CN113095567A - Loan yield prediction method, device, equipment and storage medium - Google Patents

Loan yield prediction method, device, equipment and storage medium Download PDF

Info

Publication number
CN113095567A
CN113095567A CN202110382546.8A CN202110382546A CN113095567A CN 113095567 A CN113095567 A CN 113095567A CN 202110382546 A CN202110382546 A CN 202110382546A CN 113095567 A CN113095567 A CN 113095567A
Authority
CN
China
Prior art keywords
loan
yield
time
prediction
time interval
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110382546.8A
Other languages
Chinese (zh)
Inventor
罗春江
尹亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Rural Commercial Bank Co ltd
Original Assignee
Chongqing Rural Commercial Bank Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing Rural Commercial Bank Co ltd filed Critical Chongqing Rural Commercial Bank Co ltd
Priority to CN202110382546.8A priority Critical patent/CN113095567A/en
Publication of CN113095567A publication Critical patent/CN113095567A/en
Pending legal-status Critical Current

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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/12—Timing analysis or timing optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Technology Law (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention discloses a loan yield prediction method, a loan yield prediction device, loan yield prediction equipment and a loan yield prediction storage medium, wherein the method comprises the following steps: obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time; establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction; and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs. Therefore, after learning the loan profitability of a plurality of continuous applying intervals in history through the ARIMA model, the ARIMA model is utilized to realize the prediction of the loan profitability of the time interval to which a certain time belongs, so that the prediction convenience and the prediction accuracy are greatly improved.

Description

Loan yield prediction method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of data processing, in particular to a loan yield prediction method, a loan yield prediction device, loan yield prediction equipment and a loan yield prediction storage medium.
Background
The yield of newly released credit in the financial industry is generally calculated by the following formula: the new loan yield is sum (amount of credit execution rate)/sum (amount of credit in the current month). The yield calculated by the formula can only obtain reference prediction data, and the yield of new loan issuance cannot be accurately predicted, so that data support is provided for decision making.
Disclosure of Invention
The invention aims to provide a loan yield prediction method, a loan yield prediction device, loan yield prediction equipment and a loan yield prediction storage medium, so that the prediction convenience and the prediction accuracy are greatly improved.
In order to achieve the above purpose, the invention provides the following technical scheme:
a loan yield prediction method, comprising:
obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time;
establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction;
and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs.
Preferably, before creating the ARIMA model by using the obtained loan yields of the plurality of time intervals, the method further includes:
and judging whether the obtained loan profitability of the plurality of time intervals is a stable time sequence, if so, executing the step of establishing an ARIMA model by using the obtained loan profitability of the plurality of time intervals, otherwise, performing d-order difference operation on the obtained loan profitability of the plurality of time intervals to convert the obtained loan profitability of the plurality of time intervals into the stable time sequence.
Preferably, after obtaining the corresponding prediction model for realizing the loan yield prediction, the method further includes:
D-W checking the prediction model, if the checking is passed, determining that the prediction model can be used for realizing loan yield prediction, and otherwise, returning to the step of establishing an ARIMA model by using the obtained loan yields of a plurality of time intervals.
Preferably, the method further comprises the following steps:
determining the growth proportion of the loan income rate of each time interval relative to the last time interval in the previous period of the period to which the preset time belongs; each cycle comprising a plurality of successive time intervals;
multiplying the loan yield of the time interval of the preset time and the increase proportion of the time interval at the same position in the previous period of the preset time to obtain the calculated loan yield of the time interval of the preset time;
and obtaining the final loan yield of the time interval to which the preset moment belongs by utilizing the calculated and predicted loan yield of the time interval to which the preset moment belongs.
Preferably, the obtaining of the final loan profitability of the time interval to which the preset time belongs by using the calculated and predicted loan profitability of the time interval to which the preset time belongs includes:
and performing weighted summation calculation by using the calculated and predicted loan profitability of the time interval to which the preset time belongs to obtain the final loan profitability of the time interval to which the preset time belongs.
Preferably, after obtaining the final loan yield of the time interval to which the preset time belongs, the method further includes:
and printing the final loan yield of the time interval to which the preset time belongs through a function print.
Preferably, after obtaining the final loan yield of the time interval to which the preset time belongs, the method further includes:
and drawing and outputting the time interval to which the preset time belongs and the final loan yield of a plurality of time intervals before the preset time.
A loan yield prediction apparatus comprising:
an acquisition module to: obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time;
a creation module to: establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction;
a prediction module to: and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs.
A loan yield prediction apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the loan yield prediction method as described in any one of the above when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the loan yield prediction method as claimed in any one of the preceding claims.
The invention provides a loan yield prediction method, a loan yield prediction device, loan yield prediction equipment and a loan yield prediction storage medium, wherein the method comprises the following steps: obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time; establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction; and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs. According to the method and the device, the ARIMA model is established by utilizing the historical loan profitability of a plurality of continuous time intervals, and then the created ARIMA model is imported by utilizing the loan profitability of a plurality of continuous time intervals before the preset time, so that the loan profitability of the time interval to which the preset time output by the ARIMA model belongs can be obtained. Therefore, after learning the loan profitability of a plurality of continuous applying intervals in history through the ARIMA model, the ARIMA model is utilized to realize the prediction of the loan profitability of the time interval to which a certain time belongs, so that the prediction convenience and the prediction accuracy are greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a loan yield prediction method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a loan yield prediction method according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of a loan yield prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart of a loan yield prediction method according to an embodiment of the present invention is shown, which may specifically include:
s11: and obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time.
The executive body of the loan yield prediction method provided by the embodiment of the invention can be a corresponding loan yield prediction device. The time interval can be set according to actual needs, such as one month, one week, and the like. In order to implement model training, the embodiment of the present application may collect data first, specifically, obtain the loan profit rate of each time interval of a plurality of consecutive time intervals in history, and if the time interval is one month, the collected data may be the historical monthly loan profit rate in the present year.
S12: and establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction.
After obtaining the loan yields for each of a plurality of consecutive time intervals in the history, the loan yields may be grouped into a time series, and the time series may be used for model training. In a specific implementation, the ARIMA model may be created by using AIC (Akaike information criterion) rule of ARIMA (Autoregressive Integrated Moving Average model) model. Specifically, creating an ARIMA model using the time series described above may include: respectively obtaining the self-correlation coefficient ACF and the partial self-correlation coefficient PACF of the time sequence; obtaining an optimal hierarchy p and an optimal order q through analyzing an autocorrelation graph corresponding to the ACF and a partial autocorrelation graph corresponding to the PACF; obtaining an ARIMA model from the q and the p obtained above, namely an ARIMA (p, d, q) model; where d is the difference number (default to 1).
S13: and importing the loan income rate of each time interval into a prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the loan income rate of the time interval to which the preset time belongs.
The preset time can be a time needing to realize loan yield prediction in the future, the loan yield of each time interval in a plurality of continuous time intervals which are before the preset time and are closest to the preset time can form a time sequence to be tested, and the time sequence to be tested is imported into the prediction model, so that the loan yield of the time interval to which the preset time output by the prediction model belongs can be obtained. Specifically, when the prediction model is used to realize the loan profitability of the time interval to which the preset time belongs, the loan profitability at the corresponding preset time can be obtained by a prediction function (prediction function) of the prediction model, that is, by introducing the time sequence to be tested into the prediction function. If the time interval is one month, and the loan profitability of 12 months in 2020 needs to be predicted, the loan profitability of 12 months in 2019 to 11 months in 2020 can be imported into the predict function, i.e. the loan profitability of 12 months in 2020 can be predicted.
According to the method and the device, the ARIMA model is established by utilizing the historical loan profitability of a plurality of continuous time intervals, and then the created ARIMA model is imported by utilizing the loan profitability of a plurality of continuous time intervals before the preset time, so that the loan profitability of the time interval to which the preset time output by the ARIMA model belongs can be obtained. Therefore, after learning the loan profitability of a plurality of continuous applying intervals in history through the ARIMA model, the ARIMA model is utilized to realize the prediction of the loan profitability of the time interval to which a certain time belongs, so that the prediction convenience and the prediction accuracy are greatly improved.
Before creating the ARIMA model by using the obtained loan profitability of a plurality of time intervals, the loan profitability prediction method provided by the embodiment of the invention may further include:
and judging whether the obtained loan profitability of the plurality of time intervals is a stable time sequence, if so, executing the step of establishing an ARIMA model by using the obtained loan profitability of the plurality of time intervals, otherwise, performing d-order difference operation on the obtained loan profitability of the plurality of time intervals to convert the obtained loan profitability of the plurality of time intervals into the stable time sequence.
According to the embodiment of the application, the obtained loan yield of each time interval in a plurality of historically continuous time intervals can be formed into the time sequence to be trained, whether the time sequence to be trained is a stable time sequence or not is observed through drawing software, if not, d-order difference operation is firstly carried out on the time sequence to be trained, the time sequence to be trained is converted into the stable time sequence, namely, a non-stable time sequence can be converted into the stable time sequence after d-time difference, otherwise, the time sequence to be trained can be directly used for creating the ARIMA model, so that the stability of the time sequence to be trained is ensured, and the prediction accuracy of the ARIMA model created by using the time sequence to be trained is further ensured. In addition, the time sequence after the time sequence to be trained is differentiated for 1 time is subjected to stationarity test, if the time sequence is non-stationary, the differentiation is continued until the time sequence after d times is tested to be stationary (generally, the differentiation is performed for one or two times).
After obtaining the corresponding prediction model for realizing the loan yield prediction, the loan yield prediction method provided by the embodiment of the invention may further include:
D-W checking the prediction model, if the checking is passed, determining that the prediction model can be used for realizing loan yield prediction, and otherwise, returning to the step of creating the ARIMA model by using the obtained loan yields of a plurality of time intervals.
After the prediction model is obtained, D-W inspection can be carried out on the prediction model to observe whether the prediction model conforms to normal distribution or not, if the prediction model conforms to normal distribution, the inspection is passed, otherwise, the ARIMA model needs to be created again, and therefore the prediction accuracy of the prediction model is further guaranteed.
The loan yield prediction method provided by the embodiment of the invention can also comprise the following steps:
determining the growth proportion of each time interval relative to the loan yield of the last time interval in the previous period of the period to which the preset time belongs; each cycle comprising a plurality of successive time intervals;
multiplying the loan yield of the time interval of the preset time period by the increase proportion of the time interval at the same position in the previous period of the preset time period to obtain the calculated loan yield of the time interval of the preset time period;
and obtaining the final loan yield of the time interval to which the preset moment belongs by utilizing the calculated and predicted loan yield of the time interval to which the preset moment belongs.
The embodiment of the application can also realize the initial assessment of the loan yield of the time interval to which the preset time belongs, in particular, each period can be divided into a plurality of time intervals, and the position of the time interval in the period is the number-th time interval of the period, the embodiment of the application can determine the increase ratio of the loan income rate of each time interval in the last period of the period to which the preset time belongs relative to the previous time interval, then multiplying the increase proportion specified by the loan yield of the previous time interval of the time interval to which the preset moment belongs, the loan yield of the time interval to which the preset time belongs can be obtained, and finally the loan yield of the time interval to which the preset time belongs is comprehensively obtained by using the loan yield predicted by the prediction model and the loan yield calculated in the initial assessment, so that the accuracy of loan yield prediction is further improved. The specified increase proportion is the increase proportion of the time interval in the last period of the period to which the preset time belongs, wherein the time interval is at the same position as the time interval to which the preset time belongs. The above procedure for the initial assessment is exemplified when the time interval is one month: the monthly loan yield in the previous year is the predicted loan yield of the next month, for example, the 1-month loan yield in 2019 is 2 million, the 2-month loan yield in 2019 is 3 million, the growth rate of the 2-month loan in the previous year is 50% in 2020, for example, the 1-month loan yield in 2020 is 3 million, and the predicted 2-month loan yield in 2020 is: 3 million (1+ 50%) -4.5 million.
The loan income rate prediction method provided by the embodiment of the invention obtains the final loan income rate of the time interval to which the preset time belongs by using the calculated and predicted loan income rates of the time interval to which the preset time belongs, and can include:
and performing weighted summation calculation by using the calculated and predicted loan profitability of the time interval to which the preset moment belongs to obtain the final loan profitability of the time interval to which the preset moment belongs.
If the loan profitability obtained by using the prediction model is the same as the loan profitability obtained by using the growth proportion, the loan profitability is directly used as the final loan profitability of the time interval to which the preset time belongs, otherwise, the average value of the loan profitability and the loan profitability is used as the final loan profitability of the time interval to which the preset time belongs, and the weighted sum of the loan profitability and the final loan profitability is calculated to be used as the final loan profitability of the time interval to which the preset time belongs, so that the accuracy of the predicted loan profitability is further guaranteed.
The loan yield prediction method provided by the embodiment of the invention, after obtaining the final loan yield of the time interval to which the preset time belongs, may further include:
and printing the final loan yield of the time interval to which the preset time belongs through the function print.
After the final loan yield of the time interval to which the predicted preset time belongs is obtained, the final loan yield of the time interval to which the preset time belongs can be printed and output as a function of the print, so that external personnel can obtain the data information conveniently.
The loan yield prediction method provided by the embodiment of the invention, after obtaining the final loan yield of the time interval to which the preset time belongs, may further include:
and drawing and outputting the time interval to which the preset time belongs and the final loan yield of a plurality of time intervals before the preset time.
The loan yields of a plurality of time intervals before the preset time and the loan yields of the time intervals to which the preset time belongs can be plotted and output, and an example graph obtained by plotting can be shown as fig. 2; therefore, external personnel can visually grasp and analyze the loan yield change condition based on the loan yield change condition.
It should be noted that, the loan yield may be embodied by a payment amount (or referred to as a loan amount), and in a specific implementation, a loan yield prediction method provided by an embodiment of the present invention may include:
1. collecting data: such as monthly payment values in the history of the year; the loan yield statistics may be in units of a month, i.e., the time interval may be one month.
2. Initial evaluation: calculating the monthly increase proportion of the year, namely the money put in the month is the predicted income amount of the next month; such as: in 2019, the sum of the 1-month payment is 2 million, in 2019, the sum of the 2-month payment is 3 million, and compared with 2020, the proportion of the 2-month increase in the last year is 50%; then, for example, in 2020, the payment amount is 3 million in 1 month, and the predicted payment amount in 2 months is: 3 million (1+ 50%) -4.5 million.
3. Predictive analysis with time series model: the ARIMA model is typically created using the AIC rules of the ARIMA model.
(1) The yield rates of the 2019 in 1-12 months are respectively:
[4.6,5.3,5.2,5.1,5.0,5.0,5.1,5.2,4.9,4.8,4.7,4.3]；
(2) whether the time sequence is a stable time sequence can be observed through drawing software; d-order difference operation is carried out on the non-stationary time sequence to be a stationary time sequence;
(3) respectively obtaining the self-correlation coefficient ACF and the partial self-correlation coefficient PACF of the stationary time sequence, and obtaining the optimal level p and the order q by analyzing the self-correlation diagram and the partial self-correlation diagram;
4) obtaining an ARIMA model, namely an ARIMA (p, d, q) model from the d, q and p obtained in the above way; where d is the number of differences (default to 1).
4. And (3) testing the model: and D-W testing is carried out, and whether the normal distribution is met or not is observed.
By making a D-W check model and observing whether the positive distribution is met, if the fitting model is not checked, turning to step 3: and (4) identifying an ARIMA model, reselecting the model and fitting.
5. Model prediction: predict, import the historical credit into predict with the function ARIMA.
The ARIMA (p,1, q) model with the p and the q determined is predicted, and only a prediction function is needed, and the historical payment amount value is imported into the function. Such as: the payment amount of 12 months in 2020 is predicted, and the payment amount of 12 months from 12 months in 2019 to 11 months in 2020 is introduced into the predict function, so that the payment amount of 12 months in 2020 can be predicted.
6. And (4) predicting results: and outputting the payment amount through the prediction result and printing.
Therefore, the loan yield can be accurately predicted, the efficiency of decision makers is improved through visual representation of graphs, and data support is provided for decision making.
An embodiment of the present invention further provides a loan yield prediction apparatus, as shown in fig. 3, the loan yield prediction apparatus may specifically include:
an obtaining module 11, configured to: obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time;
a creation module 12 for: establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction;
a prediction module 13 for: and importing the loan income rate of each time interval into a prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the loan income rate of the time interval to which the preset time belongs.
The embodiment of the invention also provides loan yield prediction equipment, which comprises:
a memory for storing a computer program;
a processor for implementing the steps of the loan yield prediction method as described in any one of the above when executing the computer program.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any loan yield prediction method as described above.
It should be noted that for the description of the relevant parts in the loan yield prediction apparatus, the device and the storage medium provided in the embodiment of the present invention, reference is made to the detailed description of the corresponding parts in the loan yield prediction method provided in the embodiment of the present invention, and no further description is given here. In addition, parts of the technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A loan yield prediction method, comprising:
obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time;
establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction;
and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs.
2. The method of claim 1, wherein prior to creating the ARIMA model using the obtained loan yields for the plurality of time intervals, further comprising:
and judging whether the obtained loan profitability of the plurality of time intervals is a stable time sequence, if so, executing the step of establishing an ARIMA model by using the obtained loan profitability of the plurality of time intervals, otherwise, performing d-order difference operation on the obtained loan profitability of the plurality of time intervals to convert the obtained loan profitability of the plurality of time intervals into the stable time sequence.
3. The method of claim 2, wherein obtaining the corresponding prediction model for achieving the loan yield prediction further comprises:
D-W checking the prediction model, if the checking is passed, determining that the prediction model can be used for realizing loan yield prediction, and otherwise, returning to the step of establishing an ARIMA model by using the obtained loan yields of a plurality of time intervals.
4. The method of claim 3, further comprising:
determining the growth proportion of the loan income rate of each time interval relative to the last time interval in the previous period of the period to which the preset time belongs; each cycle comprising a plurality of successive time intervals;
multiplying the loan yield of the time interval of the preset time and the increase proportion of the time interval at the same position in the previous period of the preset time to obtain the calculated loan yield of the time interval of the preset time;
and obtaining the final loan yield of the time interval to which the preset moment belongs by utilizing the calculated and predicted loan yield of the time interval to which the preset moment belongs.
5. The method according to claim 4, wherein obtaining the final loan profitability of the time interval to which the preset time belongs by using the calculated and predicted loan profitability of the time interval to which the preset time belongs comprises:
and performing weighted summation calculation by using the calculated and predicted loan profitability of the time interval to which the preset time belongs to obtain the final loan profitability of the time interval to which the preset time belongs.
6. The method according to claim 5, wherein after obtaining the final loan yield of the time interval to which the preset time belongs, the method further comprises:
and printing the final loan yield of the time interval to which the preset time belongs through a function print.
7. The method according to claim 6, wherein after obtaining the final loan yield of the time interval to which the preset time belongs, the method further comprises:
and drawing and outputting the time interval to which the preset time belongs and the final loan yield of a plurality of time intervals before the preset time.
8. A loan yield prediction apparatus, comprising:
an acquisition module to: obtaining the loan yield of each time interval in a plurality of continuous time intervals before the current time;
a creation module to: establishing an ARIMA model by using the obtained loan profitability of a plurality of time intervals to obtain a corresponding prediction model for realizing loan profitability prediction;
a prediction module to: and importing the loan yield of each time interval into the prediction model in a plurality of continuous time intervals which are before the preset time and are closest to the preset time, and determining the data output by the prediction model as the predicted loan yield of the time interval to which the preset time belongs.
9. A loan yield prediction apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the loan yield prediction method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having a computer program stored thereon, which, when executed by a processor, performs the steps of the loan yield prediction method as claimed in any one of claims 1 to 7.
CN202110382546.8A 2021-04-09 2021-04-09 Loan yield prediction method, device, equipment and storage medium Pending CN113095567A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110382546.8A CN113095567A (en) 2021-04-09 2021-04-09 Loan yield prediction method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110382546.8A CN113095567A (en) 2021-04-09 2021-04-09 Loan yield prediction method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113095567A true CN113095567A (en) 2021-07-09

Family

ID=76675808

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110382546.8A Pending CN113095567A (en) 2021-04-09 2021-04-09 Loan yield prediction method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113095567A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114154682A (en) * 2021-11-10 2022-03-08 中国建设银行股份有限公司 Customer loan yield grade prediction method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114154682A (en) * 2021-11-10 2022-03-08 中国建设银行股份有限公司 Customer loan yield grade prediction method and system

Similar Documents

Publication Publication Date Title
CN110400022B (en) Cash consumption prediction method and device for self-service teller machine
CN109193650B (en) Power grid weak point evaluation method based on high-dimensional random matrix theory
CN105279365A (en) Method for learning exemplars for anomaly detection
CN109615760A (en) Intelligently add the method and system of clear paper money to ATM in bank based on machine learning
CN112488496A (en) Financial index prediction method and device
CN111612149A (en) Main network line state detection method, system and medium based on decision tree
CN114202243A (en) Engineering project management risk early warning method and system based on random forest
CN113095567A (en) Loan yield prediction method, device, equipment and storage medium
Chu et al. On the evolution of the United Kingdom price distributions
Kumar et al. Cryptocurrency price forecasting in a volatile landscape: Sarimax modeling and short-term strategies
CN113835947A (en) Method and system for determining abnormality reason based on abnormality identification result
CN110930258A (en) Receivable financial financing cash scale prediction method and system
Chatterjee et al. Transfer function modelling in software reliability
CN112346995B (en) Banking industry-based test risk prediction model construction method and device
CN114139408A (en) Power transformer health state assessment method
CN111967774B (en) Software quality risk prediction method and device
CN113642641B (en) Data processing method and device applied to electric charge additional work order
Subhan et al. THE INFLUENCE OF ECONOMIC FACTORS ON THE STOCK PRICE OF KIMIA FARMA COMPANIES ON THE INDONESIAN STOCK EXCHANGE
Raffo et al. Estimating the financial benefit and risk associated with process changes
CN107527141A (en) The detection method and system of switch cubicle quality
KR20100081088A (en) Water quality trend extraction method and system
Kruba et al. Wind speed forecasting in Aceh using ARIMA and neural network model
Nielsen Migration Patterns of ESG Ratings
Kalantzopoulos et al. Modeling uncertainty and risk investment appraisal decisions: A Monte Carlo simulation approach
CN115147146A (en) Market risk situation determination method based on pressure simulation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210709

RJ01 Rejection of invention patent application after publication