CREDIT RISK PREDICTION METHOD AND DEVICE BASED ON LSTM MODEL

• US 20190325514A1
• Filed: 04/23/2019
• Published: 10/24/2019
• Est. Priority Date: 04/24/2018
• Status: Active Application

• Current Assignee: Advanced New Technologies Company Limited (Ant Group Co., Ltd.)
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: HONG, Manhuo
• Application Number:
  US16/392,166
• Publication Number:
  US 20190325514A1
• Time in Patent Office: Days
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof

Abstract

Methods, systems and apparatus for credit risk prediction based on an Long Short-Term Memory (LSTM) model are provided. One of the methods includes obtaining behavior data of a target account in a period that includes a plurality of time intervals, and generating, based on the behavior data of the target account, a sequence of behavior vectors. Each behavior vector corresponds to one of the time intervals. The method further includes inputting the generated sequence of behavior vectors into an LSTM encoder in the LSTM model to obtain hidden state vectors each corresponding to one of the time intervals, and obtaining a risk score of the target account in a next time interval by inputting the hidden state vectors into an LSTM decoder of the LSTM model. The next time interval is next to the last time interval in the plurality of time intervals.

Claims

1. A computer-implemented method for credit risk prediction based on an Long Short-Term Memory (LSTM) model, the method comprising:

obtaining behavior data of a target account in a period, wherein the period comprises a plurality of time intervals;

generating, based on the behavior data of the target account, a sequence of behavior vectors, each behavior vector corresponding to one of the time intervals;

inputting the generated sequence of behavior vectors into an LSTM encoder in an LSTM model to obtain hidden state vectors each corresponding to one of the time intervals, wherein the LSTM model comprises the LSTM encoder and an LSTM decoder; and

obtaining a risk score of the target account in a next time interval by inputting the hidden state vectors into the LSTM decoder, wherein the next time interval is next to the last time interval in the plurality of time intervals.

2. The method according to claim 1, further comprising:

obtaining a weight of each hidden state vector on the risk score from the LSTM decoder, wherein the weight of each hidden state vector indicates a contribution of the hidden state vector to the risk score.

3. The method according to claim 1, further comprising:

obtaining behavior data of a plurality of sample accounts in the period comprising the plurality of time intervals;

generating, based on the behavior data of the plurality of sample accounts, a sample sequence of behavior vectors, each behavior vector in the sample sequence corresponding to one of the time intervals; and

training the LSTM model by using the generated sample sequence of behavior vectors as training samples.

4. The method according to claim 3, wherein obtaining behavior data of a plurality of sample accounts comprises:

obtaining the behavior data based on a variety of user behaviors including one or more of credit performance behaviors, user consumption behaviors, and financial payment behaviors.

5. The method according to claim 3, wherein generating, based on the behavior data of the plurality of sample accounts, a sample sequence of behavior vectors comprises:

extracting one or more factors from the obtained behavior data of the sample accounts;

digitizing the one or more factors to obtain behavior vectors each corresponding to the behavior data in one of the time intervals; and

splicing the behavior vectors to obtain the sample sequence of the behavior vectors.

6. The method according to claim 5, wherein the factors comprise statuses of debit or credit orders and debit or credit repayment amounts corresponding to the credit performance behaviors, categories and quantities of user consumption corresponding to the user consumption behaviors, and financial payment types and financial income amounts corresponding to the financing payment behaviors.

7. The method according to claim 1, wherein the LSTM encoder has a multi-layer many-to-one structure, and the LSTM decoder has a multi-layer many-to-many structure including equal numbers of input nodes and output nodes.

8. The method according to claim 1, wherein inputting the generated sequence of behavior vectors into an LSTM encoder in an LSTM model to obtain hidden state vectors comprises:

inputting the generated sequence of behavior vectors into the LSTM encoder to obtain first hidden state vectors based on a forward propagation computation, each first hidden state vector corresponding to one of the time intervals;

inputting a reverse of the generated sequence of the behavior vectors into the LSTM encoder to obtain second hidden state vectors based on a back propagation computation, each second hidden state vector corresponding to one of the time intervals; and

for each time interval, splicing a first hidden state vector and a second hidden state vector both corresponding to the time interval to obtain the hidden state vector corresponding to the time interval.

9. The method according to claim 1, wherein inputting the hidden state vectors into the LSTM decoder to obtain a risk score of the target account in a next time interval comprises:

inputting the hidden state vectors into the LSTM decoder to obtain an output vector of the target account in the next time interval; and

digitizing the output vector to obtain the risk score of the target account in the next time interval.

10. The method according to claim 9, wherein the output vector is a multi-dimensional vector;

and

digitizing the output vector comprises any one of the following;

extracting a value of a sub-vector in the output vector as a risk score, wherein the value is between 0 and 1;

in response to that the output vector comprises a plurality of sub-vectors whose values are between 0 and 1, calculating an average of the values of the plurality of sub-vectors as the risk score; and

in response to that the output vector comprises a plurality of sub-vectors whose values are between 0 and 1, extracting the maximal value or the minimal value of the values of the plurality of sub-vectors as the risk score.

11. A system for credit risk prediction based on an Long Short-Term Memory (LSTM) model, comprising:

one or more processors; and

one or more computer-readable memories coupled to the one or more processors and having instructions stored thereon that are executable by the one or more processors to perform a method comprising;

obtaining behavior data of a target account in a period, wherein the period comprises a plurality of time intervals;

generating, based on the behavior data of the target account, a sequence of behavior vectors, each behavior vector corresponding to one of the time intervals;

inputting the generated sequence of behavior vectors into an LSTM encoder in an LSTM model to obtain hidden state vectors each corresponding to one of the time intervals, wherein the LSTM model comprises the LSTM encoder and an LSTM decoder; and

obtaining a risk score of the target account in a next time interval by inputting the hidden state vectors into the LSTM decoder, wherein the next time interval is next to the last time interval in the plurality of time intervals.

12. The system according to claim 11, wherein the method further comprises:

obtaining a weight of each hidden state vector on the risk score from the LSTM decoder, wherein the weight of each hidden state vector indicates a contribution of the hidden state vector to the risk score.

13. The system according to claim 11, wherein the method further comprises:

obtaining behavior data of a plurality of sample accounts in the period comprising the plurality of time intervals;

generating, based on the behavior data of the plurality of sample accounts, a sample sequence of behavior vectors, each behavior vector in the sample sequence corresponding to one of the time intervals; and

training the LSTM model by using the generated sample sequence of behavior vectors as training samples.

14. The system according to claim 13, wherein obtaining behavior data of a plurality of sample accounts comprises:

obtaining the behavior data based on a variety of user behaviors including one or more of credit performance behaviors, user consumption behaviors, and financial payment behaviors.

15. The system according to claim 13, wherein generating, based on the behavior data of the plurality of sample accounts, a sample sequence of behavior vectors comprises:

extracting one or more factors from the obtained behavior data of the sample accounts;

digitizing the one or more factors to obtain behavior vectors each corresponding to the behavior data in one of the time intervals; and

splicing the behavior vectors to obtain the sample sequence of the behavior vectors.

16. The system according to claim 15, wherein the factors comprise statuses of debit or credit orders and debit or credit repayment amounts corresponding to the credit performance behaviors, categories and quantities of user consumption corresponding to the user consumption behaviors, and financial payment types and financial income amounts corresponding to the financing payment behaviors.

17. The system according to claim 11, wherein inputting the generated sequence of behavior vectors into an LSTM encoder in an LSTM model to obtain hidden state vectors comprises:

inputting the generated sequence of behavior vectors into the LSTM encoder to obtain first hidden state vectors based on a forward propagation computation, each first hidden state vector corresponding to one of the time intervals;

inputting a reverse of the generated sequence of the behavior vectors into the LSTM encoder to obtain second hidden state vectors based on a back propagation computation, each second hidden state vector corresponding to one of the time intervals; and

for each time interval, splicing a first hidden state vector and a second hidden state vector both corresponding to the time interval to obtain the hidden state vector corresponding to the time interval.

18. The system according to claim 11, wherein inputting the hidden state vectors into the LSTM decoder to obtain a risk score of the target account in a next time interval comprises:

inputting the hidden state vectors into the LSTM decoder to obtain an output vector of the target account in the next time interval; and

digitizing the output vector to obtain the risk score of the target account in the next time interval.

19. The system according to claim 18, wherein the output vector is a multi-dimensional vector;

and

digitizing the output vector comprises any one of the following;

extracting a value of a sub-vector in the output vector as a risk score, wherein the value is between 0 and 1;

in response to that the output vector comprises a plurality of sub-vectors whose values are between 0 and 1, calculating an average of the values of the plurality of sub-vectors as the risk score; and

in response to that the output vector comprises a plurality of sub-vectors whose values are between 0 and 1, extracting the maximal value or the minimal value of the values of the plurality of sub-vectors as the risk score.

20. A non-transitory computer-readable storage medium configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

obtaining behavior data of a target account in a period, wherein the period comprises a plurality of time intervals;

generating, based on the behavior data of the target account, a sequence of behavior vectors, each behavior vector corresponding to one of the time intervals;

inputting the generated sequence of behavior vectors into an LSTM encoder in an LSTM model to obtain hidden state vectors each corresponding to one of the time intervals, wherein the LSTM model comprises the LSTM encoder and an LSTM decoder; and

obtaining a risk score of the target account in a next time interval by inputting the hidden state vectors into the LSTM decoder, wherein the next time interval is next to the last time interval in the plurality of time intervals.