CN115099933A - Service budget method, device and equipment - Google Patents
Service budget method, device and equipment Download PDFInfo
- Publication number
- CN115099933A CN115099933A CN202210728675.2A CN202210728675A CN115099933A CN 115099933 A CN115099933 A CN 115099933A CN 202210728675 A CN202210728675 A CN 202210728675A CN 115099933 A CN115099933 A CN 115099933A
- Authority
- CN
- China
- Prior art keywords
- service
- budgeted
- data
- value
- influence
- 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
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q40/12—Accounting
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Mathematical Analysis (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a service budgeting method, a device and equipment, wherein the method comprises the steps of determining the service types of services to be budgeted and acquiring historical service data of each service to be budgeted; determining an influence factor influencing the service development of each service to be budgeted, and acquiring corresponding historical factor data of each service to be budgeted based on the influence factor; predicting future cause data of each service to be budgeted in a first time period by a time sequence prediction method based on the influence causes and the historical cause data; taking historical kinetic factor data as independent variables, taking historical service data as dependent variables, and fitting by using a Lasso regression model to obtain a multiple linear regression equation; and substituting the future kinetic data into a multiple linear regression equation to obtain a precalculated value of the corresponding service to be budgeted. The method and the device have the advantages that the manual intervention in the service budget process is reduced, and the accuracy and fineness of the service budget are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a service budgeting method, a service budgeting device and service budgeting equipment.
Background
In the existing bank budget management method, budget index values of loan-saving business and fund business scales are manually determined based on business experience, business historical scale conditions and bank operation targets in the same year, and the budget index values only relate to a plurality of large classes and cannot penetrate into finer business varieties, so fine management cannot be achieved in budget management.
Disclosure of Invention
The embodiment of the invention provides a service budgeting method, a device and equipment, which solve the technical problem of low budget precision caused by more manual intervention and budget based on service large-class indexes during service budgeting in the prior art.
In a first aspect, an embodiment of the present invention provides a service budgeting method, where the service budgeting method includes:
determining the service types of services to be budgeted, and acquiring historical service data of each service to be budgeted;
determining an influence cause influencing the service development of each service to be budgeted, and acquiring historical cause data corresponding to each service to be budgeted based on the influence cause;
predicting future kinetic factor data of each service to be budgeted in a first time period by a time series prediction method based on the influence kinetic factors and the historical kinetic factor data;
taking the historical kinetic factor data as independent variables, taking the historical service data as dependent variables, and fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and substituting the future kinetic data into the multiple linear regression equation to obtain a precalculated value corresponding to the service to be budgeted.
In a second aspect, an embodiment of the present invention further provides a service budgeting apparatus, where the service budgeting apparatus includes:
the system comprises a type determining unit, a data processing unit and a data processing unit, wherein the type determining unit is used for determining the service type of the service to be budgeted and acquiring historical service data of each service to be budgeted;
the dynamic factor determining unit is used for determining an influence dynamic factor influencing the service development of each service to be budgeted and acquiring historical dynamic factor data corresponding to each service to be budgeted based on the influence dynamic factor;
the cause prediction unit is used for predicting future cause data of each service to be budgeted in a first time period through a time series prediction method based on the influence cause and the historical cause data;
an equation fitting unit, configured to use the historical motion factor data as an independent variable, use the historical service data as a dependent variable, and perform fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and the service budget unit is used for substituting the future kinetic factor data into the multiple linear regression equation to obtain a budget value corresponding to the service to be budgeted.
In a third aspect, an embodiment of the present invention further provides a service budget apparatus, where the service budget apparatus includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a business budgeting method as in any of the first aspect of embodiments of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the service budgeting method according to any one of the first aspect of the embodiments of the present invention.
In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the service budgeting method according to any one of the first aspect of the embodiment of the present invention.
The embodiment of the invention discloses a service budgeting method, a device and equipment, wherein the method comprises the steps of determining the service types of services to be budgeted and acquiring historical service data of each service to be budgeted; determining an influence factor influencing the service development of each service to be budgeted, and acquiring corresponding historical factor data of each service to be budgeted based on the influence factor; predicting future kinetic data of each service to be budgeted in a first time period by a time series prediction method based on the influence kinetic and historical kinetic data; taking historical kinetic factor data as independent variables, taking historical service data as dependent variables, and fitting by using a Lasso regression model to obtain a multiple linear regression equation; and substituting the future kinetic data into a multiple linear regression equation to obtain a precalculated value of the corresponding service to be budgeted. According to the method and the device, the service classes are subdivided into different service classes, the future cause data are obtained through prediction based on a time sequence prediction method according to the influence causes of each service class, and finally the future cause data are substituted into a multiple linear regression equation to obtain the budget value of the corresponding service to be budgeted, so that the technical problems of low budget precision caused by more manual intervention and budget based on service class indexes in service budgeting in the prior art are solved, and the technical effects of reducing the manual intervention in the service budgeting process and improving the accuracy and fineness of service budgeting are achieved.
Drawings
Fig. 1 is a flowchart of a service budgeting method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for budgeting services according to an embodiment of the present invention;
FIG. 3 is a flowchart of another method for budgeting services according to an embodiment of the present invention;
FIG. 4 is a block diagram of a service budgeting apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a service budget apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
It should be noted that the terms "first", "second", and the like in the description and claims of the present invention and the accompanying drawings are used for distinguishing different objects, and are not used for limiting a specific order. The following embodiments of the present invention may be implemented individually, or in combination with each other, and the embodiments of the present invention are not limited in this respect.
Fig. 1 is a flowchart of a service budgeting method according to an embodiment of the present invention. The service budgeting method can be applied to all service scenes needing budgeting, such as scenes of budgeting for loan-saving services and fund services by banks. The service budgeting method may be performed by a service budgeting apparatus, which may be implemented in hardware and/or software, and may be generally integrated in a server. According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
As shown in fig. 1, the service budgeting method specifically includes the following steps:
s101, determining the service types of the services to be budgeted, and acquiring historical service data of each service to be budgeted.
Specifically, taking the budget of banking services as an example, the actual service conditions of a bank mainly include loan-saving services and fund services, which are used as services to be budgeted, the large class of the services is divided into the minimum service classes required by budget management, and the historical specification value (i.e., the historical service data) of each service class is obtained. In general, the frequency of acquiring the historical service data may be set to monthly, that is, the historical service data of each service category of each month is acquired monthly, and the time length of acquiring the data is at least 3 years.
Illustratively, banking varieties can be divided into three major segments of companies, retail and credit cards, and financial markets according to actual business categories. The company plate is divided into deposit business and loan business, the deposit business comprises deposit to the public in the period, notice deposit to the public, etc., and the loan business comprises loan to the public in the short period, loan to the public in the middle and long period, loan to the public in the short period, etc.; the retail and credit card block is also divided into deposit type business and loan type business, wherein the deposit type business comprises a current deposit, a notice deposit, a deposit of a guarantee fund, a deposit of a credit card and the like; the loan service comprises individual house mortgage loan, individual business loan, individual consumption loan, credit card overdraft and the like; financial market plate business is divided into fund business and liability business of the fund market, and the fund business of the fund market comprises foreign currency payment, other storage synchronization active periods, storage synchronization regular periods and the like; the debt services in the gold city comprise deposit financial institution deposit in due date, non-deposit financial institution deposit in due date, and homopathy deposit slip.
S102, determining an influence factor influencing the service development of each service to be budgeted, and acquiring historical factor data corresponding to each service to be budgeted based on the influence factor.
Specifically, for each service type of the service to be budgeted, according to service experience and objective economic law, an influence factor capable of influencing the service development is determined, and historical factor data corresponding to each service to be budgeted is obtained. In general, the frequency of acquiring the historical cause data can be set to be monthly, that is, the historical cause data of each business category in each month under the influence cause is acquired monthly, and the time length of acquiring the data is at least 3 years.
It should be noted that after determining the influence factors of each service to be budgeted, since there are a plurality of influence factors of one service to be budgeted and the influence degrees of each influence factor on the service to be budgeted are different, for precision of budgeting, a preset number of influence factors with the strongest influence degrees need to be selected from the influence factors as subsequent budgeting.
Illustratively, taking the banking budget as an example, the influence factors can be divided into internal factors and external factors, wherein the internal factors include indexes capable of reflecting the development of the internal business, such as the number of retail deposit businesses, the base number of retail customers, and the average deposit balance of retail customers, and the external factors are mainly Domestic macro economy or industry indexes, and international macro economy indexes, including CPI (Consumer Price Index), GDP (Gross Domestic Product), M2 (generalized currency supply), national debt revenue rate, and the like. According to the types of factors which may be influenced by different types of services to be budgeted in the banking budget service, determining the relevant influence factors of the service types, and then acquiring historical factor data of the corresponding services to be budgeted according to the influence factors.
S103, predicting future kinetic data of each service to be budgeted in a first time period by a time series prediction method based on the influence kinetic and the historical kinetic data.
Specifically, after the influence cause of each service to be budgeted is determined, future cause data of each service to be budgeted in a first time period is obtained through prediction by a time series prediction method. For example, in the current ten-day of month 1, 12 values are predicted by a time series prediction method according to actual data of the influence factor at the end of 12 months since the last year (i.e., the historical factor data), and the values respectively correspond to predicted values of the influence factor from the end of 1 month to the end of 12 months of the current year (i.e., the future factor data, where the first time period is 12 months); for another example, in the last 7 th month, 6 values are predicted by a time series prediction method according to actual data of the cause at the end of 6 months of the year (i.e., the historical cause data), and the 6 values respectively correspond to predicted values of the cause from the end of 7 months to the end of 12 months of the year (i.e., the future cause data, where the first time period is 6 months).
And S104, fitting by using a Lasso regression model by using the historical kinetic factor data as independent variables and the historical service data as dependent variables to obtain a multiple linear regression equation.
Specifically, the Lasso regression model is called as Least absolute shrinkage and selection operator. The method is a compression estimation, which obtains a more refined model by constructing a penalty function, so that the method compresses some regression coefficients, namely, the sum of absolute values of the forcing coefficients is smaller than a certain fixed value; while some regression coefficients are set to zero. Thus preserving the advantage of subset puncturing, a process that handles biased estimation of data with complex collinearity.
Because the Lasso regression model adds the L1 norm on the basis of the linear regression loss function, and has an automatic selection function on the influence factors, in the influence factors with the highest influence degree selected in the step S102, the Lasso regression model can automatically eliminate the influence factors which have little influence on the prediction value of the service to be budgeted again, so that the effect of automatically selecting the influence factors according to the actual data condition is realized, and the manual intervention is reduced.
In the embodiment of the invention, historical kinetic data is used as independent variables, historical service data is used as dependent variables and is substituted into a Lasso regression model, and a multiple linear regression equation is obtained by performing multiple linear regression fitting by using the Lasso regression model.
And S105, substituting the future kinetic factor data into a multiple linear regression equation to obtain a budget value of the corresponding service to be budgeted.
Specifically, after obtaining the multiple linear regression equation, substituting the future kinetic data of each service to be budgeted into the equation, so as to obtain the budget value of the corresponding service to be budgeted.
According to the method and the device, the service classes are subdivided into different service classes, the future cause data are obtained through prediction based on a time sequence prediction method according to the influence causes of each service class, and finally the future cause data are substituted into a multiple linear regression equation to obtain the budget value of the corresponding service to be budgeted, so that the technical problems that in the prior art, when service budgeting is carried out, manual intervention is more, and budgeting is carried out based on the service class indexes, so that the budget precision is lower are solved, and the technical effects of reducing the manual intervention in the service budgeting process and improving the accuracy and fineness of the service budget are achieved.
Based on the foregoing technical solutions, fig. 2 is a flowchart of another service budgeting method provided in the embodiment of the present invention, and as shown in fig. 2, after determining an influence cause influencing service development of each service to be budgeted in S102, the service budgeting method further includes:
and S201, calculating a correlation coefficient between each influence cause and corresponding historical service data.
Specifically, because the determined influence factors of each service to be budgeted are more, and the influence degrees of different influence factors on the service to be budgeted are different, it is necessary to determine which influence factor has the greatest influence degree on the service to be budgeted among the plurality of influence factors. Based on this, first, correlation coefficients between each influence factor and corresponding historical service data need to be calculated, and the correlation between the influence factor and corresponding historical service data is determined, specifically, if there is more than one influence factor with high correlation in the calculated correlation coefficients between different influence factors and corresponding historical service data, the influence factors are further arranged in a descending order according to the correlation (that is, the following influence factor sequence), and a preset number of influence factors with the top-ranked correlation rank (for example, the influence factors with the top-six ranked correlation rank) are retained; secondly, the correlation between different influence factors is calculated, only one influence factor with larger influence on the budget service is reserved for the influence factor with high correlation between every two influence factors, and the problem of collinearity when the Lasso regression model is fitted is avoided.
S202, the influence factors are sequenced based on the correlation coefficients to obtain an influence factor sequence, wherein the influence factor sequence is used for representing the influence degree of the influence factors on the service to be budgeted.
Specifically, after obtaining the correlation coefficient between each influence cause and the corresponding historical service data, the obtained correlation coefficients are sorted according to the correlation degree thereof, so as to obtain an influence cause sequence.
Optionally, S202 specifically includes: and judging whether the absolute value of each correlation coefficient is larger than a preset standard value or not, and sequencing the influence factors according to the judgment result to obtain an influence factor sequence.
Specifically, after the correlation coefficient between each influence cause and the corresponding historical service data is calculated, it is determined whether the absolute value of each correlation coefficient is greater than a preset standard value, and in a normal case, the preset standard value may be set to 0.3, that is, it is determined whether the absolute value of the correlation coefficient is greater than the preset standard value of 0.3.
S203, reserving a preset number of influence factors in the influence factor sequence for standby.
Specifically, after the influence factor sequence is obtained, the influence factors of the preset number are selected as the factors having the greatest influence on the service to be budgeted, and the subsequent budgeting work is continued. For example, if the preset number can be set to 6, the first 6 influencing factors with the strongest correlation in the influencing factor sequence are reserved for standby. If the total number of the influence factors in the influence factor sequence does not satisfy 6, the number of the influence factors in the actual influence factor sequence is used as a standard.
On the basis of the foregoing technical solutions, fig. 3 is a flowchart of another service budgeting method provided in the embodiment of the present invention, and as shown in fig. 3, S103 specifically includes:
s301, determining the optimal parameters in the seasonal difference autoregressive moving average model according to a minimum information quantity criterion or a Bayes information criterion.
Specifically, a Seasonal Autoregressive Integrated Moving Average (SARIMA) model may be selected as a time series prediction method to predict future kinetic data, and since the SARIMA model has a plurality of parameter combinations, a parameter combination that can minimize a predicted statistic value needs to be calculated by using an information minimization criterion (AIC criterion) or a bayesian information criterion (BIC criterion), and is substituted into the SARIMA model as an optimal parameter for subsequent calculation.
The AIC criterion or the BIC criterion is used for measuring the complexity of the estimation model and the goodness of fitting data, and the predicted value obtained through the SARIMA model can be more accurate through the determined optimal parameters.
And S302, based on the influence cause and the historical cause data, predicting to obtain future cause data of each service to be budgeted in the first time period by using the optimal parameters and the seasonal difference autoregressive moving average model.
After the optimal parameters are obtained, based on the influence dynamic factors and historical dynamic factor data, the future dynamic factor data in the future first time period can be obtained in a prediction mode by using the SARIMA model using the optimal parameters.
On the basis of the above technical solutions, before substituting the future kinetic data into the multiple linear regression equation to obtain the budget value of the corresponding service to be budgeted in S105, the service budgeting method includes: verifying whether the error rate of a precalculated value calculated by the multiple linear regression equation is less than a preset error value or not; if yes, predicting a precalculated value of the corresponding service to be budgeted by using a multiple linear regression equation; if not, predicting the budget value of the service to be budgeted by using a preset statistical model.
Specifically, in the fitting process of the actual multiple linear regression equation, the regression model for obtaining each service to be budgeted is obtained by fitting on a training set, namely after historical motile data and historical service data are obtained, the historical motile data and the historical service data are divided into the training set and a verification set, the regression model obtained by training is verified by using the data of the verification set, whether the error rate between the predicted value obtained by the regression model and the actual service data of the service to be budgeted meets a preset error value or not is judged, and for the service to be budgeted with the error rate within the preset error value, the result obtained by selecting the Lasso regression model as the prediction method is more accurate, so that the Lasso regression model can be continuously used for predicting the budget value subsequently; if the error rate is greater than the preset error value, the error rate indicates that the error is larger in the result obtained by selecting the Lasso regression model as the prediction method, so that the preset statistical model can be selected to predict the budget value of the service to be budgeted.
Optionally, verifying whether the error rate of the budget value calculated by the multiple linear regression equation is smaller than the preset error value includes: taking data in a second time period in the historical service data as verification set data; substituting the future kinetic factor data into a multiple linear regression equation to obtain a verification predicted value of a second time period; calculating a relative root mean square error between the verification predicted value and an actual service value in a second time period, wherein the actual service value is verification set data; and judging whether the relative root mean square error is smaller than a preset error value.
Specifically, a length of 6 months is generally reserved (i.e., the second hour described above)Time period) as verification set data. After a regression model is obtained through fitting, future kinetic factor data obtained through prediction by a time series prediction method are substituted into a multiple linear regression equation obtained through fitting, 6 predicted values can be obtained through calculation, the 6 predicted values are verification predicted values of the 6 months, historical service data of the reserved six months are used as actual service values, the 6 verification predicted values are compared with actual scale values (namely the actual service values) of the service to be budgeted, the average prediction error rate of each month is obtained, and the calculation formula is as follows
(i.e., the Relative Root Mean square Error, RRMSE, where n is the total number of samples, P i Is the ith prediction value, T i The ith actual traffic value).
The preset error value is set to be 10%, namely, for the service to be budgeted with the error rate within 10%, the result obtained by selecting the Lasso regression model as the prediction method is more accurate, so that the Lasso regression model can be continuously used for predicting the budget value subsequently; if the error rate is larger than 10%, it indicates that the error is larger in the result obtained by selecting the Lasso regression model as the prediction method, so that the preset statistical model can be selected to predict the budget value of the service to be budgeted.
Optionally, the preset statistical model includes:
annual moving average model
Wherein, a t Is an annual average traffic prediction value, a t-n Is the average service value of t-n months, t is the current month, n is the number of months, n is a positive integer; wherein n is generally 12;
annual weighted average model
Wherein, b t Is an annual weighted average traffic prediction value, b t-n Is flat for t-n monthsMean traffic value, ω t-n Is a weight coefficient of t-n months, t is the current month, n is the number of months, n is a positive integer; wherein n is generally 12;
year-year model
Wherein, c t Is a year-year service prediction value, t is the current month, h is a year-year-year coefficient,
c t-1 to c t-12 Respectively representing average traffic values 1 to 24 months before the current month;
lunar year-on-year model d t ＝s t d t-12 Wherein d is t Is a predicted value of the t-month-degree unity-ratio business, d t-12 Is the service value of t months in the last year, s t Is a monthly unity ratio coefficient of the density of the sample,
monthly growth model e t Ft + g, wherein e t The predicted value is t month-degree growth, f is historical average service growth rate, and g is a constant.
Specifically, the monthly growth model is actually obtained by fitting historical service data of the service to be budgeted based on a linear regression equation, wherein f is a slope of the equation, and means that the slope represents a historical average service growth rate of the service to be budgeted, and g is an intercept of the equation, and as viewed from the linear regression equation, g is actually a constant, and means that the slope represents an initial service value of the service to be budgeted before the monthly growth value of the period of time is calculated.
Optionally, there are a plurality of preset statistical models, and predicting the budget value of the service to be budgeted by using the preset statistical models includes: respectively predicting future service values of the services to be budgeted by utilizing a plurality of preset statistical models; and taking the future service value with the minimum error rate in the plurality of predicted future service values as a budget value of the service to be budgeted.
Specifically, for the service to be budgeted with an error rate greater than 10%, the five preset statistical models may be used to calculate the future service value of the service to be budgeted, and then select the future service value with the smallest error rate as the budget value of the service to be budgeted.
Optionally, after obtaining the predicted value of part of the services to be budgeted based on the multiple linear regression equation prediction and obtaining the predicted value of part of the services to be budgeted based on the preset statistical model, summarizing the predicted values and the predicted values to obtain the predicted values of all the services to be budgeted, extracting the predicted values of part of the services to be budgeted according to actual needs, and adjusting the summarized predicted values according to indexes such as next year target income to obtain a final budget result.
Illustratively, taking the budget of banking services as an example, if a budget value for a financial market needs to be obtained, only the predicted values of the various service categories under the financial market plate need to be extracted, and the extracted predicted values are adjusted according to a budget target actually formulated by a bank to obtain a final budget result under the financial market plate.
Fig. 4 is a structural diagram of a service budgeting apparatus according to an embodiment of the present invention, and as shown in fig. 4, the service budgeting apparatus includes:
a category determining unit 41, configured to determine a service category of a service to be budgeted, and obtain historical service data of each service to be budgeted;
the cause determining unit 42 is configured to determine an influence cause influencing the service development of each service to be budgeted, and obtain historical cause data corresponding to each service to be budgeted based on the influence cause;
the cause prediction unit 43 is configured to predict, by using a time series prediction method, future cause data of each service to be budgeted in the first time period based on the influence cause and the historical cause data;
an equation fitting unit 44, configured to use the historical kinetic data as an independent variable, use the historical service data as a dependent variable, and perform fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and the service budget unit 45 is used for substituting the future kinetic data into the multiple linear regression equation to obtain a budget value of the corresponding service to be budgeted.
Optionally, after the cause determining unit 42 determines an influence cause influencing the service development of each service to be budgeted, the service budgeting apparatus further includes:
the first calculation unit is used for calculating a correlation coefficient between each influence cause and corresponding historical service data;
the system comprises a cause sequencing unit, a calculation unit and a calculation unit, wherein the cause sequencing unit is used for sequencing influence causes based on correlation coefficients to obtain an influence cause sequence, and the influence cause sequence is used for representing the influence degree of the influence causes on the service to be budgeted;
and the cause screening unit is used for reserving the influence causes with the preset number in the influence cause sequence for standby.
Optionally, the cause sorting unit is specifically configured to:
and judging whether the absolute value of each correlation coefficient is larger than a preset standard value or not, and sequencing the influence factors according to the judgment result to obtain an influence factor sequence.
Optionally, the cause prediction unit 43 is specifically configured to:
determining the optimal parameters in the seasonal difference autoregressive moving average model according to the minimum information quantity criterion or the Bayesian information criterion;
and based on the influence cause and the historical cause data, predicting to obtain future cause data of each service to be budgeted in the first time period by using the optimal parameters and the seasonal difference autoregressive moving average model.
Optionally, before the service budgeting unit 45 substitutes the future kinetic data into the multiple linear regression equation to obtain the budget value of the corresponding service to be budgeted, the service budgeting apparatus includes:
the error verification unit is used for verifying whether the error rate of a pre-calculated value obtained by the calculation of the multiple linear regression equation is smaller than a preset error value or not;
if the judgment result of the error verification unit is yes, the service budgeting unit 45 predicts a budget value of the corresponding service to be budgeted by using a multiple linear regression equation;
if the result of the error verification unit is negative, the service budgeting unit 45 predicts the budget value of the service to be budgeted by using a preset statistical model.
Optionally, the error verification unit is specifically configured to:
taking the historical cause data and the data in the historical service data within the second time period as verification set data, and substituting the verification set data into a multiple linear regression equation to obtain a verification predicted value of the second time period;
calculating a relative root mean square error between the verification predicted value and an actual service value in a second time period;
and judging whether the relative root mean square error is smaller than a preset error value.
Optionally, the preset statistical model includes:
annual moving average model
Wherein, a t Is an annual average traffic prediction value, a t-n Is the average service value of t-n months, t is the current month, n is the number of months, n is a positive integer;
annual weighted average model
Wherein, b t Is an annual weighted average traffic prediction value, b t-n Is the average traffic value, omega, of t-n months t-n Is a weight coefficient of t-n months, t is the current month, n is the number of months, n is a positive integer;
year-year model
Wherein, c t Is a year-year service prediction value, t is the current month, h is a year-year-year coefficient,
c t-1 to c t-12 Respectively representing average traffic values 1 to 24 months before the current month;
lunar year comparison model d t ＝s t d t-12 Wherein d is t Is a predicted value of the t-month-degree unity-ratio business, d t-12 Is the service value of t months in the last year, s t Is a monthly geometric coefficient of similarity,
monthly growth model e t Ft + g, wherein e t The predicted value of the monthly growth of the t months is, f is the historical average service growth rate, and g is a constant.
Optionally, there are a plurality of preset statistical models, and the predicting, by the service budgeting unit 45, the budget value of the service to be budgeted by using the preset statistical model specifically includes:
respectively predicting future service values of the services to be budgeted by utilizing a plurality of preset statistical models;
and taking the future service value with the minimum error rate in the plurality of predicted future service values as a budget value of the service to be budgeted.
The device provided by the embodiment of the present invention has the same implementation principle and the same technical effects as those of the foregoing method embodiments, and for the sake of brief description, reference may be made to corresponding contents in the foregoing method embodiments for the parts of the device embodiments that are not mentioned.
The service budgeting device provided by the embodiment of the invention has the same technical characteristics as the service budgeting method provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
Fig. 5 is a schematic structural diagram of a service budgeting apparatus according to an embodiment of the present invention, and as shown in fig. 5, the service budgeting apparatus includes a processor 51, a memory 52, an input device 53, and an output device 54; the number of processors 51 in the service budgeting device may be one or more, and one processor 51 is taken as an example in fig. 5; the processor 51, the memory 52, the input means 53 and the output means 54 in the traffic budgeting apparatus may be connected by a bus or other means, as exemplified by a bus connection in fig. 5.
The memory 52 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the service budgeting method in the embodiment of the present invention (for example, the category determining unit 41, the cause determining unit 42, the cause predicting unit 43, the equation fitting unit 44, and the service budgeting unit 45). The processor 51 executes various functional applications and data processing of the service budgeting apparatus by executing software programs, instructions and modules stored in the memory 52, that is, implements the service budgeting method described above.
The memory 52 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 52 can further include memory located remotely from the processor 51, which can be connected to the traffic budgeting apparatus via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 53 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function control of the service budgeting apparatus. The output device 54 may include a display device such as a display screen.
Embodiments of the present invention also provide a storage medium containing computer-executable instructions which, when executed by a computer processor, perform a method of service budgeting.
Specifically, the service budgeting method includes:
determining the service types of the services to be budgeted, and acquiring historical service data of each service to be budgeted;
determining an influence cause influencing the service development of each service to be budgeted, and acquiring historical cause data corresponding to each service to be budgeted based on the influence cause;
predicting future kinetic data of each service to be budgeted in a first time period by a time series prediction method based on the influence kinetic and historical kinetic data;
taking historical kinetic factor data as independent variables, taking historical service data as dependent variables, and fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and substituting the future kinetic data into a multiple linear regression equation to obtain a precalculated value of the corresponding service to be budgeted.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the service budget method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the service budget apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Embodiments of the present invention also provide a computer program product comprising computer-executable instructions for performing the service budgeting method provided by any of the embodiments of the present invention when executed by a computer processor.
Of course, the computer program product provided in the embodiments of the present application, whose computer executable instructions are not limited to the method operations described above, may also execute the relevant operations in the method provided in any embodiment of the present invention.
In the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Finally, it should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention and the technical principles applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.
Claims (12)
1. A service budgeting method, wherein the service budgeting method comprises:
determining the service types of services to be budgeted, and acquiring historical service data of each service to be budgeted;
determining an influence cause influencing the service development of each service to be budgeted, and acquiring historical cause data corresponding to each service to be budgeted based on the influence cause;
predicting future kinetic factor data of each service to be budgeted in a first time period by a time series prediction method based on the influence kinetic factors and the historical kinetic factor data;
taking the historical kinetic factor data as independent variables, taking the historical service data as dependent variables, and fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and substituting the future kinetic data into the multiple linear regression equation to obtain a precalculated value corresponding to the service to be budgeted.
2. The service budgeting method according to claim 1, wherein after determining the influence factors affecting the service development of each service to be budgeted, the service budgeting method further comprises:
calculating a correlation coefficient between each influence cause and the corresponding historical service data;
sequencing the influence factors based on the correlation coefficients to obtain an influence factor sequence, wherein the influence factor sequence is used for representing the influence degree of the influence factors on the service to be budgeted;
and reserving a preset number of the influence factors in the influence factor sequence for standby.
3. The traffic budgeting method of claim 2, wherein the ordering the impact factors based on the correlation coefficients to obtain an impact factor sequence comprises:
and judging whether the absolute value of each correlation coefficient is larger than a preset standard value or not, and sequencing the influence factors according to the judgment result to obtain the influence factor sequence.
4. The service budgeting method according to claim 1, wherein predicting future incentive data of each service to be budgeted in the first time period by a time series prediction method based on the influence incentive and the historical incentive data comprises:
determining the optimal parameters in the seasonal difference autoregressive moving average model according to the minimum information quantity criterion or the Bayesian information criterion;
and predicting future kinetic factor data of each service to be budgeted in the first time period by using the optimal parameters and the seasonal differential autoregressive moving average model based on the influence kinetic factors and the historical kinetic factor data.
5. The service budgeting method according to claim 1, wherein before substituting the future-cause data into the multiple linear regression equation to obtain a budget value of the corresponding service to be budgeted, the service budgeting method includes:
verifying whether the error rate of the precalculated value calculated by the multiple linear regression equation is smaller than a preset error value or not;
if yes, predicting a precalculated value of the corresponding service to be budgeted by using the multiple linear regression equation;
if not, predicting the budget value of the service to be budgeted by using a preset statistical model.
6. The traffic budgeting method of claim 5, wherein verifying whether the error rate of the budget value calculated by the multiple linear regression equation is less than a preset error value comprises:
taking data in a second time period in the historical service data as verification set data;
substituting the future kinetic factor data into the multiple linear regression equation to obtain a verification predicted value of the second time period;
calculating a relative root mean square error between the verification predicted value and an actual service value in the second time period, wherein the actual service value is the verification set data;
and judging whether the relative root mean square error is smaller than a preset error value.
7. The traffic budgeting method of claim 5, wherein the preset statistical model comprises:
annual moving average model
Wherein, a t Is an annual average traffic prediction value, a t-n Is the average service value of t-n months, t is the current month, n is the number of months, n is a positive integer;
annual weighted average model
Wherein, b t Is an annual weighted average traffic prediction value, b t-n Is the average traffic value, omega, of t-n months t-n Is a weight coefficient of t-n months, t is the current month, n is the number of months, n is a positive integer;
year-year model
Wherein, c t Is a year-year service prediction value, t is the current month, h is a year-year-year coefficient,
c t-1 to c t-12 Respectively representing average traffic values 1 to 24 months before the current month;
lunar year-on-year model d t ＝s t d t-12 Wherein d is t Is a predicted value of the t-month-degree unity-ratio business, d t-12 Is the service value of t months in the last year, s t Is a monthly unity ratio coefficient of the density of the sample,
monthly growth model e t Ft + g, wherein e t The predicted value is t month-degree growth, f is historical average service growth rate, and g is a constant.
8. The service budgeting method according to claim 5, wherein the preset statistical model is plural, and predicting the budget value of the service to be budgeted by using the preset statistical model comprises:
respectively predicting future service values of the services to be budgeted by utilizing a plurality of preset statistical models;
and taking the future service value with the minimum error rate in the plurality of predicted future service values as a budget value of the service to be budgeted.
9. A traffic budget apparatus, characterized in that the traffic budget apparatus comprises:
the system comprises a type determining unit, a data processing unit and a data processing unit, wherein the type determining unit is used for determining the service type of the service to be budgeted and acquiring historical service data of each service to be budgeted;
the dynamic factor determining unit is used for determining an influence dynamic factor influencing the service development of each service to be budgeted and acquiring historical dynamic factor data corresponding to each service to be budgeted based on the influence dynamic factor;
the dynamic factor prediction unit is used for predicting future dynamic factor data of each service to be budgeted in a first time period through a time series prediction method based on the influence dynamic factors and the historical dynamic factor data;
an equation fitting unit, configured to use the historical motion factor data as an independent variable, use the historical service data as a dependent variable, and perform fitting by using a Lasso regression model to obtain a multiple linear regression equation;
and the service budget unit is used for substituting the future kinetic factor data into the multiple linear regression equation to obtain a budget value corresponding to the service to be budgeted.
10. A business budgeting apparatus, characterized in that the business budgeting apparatus comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the business budgeting method of any of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the service budgeting method according to any one of claims 1 to 8.
12. A computer program product comprising a computer program which, when executed by a processor, implements a traffic budgeting method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210728675.2A CN115099933A (en) | 2022-06-24 | 2022-06-24 | Service budget method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210728675.2A CN115099933A (en) | 2022-06-24 | 2022-06-24 | Service budget method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115099933A true CN115099933A (en) | 2022-09-23 |
Family
ID=83292027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210728675.2A Pending CN115099933A (en) | 2022-06-24 | 2022-06-24 | Service budget method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115099933A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502019A (en) * | 2023-04-27 | 2023-07-28 | 广东花至美容科技有限公司 | Skin collagen protein lifting rate calculation method, storage medium and electronic equipment |
-
2022
- 2022-06-24 CN CN202210728675.2A patent/CN115099933A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502019A (en) * | 2023-04-27 | 2023-07-28 | 广东花至美容科技有限公司 | Skin collagen protein lifting rate calculation method, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Fontnouvelle et al. | Using loss data to quantify operational risk | |
| US6098052A (en) | Credit card collection strategy model | |
| US8577791B2 (en) | System and computer program for modeling and pricing loan products | |
| EP1066582A1 (en) | System, method, and computer program product for assessing risk within a predefined market | |
| CN111709826A (en) | Target information determination method and device | |
| CN110689437A (en) | Communication construction project financial risk prediction method based on random forest | |
| RU2640633C2 (en) | Calculation of probability that company complies with its obligations | |
| CN111738819A (en) | Method, device and equipment for screening characterization data | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN111626855A (en) | Bond credit interest difference prediction method and system | |
| Karminsky et al. | Increase of banks’ credit risks forecasting power by the usage of the set of alternative models | |
| CN115099933A (en) | Service budget method, device and equipment | |
| CN116911994B (en) | External trade risk early warning system | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| CN114943582A (en) | Information recommendation method and system and recommendation server | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN114219611A (en) | Loan amount calculation method and device, computer equipment and storage medium | |
| CN113240513A (en) | Method for determining user credit line and related device | |
| CN113222767A (en) | Data processing method and device for indexing securities combination | |
| CN111461863A (en) | Data processing method and device, computer equipment and storage medium | |
| CN117994017A (en) | Method for constructing retail credit risk prediction model and online credit service Scoredelta model | |
| CN117788133A (en) | Method for constructing retail credit risk prediction model and retail credit score model | |
| CN118071482A (en) | Method for constructing retail credit risk prediction model and consumer credit business Scorebetad model | |
| CN118071483A (en) | Method for constructing retail credit risk prediction model and personal credit business Scorepsi model | |
| CN117764692A (en) | Method for predicting credit risk default probability |
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 |