或多個示例中,本發明所描述的功能可以用硬體、軟體、固件或它們的任意組合來實施。當使用軟體實施時,可以將這些功能儲存在電腦可讀媒體中或者作為電腦可讀媒體上的一個或多個指令或程式碼進行傳輸。 It should be appreciated by those skilled in the art that, in one or more of the above examples, the functions described herein may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
以上所述的具體實施方式,對本發明的目的、技術方案和有益效果進行了進一步詳細說明,所應理解的是,以 上所述僅為本發明的具體實施方式而已,並不用於限定本發明的保護範圍,凡在本發明的技術方案的基礎之上,所做的任何修改、等效替換、改進等,均應包括在本發明的保護範圍之內。 The specific embodiments described above further describe the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the The above are only specific embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the present invention shall be Included in the protection scope of the present invention.
21:步驟 21: Steps
22:步驟 22: Steps
23:步驟 23: Steps
24:步驟 24: Steps
800:確定用戶的金融違約風險的裝置 800: Means for determining a user's risk of financial default
81:獲取單元 81: Get Unit
82:第一處理單元 82: The first processing unit
83:第二處理單元 83: Second processing unit
84:確定單元 84: Determine unit
A:神經元 A: Neurons
C:輸出 C: output
U:權重 U: weight
W:權重 W: weight
X:輸入層狀態 X: Input layer state
t:時刻 t: time
1-7:資料 1-7: Information
為了更清楚地說明本發明的實施例的技術方案,下面將對實施例描述中所需要使用的附圖作簡單地介紹,顯而易見地,下面描述中的附圖僅僅是本發明的一些實施例,對於本領域普通技術人員來講,在不付出創造性勞動的前提下,還可以根據這些附圖獲得其它的附圖。 圖1示出本說明書揭露的一個實施例的實施場景示意圖; 圖2示出根據一個實施例的確定用戶的金融違約風險的方法流程圖; 圖3示出循環神經網路的一個神經元的時序狀態示意圖; 圖4示出利用基於循環神經網路的第一模型來處理短期操作序列的示意圖; 圖5示出利用基於循環神經網路的第二模型來處理長期行為資料集序列的示意圖; 圖6示出對第一輸出結果和第二輸出結果進行預定處理的示意圖; 圖7示出利用基於全連接神經網路的預測模型來處理屬性資訊的示意圖; 圖8示出根據一個實施例的確定用戶的金融違約風險的裝置的示意性方塊圖。In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort. FIG. 1 shows a schematic diagram of an implementation scenario of an embodiment disclosed in this specification; Figure 2 illustrates a flow chart of a method of determining a user's risk of financial default according to one embodiment; Fig. 3 shows a schematic diagram of a time sequence state of a neuron of a recurrent neural network; 4 shows a schematic diagram of processing a short-term sequence of operations with a first model based on a recurrent neural network; 5 shows a schematic diagram of processing a sequence of long-term behavioral datasets with a second model based on a recurrent neural network; 6 shows a schematic diagram of performing predetermined processing on the first output result and the second output result; 7 shows a schematic diagram of processing attribute information using a prediction model based on a fully connected neural network; Figure 8 shows a schematic block diagram of an apparatus for determining a user's risk of financial default according to one embodiment.
Claims (20)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811278478.5 | 2018-10-30 | ||
CN201811278478.5A CN109615454A (en) | 2018-10-30 | 2018-10-30 | Determine the method and device of user's finance default risk |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202016860A TW202016860A (en) | 2020-05-01 |
TWI759620B true TWI759620B (en) | 2022-04-01 |
Family
ID=66002128
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW108128019A TWI759620B (en) | 2018-10-30 | 2019-08-07 | Method and apparatus for determining user's financial default risk and computer-readable storage medium and computing device |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN109615454A (en) |
TW (1) | TWI759620B (en) |
WO (1) | WO2020088007A1 (en) |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615454A (en) * | 2018-10-30 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Determine the method and device of user's finance default risk |
CN110147940A (en) * | 2019-04-26 | 2019-08-20 | 阿里巴巴集团控股有限公司 | A kind of risk control processing method, equipment, medium and device |
CN112115258B (en) * | 2019-06-20 | 2023-09-26 | 腾讯科技(深圳)有限公司 | Credit evaluation method and device for user, server and storage medium |
CN110415102A (en) * | 2019-06-28 | 2019-11-05 | 上海上湖信息技术有限公司 | User credit methods of risk assessment and device, computer readable storage medium |
CN110580268A (en) * | 2019-08-05 | 2019-12-17 | 西北大学 | Credit scoring integrated classification system and method based on deep learning |
CN110515983A (en) * | 2019-08-06 | 2019-11-29 | 阿里巴巴集团控股有限公司 | A kind of user credibility assessment method, device and electronic equipment |
CN111242771A (en) * | 2020-01-13 | 2020-06-05 | 北京明略软件系统有限公司 | User operation behavior processing method and device and computer-readable storage medium |
CN111275350B (en) * | 2020-02-08 | 2021-06-04 | 支付宝(杭州)信息技术有限公司 | Method and device for updating event evaluation model |
CN111429006A (en) * | 2020-03-24 | 2020-07-17 | 北京明略软件系统有限公司 | Financial risk index prediction model construction method and device and risk situation prediction method and device |
US11379842B2 (en) * | 2020-04-07 | 2022-07-05 | Intuit Inc. | Method and system for detecting fraudulent transactions using a fraud detection model trained based on dynamic time segments |
CN111652430A (en) * | 2020-05-29 | 2020-09-11 | 蚌埠学院 | Internet financial platform default rate prediction method and system |
JP2023533069A (en) * | 2020-07-09 | 2023-08-01 | フィーチャースペース・リミテッド | Neural network architecture for transactional data processing |
CN111815425A (en) * | 2020-07-27 | 2020-10-23 | 上海观安信息技术股份有限公司 | User credit risk grade judgment method and system based on entity embedding |
CN112308294B (en) * | 2020-10-10 | 2024-06-14 | 北京贝壳时代网络科技有限公司 | Method and device for predicting default probability |
CN112184427A (en) * | 2020-10-16 | 2021-01-05 | 上海印闪网络科技有限公司 | Method for analyzing loan risk based on operation behavior of user on-line loan recommendation application |
CN112529695A (en) * | 2020-12-23 | 2021-03-19 | 招联消费金融有限公司 | Credit risk determination method, credit risk determination device, computer equipment and storage medium |
CN112818868B (en) * | 2021-02-03 | 2024-05-28 | 招联消费金融股份有限公司 | Method and device for identifying illegal user based on behavior sequence characteristic data |
CN112991077B (en) * | 2021-02-18 | 2024-03-19 | 深圳无域科技技术有限公司 | Financial risk control system and method |
CN113781201B (en) * | 2021-08-19 | 2023-02-03 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device for electronic financial activity |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529729A (en) * | 2016-11-18 | 2017-03-22 | 同济大学 | Method and system for forecasting default of credit card user based on BP_Adaboost model |
US9760850B1 (en) * | 2016-07-01 | 2017-09-12 | Intraspexion Inc. | Using classified text and deep learning algorithms to identify risk and provide early warning |
CN107301864A (en) * | 2017-08-16 | 2017-10-27 | 重庆邮电大学 | A kind of two-way LSTM acoustic models of depth based on Maxout neurons |
CN108416663A (en) * | 2018-01-18 | 2018-08-17 | 阿里巴巴集团控股有限公司 | The method and device of the financial default risk of assessment |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150301510A1 (en) * | 2014-04-22 | 2015-10-22 | Siegmund Düll | Controlling a Target System |
US10572877B2 (en) * | 2014-10-14 | 2020-02-25 | Jpmorgan Chase Bank, N.A. | Identifying potentially risky transactions |
CN107316198B (en) * | 2016-04-26 | 2020-05-29 | 阿里巴巴集团控股有限公司 | Account risk identification method and device |
CN108280757B (en) * | 2017-02-13 | 2021-08-17 | 腾讯科技(深圳)有限公司 | User credit evaluation method and device |
CN108629413B (en) * | 2017-03-15 | 2020-06-16 | 创新先进技术有限公司 | Neural network model training and transaction behavior risk identification method and device |
CN107886243A (en) * | 2017-11-10 | 2018-04-06 | 阿里巴巴集团控股有限公司 | Risk identification model construction and Risk Identification Method, device and equipment |
CN108510280B (en) * | 2018-03-23 | 2020-07-31 | 上海氪信信息技术有限公司 | Financial fraud behavior prediction method based on mobile equipment behavior data |
CN108596434B (en) * | 2018-03-23 | 2019-08-02 | 卫盈联信息技术(深圳)有限公司 | Fraud detection and methods of risk assessment, system, equipment and storage medium |
CN109615454A (en) * | 2018-10-30 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Determine the method and device of user's finance default risk |
-
2018
- 2018-10-30 CN CN201811278478.5A patent/CN109615454A/en active Pending
-
2019
- 2019-07-29 WO PCT/CN2019/098102 patent/WO2020088007A1/en active Application Filing
- 2019-08-07 TW TW108128019A patent/TWI759620B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9760850B1 (en) * | 2016-07-01 | 2017-09-12 | Intraspexion Inc. | Using classified text and deep learning algorithms to identify risk and provide early warning |
CN106529729A (en) * | 2016-11-18 | 2017-03-22 | 同济大学 | Method and system for forecasting default of credit card user based on BP_Adaboost model |
CN107301864A (en) * | 2017-08-16 | 2017-10-27 | 重庆邮电大学 | A kind of two-way LSTM acoustic models of depth based on Maxout neurons |
CN108416663A (en) * | 2018-01-18 | 2018-08-17 | 阿里巴巴集团控股有限公司 | The method and device of the financial default risk of assessment |
Also Published As
Publication number | Publication date |
---|---|
TW202016860A (en) | 2020-05-01 |
CN109615454A (en) | 2019-04-12 |
WO2020088007A1 (en) | 2020-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI759620B (en) | Method and apparatus for determining user's financial default risk and computer-readable storage medium and computing device | |
Boone et al. | Forecasting sales in the supply chain: Consumer analytics in the big data era | |
WO2020143409A1 (en) | Method and device for predicting business indicators | |
CN109741146A (en) | Products Show method, apparatus, equipment and storage medium based on user behavior | |
US20190019203A1 (en) | Method for providing marketing management data for optimization of distribution and logistics and apparatus for the same | |
CA3096061C (en) | Methods and systems for notifying users of new applications | |
CN113077317A (en) | Item recommendation method, device and equipment based on user data and storage medium | |
US20200410465A1 (en) | Payment-driven sourcing | |
US12051023B2 (en) | Benchmarking of user experience quality | |
Chen et al. | Common pitfalls in training and evaluating recommender systems | |
CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
US20210150604A1 (en) | Systems and methods for customization of reviews | |
US11587148B2 (en) | Item level data determination device, method, and non-transitory computer-readable media | |
CN112561565A (en) | User demand identification method based on behavior log | |
US20230289830A1 (en) | Product Availability Inference Using Merchant Data and Website Interaction | |
US11544053B2 (en) | Methods and systems for generating application build recommendations | |
US12081613B2 (en) | Systems and methods for decentralized detection of software platforms operating on website pages | |
CA3098792A1 (en) | Systems and methods for customization of reviews | |
CN107357847B (en) | Data processing method and device | |
US20230066770A1 (en) | Cross-channel actionable insights | |
US11710137B2 (en) | Method and system for identifying electronic devices of genuine customers of organizations | |
US10395312B2 (en) | System and method for proactively offering financing offers to customers of E-commerce websites | |
JP2021136033A (en) | Information processing device, information processing method and program | |
CN113902553A (en) | Risk identification method and device based on knowledge graph, computer equipment and medium | |
Choi et al. | Fast swaption pricing in gaussian term structure models |