CN115526403A

CN115526403A - Financial data prediction method, system, equipment, storage medium and product

Info

Publication number: CN115526403A
Application number: CN202211216675.0A
Authority: CN
Inventors: 孙冰冰; 张逸
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2022-12-27

Abstract

The invention discloses a method, a system, equipment, a storage medium and a product for predicting financial data. The method comprises the following steps: acquiring basic service data of stock service, and determining the stock service data of the stock service in a prediction time range; determining predicted service data in the prediction time range; and performing prediction processing on financial data based on the predicted business data and the stock business data to obtain predicted financial data in a prediction time range. The method and the system predict the predicted financial data through three service types, namely the stock conversion service, the stock conversion service and the newly added service, increase the reference of the stock conversion service and the newly added service and improve the accuracy of prediction.

Description

Financial data prediction method, system, equipment, storage medium and product

Technical Field

The invention relates to the technical field of information processing, in particular to a method, a system, equipment, a storage medium and a product for predicting financial data.

Background

In order to plan the overall operation, the financial institution needs to predict the financial data of the business, wherein the net interest income in the financial data is an important income source of the financial institution, and correspondingly, the net interest income is also a main prediction object in the financial data.

At present, the prediction mode of the net interest income is mainly based on the stock business data of the financial institution, and after the accumulation and the summarization processing are carried out by accessing the general ledger data, the ratio of the net interest income to the general interest assets is determined as the prediction result of the net interest income. The prediction method has the problem of inaccurate prediction.

Disclosure of Invention

The invention provides a method, a system, equipment, a storage medium and a product for predicting financial data, which aim to solve the problem of inaccurate prediction of the financial data

According to an aspect of the present invention, there is provided a method of predicting financial data, including:

acquiring basic service data of stock service, and determining the stock service data of the stock service in a prediction time range;

determining predicted service data in the prediction time range;

and performing prediction processing on financial data based on the predicted business data and the stock business data to obtain predicted financial data in a prediction time range.

Further, the predicted service data comprises stock conversion service data and newly added service data;

the determining the predicted service data in the prediction time range includes:

determining inventory conversion business data in the prediction time range based on the inventory business; and/or predicting the newly added service data in the prediction time range based on the pre-configured product attributes.

Further, the determining the inventory conversion service data in the prediction time range based on the inventory service comprises:

and reading basic service data of each stock service from a data warehouse, and predicting stock conversion service data in the prediction time range based on the basic service data.

Further, the reading basic service data of each stock service from a data warehouse and predicting stock conversion service data in the prediction time range based on the basic service data includes:

and extracting prediction reference data from the basic service data, and inputting the prediction reference data of each stock service into a conversion service prediction model to obtain stock conversion service data output by the conversion service prediction model.

Further, the reading basic service data of each stock service from a data warehouse, and predicting stock conversion service data in the prediction time range based on the basic service data includes:

at least part of basic service data of each stock quantity service is displayed through a client, stock quantity conversion service fed back by the client is received, and stock quantity conversion service data of the stock quantity conversion service in a prediction time range are predicted.

Further, predicting the newly added service data within the prediction time range based on the preconfigured product attributes includes:

reading the product attributes of various types of products, and inputting the product attributes of various types of products into a newly added service prediction model to obtain newly added service data within the prediction time range;

or reading the product attributes of each type of product, respectively predicting the product attributes of each type of product based on the newly added service prediction model to obtain newly added service information corresponding to each type of product, and predicting newly added service data within the prediction time range of the newly added service information corresponding to each type of product.

Further, the prediction time range comprises a first prediction time range before the financial parameter change node and a second prediction time range after the financial parameter change node;

the method further comprises the following steps: predicting a predicted financial parameter within the second predicted time range;

correspondingly, the determining of the inventory business data of the inventory business in the prediction time range comprises: determining inventory business data within the first prediction time range based on known financial parameters; and/or determining inventory business data within the second predicted time range based on the predicted financial parameters;

and, the determining the predicted service data within the prediction time range comprises: determining predicted business data within the first predicted time range based on known financial parameters; and/or, determining predicted business data within the second predicted time range based on the predicted financial parameter.

Further, the predicted financial data is net interest balance data, and the financial parameters include interest rate.

Further, the method further comprises: configuring a pressure scenario in a prediction process; and under the pressure situation, performing pressure prediction processing on one or more of the predicted business data and the stock business data to obtain predicted financial data under the pressure situation.

Further, the pressure scenario includes one or more of: financial parameter floating scenes and user financial behavior scenes.

Further, the configuring the pressure scenario in the prediction process includes: the method comprises the steps of displaying a pressure scenario configuration interface through a client, and receiving a pressure scenario fed back by the client, wherein the pressure scenario comprises scenario parameters.

According to an aspect of the present invention, there is provided a prediction system of financial data, including:

the stock business metering module is used for determining stock business data of the stock business in a prediction time range;

the service prediction module is used for determining predicted service data in the prediction time range;

and the financial data prediction module is respectively connected with the stock business metering module and the business prediction module, receives the stock business data and the predicted business data, and performs prediction processing on the financial data based on the predicted business data and the stock business data to obtain the predicted financial data within a prediction time range.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method of predicting financial data according to any embodiment of the invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to perform a method for predicting financial data according to any one of the embodiments of the present invention when the computer instructions are executed.

According to another aspect of the present invention, there is provided a computer program product, characterized in that the computer program product comprises a computer program, which when executed by a processor implements the method of prediction of financial data according to any of the embodiments of the present invention.

According to the technical scheme of the embodiment of the invention, the interest balance data of the stock business, the stock conversion business and the newly added business in the prediction time range are respectively determined based on the basic business data, and then the financial data is predicted based on the stock business, the stock conversion business and the newly added business, so that the reference to the stock conversion business and the newly added business is increased, the predicted financial data is predicted from three business types of the stock business, the stock conversion business and the newly added business, and the prediction accuracy is improved; meanwhile, the predicted financial data under different pressure scenes can be predicted by configuring different pressure scenes, and the predicted financial data under different pressure scenes can be analyzed.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a method for predicting financial data according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a system for predicting financial data according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions of the present invention, 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.

It should be noted that the terms "first feature data", "second feature data", and the like in the description and the claims of the present invention and the drawings described above are used for distinguishing similar objects and are not necessarily used for describing a particular sequence or order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The technical scheme related by the application can be used for acquiring, storing and/or processing the data, and the relevant regulations of national laws and regulations are met.

Example one

Fig. 1 is a flowchart of a method for predicting financial data according to an embodiment of the present invention, where the embodiment is applicable to a case of predicting financial data (e.g., net interest balance data) in the financial industry, and the method may be implemented by a system for predicting financial data, which may be implemented in hardware and/or software, and the predicting of financial data may be configured in an electronic device and/or product. As shown in fig. 1, the method includes:

s110, acquiring basic service data of stock service, and determining the stock service data of the stock service in a prediction time range.

And S120, determining the predicted service data in the prediction time range.

S130, performing prediction processing on financial data based on the predicted business data and the stock business data to obtain predicted financial data in a prediction time range.

The basic business data refers to general ledger data of the inventory business stored in the data warehouse, and specifically, the basic business data includes but is not limited to actual data of the inventory liability business in tables such as deposits, loans, bonds, borrowings, buys, currency fall-off periods, interest rate fall-off periods, and the like of each inventory business, and auxiliary information such as general ledgers, institutions, standard interest rates, and products, which is not limited herein. The inventory business data refers to interest income and expenditure data of the volume business in a prediction time range, and specifically, the inventory business data is the interest income and expenditure data determined based on the interest income data and the interest expenditure data of the inventory business, wherein the inventory business is the existing business of a financial institution, and comprises the existing business corresponding to different products respectively, for example, the interest income data corresponding to the income type of the inventory business, and the interest expenditure data corresponding to the liability type of the inventory business.

The predicted service data refers to interest balance data of a predicted service in a predicted time range, and the predicted service is a non-existing service predicted in the predicted time range, for example, a newly added service in the predicted time range, namely an incremental service, or an inventory conversion service converted from an inventory service, and the like.

In this embodiment, basic service data of the stock service in the data warehouse is acquired, interest cash flow of the stock service in a prediction time range is acquired by splitting cash flow based on the basic service data, and the interest cash flow is summarized and accumulated through a plurality of dimensions to acquire stock service data in the prediction time range, wherein the summarized and accumulated dimensions include but are not limited to dimensions of mechanisms, service categories, currency types and the like, and are not limited herein; predicting based on the predicted service information to obtain predicted service data in a predicted time range, and performing prediction processing on financial data based on stock service data and the predicted service data to obtain predicted financial data in the predicted time range; the predicted financial data may be net interest balance data, and specifically, the predicted financial data is a net interest difference (NIM) within a predicted time range; the prediction time range in this embodiment is set by a person skilled in the art according to requirements, and is not limited herein. In the embodiment, the prediction system of the financial data is arranged to predict the business within the prediction time range obtained by prediction in the prediction process of the financial data, the predicted business data is further obtained by prediction, and the predicted financial data within the prediction time range is obtained by prediction of the stock business data and the predicted business data, so that the comprehensiveness of the business involved in the prediction process of the financial data is improved, and the accuracy of the prediction of the financial data is improved.

On the basis of the above embodiment, optionally, the predicted service data includes stock conversion service data and newly added service data; the determining the predicted service data in the prediction time range includes: determining inventory conversion business data in the prediction time range based on the inventory business; and/or predicting the newly added service data in the prediction time range based on the pre-configured product attributes.

The inventory conversion service refers to an inventory conversion service obtained by performing service conversion on the inventory service, and specifically, the inventory conversion service may include, but is not limited to, a due continuation service of the inventory service and a due new generation service of the inventory service, and accordingly, the inventory conversion service data is interest and expenditure data of the inventory conversion service in a prediction time range. In this embodiment, the stock conversion service corresponding to the stock service is predicted based on the stock service, the stock conversion service information of the stock conversion service is obtained based on the basic service data of the stock service, and then prediction is performed based on the stock conversion service information, so that the stock conversion service data within the prediction time range is obtained. Specifically, if the stock business needs business conversion in the prediction time range, the stock business is converted into the stock conversion business, the time point of business conversion is used as a conversion node, prediction is carried out based on the stock conversion business information, and stock conversion business data in the prediction time range after the conversion node are obtained. It can be understood that before the conversion node, interest cash flow of the stock service in the prediction time range is obtained by splitting the cash flow based on the basic service data, the interest cash flow is collected and accumulated through a plurality of dimensions, the stock service data in the prediction time range is collected and accumulated through a plurality of dimensions, and the stock service data in the prediction time range before the conversion node is obtained.

The newly added service data refers to interest balance data of the newly added service within the prediction time range. The product attribute refers to an attribute of each type of financial product released by the financial institution, and specifically, the product of the financial institution includes, but is not limited to, a deposit product, a loan product, and the like, and is not limited herein. In this embodiment, newly added service data within a prediction time range is predicted based on a preconfigured product attribute. Specifically, the newly added service may be predicted by calling a preset machine learning model, where the machine learning model, that is, the newly added service prediction model, may include, but is not limited to, a neural network model, and the like. The newly added service prediction model is obtained by pre-training, for example, by training product attributes before a historical time period and newly added service data in the historical time period.

On the basis of the foregoing embodiment, optionally, predicting new service data in the prediction time range based on a preconfigured product attribute includes: reading the product attributes of various types of products, and inputting the product attributes of various types of products into a newly added service prediction model to obtain newly added service data within the prediction time range; or reading the product attributes of the products of each type, respectively predicting the product attributes of the products of each type based on the newly added service prediction model to obtain newly added service information corresponding to the products of each type, and predicting newly added service data within the prediction time range of the newly added service information corresponding to the products of each type.

In this embodiment, the product attributes of each type of product are pre-stored in the database or the preset storage space, and can be read according to the requirements. Optionally, the newly added service prediction model may have a prediction function for different types of products, and correspondingly, the product attributes of each type of product may be input into the newly added service prediction model to obtain newly added service data of each type of product within the prediction time range.

Optionally, a newly added service prediction model is preset, and the newly added service prediction model can be used for performing prediction processing on one type of product, and correspondingly, the product attributes of each type of product are read, and the product attributes of each type of product are respectively subjected to prediction processing based on the newly added service prediction model, so as to obtain newly added service information corresponding to each type of product. Illustratively, a plurality of newly added service prediction models can be called in parallel to predict different types of products; illustratively, the number of the newly added service prediction models is multiple, the different newly added service prediction models are respectively used for predicting different types of products, correspondingly, the corresponding newly added service prediction model is called according to the product type, and the product attribute of the type of product is input into the corresponding newly added service prediction model for prediction processing. And predicting the newly added service data of each type of product in the prediction time range based on the newly added service information corresponding to each type of product, wherein the newly added service prediction model can be a machine learning model trained based on historical data of each type of product, and the model type and the specific structure and parameters of the model are not limited.

On the basis of the foregoing embodiment, optionally, the determining inventory conversion service data in the prediction time range based on the inventory service includes: and reading basic service data of each stock service from a data warehouse, and predicting stock conversion service data in the prediction time range based on the basic service data.

The data warehouse is used for storing basic service data of the stock service, and specifically, the data warehouse may be a database, and may also be a storage device, which is not limited herein. In this embodiment, the basic service data of each stock quantity service is read from the data warehouse through the data interface, and prediction is performed based on the basic service data, so as to obtain the stock quantity conversion service data of the stock quantity conversion service within the prediction time range.

On the basis of the foregoing embodiment, optionally, the reading the basic service data of each inventory service from the data warehouse, and predicting the inventory conversion service data within the prediction time range based on the basic service data includes: and extracting prediction reference data from the basic service data, and inputting the prediction reference data of each stock service into a conversion service prediction model to obtain stock conversion service data output by the conversion service prediction model.

In this embodiment, the basic service data of each stock service is read from the data warehouse through the data interface, the prediction reference data is extracted from the basic service data, and the prediction reference data of each stock service is input into the conversion service prediction model, so as to obtain the stock conversion service data output by the conversion service prediction model.

The forecast reference data refers to basic service data of the stock conversion service inheriting the original stock service, specifically, the stock conversion service includes a stock service continuation service and a stock service due new generation service, under the condition that the stock conversion service is the stock service continuation service, exemplarily, a room credit service is assumed to be paid for in 360 periods, after each period of payment, the room credit data with one period consistent with the stock service attribute is directly added on the basis of the original stock service through mode measurement and calculation, the service after the room credit data is added is the stock conversion service, the basic service data of the stock conversion service is the same as the original stock service, namely, the forecast reference parameter is the basic service data of the original stock service. In the case that the stock conversion service is a new generation service when the stock service expires, for example, taking the original stock service as a periodic deposit service, the periodic deposit service is automatically converted into a deposit-alive service after the periodic deposit service expires, the converted deposit-alive service is the stock conversion service, and the basic service data of the periodic deposit service, which is the same as that of the deposit-alive service, is the prediction reference data. In this embodiment, the basic service data of the stock services is read through the data interface, the basic service data is extracted to obtain prediction reference data, the prediction reference data of each stock service is input to the conversion service prediction model to perform prediction, and stock conversion service data is obtained, where the conversion service prediction model may be a machine learning model obtained based on historical data training of the stock services, and is not limited here. Here, in order to avoid a case where the data amount index is increased as new data in the service information corresponding to the stock quantity conversion service, the service information of the stock quantity service may be updated as the service information of the stock quantity conversion service so as to reduce the data amount of the service information.

On the basis of the foregoing embodiment, optionally, the reading the basic service data of each inventory service from the data warehouse, and predicting the inventory conversion service data within the prediction time range based on the basic service data includes: at least part of basic service data of each stock quantity service is displayed through a client, stock quantity conversion service fed back by the client is received, and stock quantity conversion service data of the stock quantity conversion service in a prediction time range are predicted.

The client is configured with a display component, can display information, and realizes information interaction with an operation user, and the client includes but is not limited to a mobile phone, a PC, a tablet computer and other terminal devices. In this embodiment, a user may convert stock keeping services into stock keeping conversion services through a client, specifically, at least part of data in basic service data of each stock keeping service is sent to the client, and the client receives and displays corresponding basic service data on a data display page, where at least part of data in the basic service data may include, but is not limited to, a service identifier, time information, and the like of the stock keeping services. And receiving the configuration operation of the user on the displayed basic service data through the data display page, and determining the stock conversion service (for example, determining the corresponding stock conversion service based on the selected stock conversion service). Receiving the stock conversion service fed back by the client, and predicting the stock conversion service data of the stock conversion service in the prediction time range, wherein the basic service data may be sent to the client by network push, and the method is not limited here. The manner of the client feeding back the stock quantity service data may be to store the configured basic service data in the component database, and periodically synchronize the basic service data to the distributed database of the stock quantity conversion service prediction sub-module 121, which is not limited herein.

On the basis of the foregoing embodiment, optionally, the predicted time range includes a first predicted time range before the financial parameter changing node and a second predicted time range after the financial parameter changing node; the method further comprises the following steps: predicting a predicted financial parameter within the second predicted time range; correspondingly, the determining of the inventory business data of the inventory business in the prediction time range comprises: determining inventory business data within the first prediction time range based on known financial parameters; and/or determining inventory business data within the second predicted time range based on the predicted financial parameters; and, the determining the predicted service data within the prediction time range comprises: determining predicted business data within the first predicted time range based on known financial parameters; and/or determining predicted business data within the second predicted time range based on the predicted financial parameter.

The financial parameters are related parameters for determining the service data, specifically, the financial parameters include interest rates, and correspondingly, the first prediction time range is a prediction time range before an interest rate change node in the prediction time range, and the second prediction time range is a prediction time range after the interest rate change node in the prediction time range. In this embodiment, the financial parameters in the first prediction time range are known financial parameters, and the predicted financial parameters in the second prediction time range are predicted by the financial parameter prediction module, specifically, the known financial parameters in the first prediction time range and the related parameters may be input into a preset financial parameter prediction model to obtain the predicted financial parameters in the second prediction time range.

In the embodiment, the interest cash flow of the inventory service in the first prediction time range is obtained through cash flow splitting based on the known financial parameters and the inventory service information, and the interest cash flow is subjected to multi-dimensional summary accumulation to obtain inventory service data in the first prediction time range; and splitting the cash flow based on the predicted financial parameters and the stock business information to obtain interest cash flow of the stock business in a second prediction time range, and summarizing and accumulating the interest cash flow through a plurality of dimensions to obtain stock business data in the second prediction time range.

In the embodiment, prediction is performed based on known financial parameters and prediction service information to obtain prediction service data within a first prediction time range, and specifically, the known financial parameters and the prediction reference data are input into a conversion service prediction model to perform prediction to obtain stock conversion service data within the first prediction time range; and/or inputting known financial parameters and product attributes of various types of products into the newly added service prediction model for prediction to obtain newly added service data within the first prediction time range. Predicting based on the predicted financial parameters and the predicted business information to obtain predicted business data in a second prediction time range, and specifically, inputting the predicted financial parameters and the predicted reference data into a conversion business prediction model for prediction to obtain stock conversion business data in the second prediction time range; and/or inputting the predicted financial parameters and the product attributes of various types of products into a newly added service prediction model for prediction to obtain newly added service data within a second prediction time range.

The financial parameter prediction module predicts and obtains a predicted financial parameter in a second prediction time range based on the balance of the financial parameter change node, the stock business data and the predicted business data. For example, taking the financial parameter as the interest rate, the interest rate in the second prediction time range may be a ratio of a sum of data of stock business data and prediction business data of the financial parameter changing node to a balance of the financial parameter changing node.

On the basis of the foregoing embodiment, optionally, the method further includes: configuring a pressure scenario in a prediction process; and under the pressure situation, performing pressure prediction processing on one or more of the predicted business data and the stock business data to obtain predicted financial data under the pressure situation.

The pressure scenario refers to a special scenario or event simulated by configuring related parameters, and is used for evaluating the influence of the special scenario or event in the financial market on the value change of the asset combination. In this embodiment, the financial parameters are predicted and predicted under a pressure scenario, specifically, the pressure scenario in the prediction process is configured, under the configured pressure scenario, the stock business data and the predicted business data are predicted based on the method provided in the above embodiment, and one or more of the predicted business data and the stock business data are subjected to pressure prediction processing, so as to obtain the predicted financial data under the pressure scenario.

On the basis of the foregoing embodiment, optionally, the pressure scenario includes one or more of the following: financial parameter floating scenes and user financial behavior scenes.

In this embodiment, the stress scenario includes one or more of a financial parameter floating scenario and a user financial behavior scenario, specifically, the financial parameter floating scenario may be an interest rate variation scenario, and for example, the financial parameter floating scenario includes, but is not limited to, that a long-term interest rate decreases faster than a short-term interest rate, a short-term interest rate increases faster than a long-term interest rate, a short-term interest rate decreases faster than a long-term interest rate, and the like, which is not limited herein; the user financial behavior scenes include, but are not limited to, situations such as a user paying a large amount of money in advance, a user defaulting a large amount of loans, and a large amount of users failing to pay back loans in special situations, and the like, and are not limited herein.

On the basis of the foregoing embodiment, optionally, the configuring a pressure scenario in the prediction process includes: displaying a pressure scenario configuration interface through a client, and receiving a pressure scenario fed back by the client, wherein the pressure scenario comprises scenario parameters.

In this embodiment, a client displays a pressure scenario configuration interface, a user can configure scenario parameters in the pressure configuration interface through the pressure configuration interface to obtain a corresponding pressure scenario, and then feeds back the pressure scenario to receive the pressure scenario fed back by the client, so that the pressure scenario configuration is completed; wherein the pressure scenario includes the configured completed scenario parameters. The situation parameters may include parameters of different pressure intensities, so as to perform pressure tests of different pressure intensities.

In this embodiment, the prediction business data under the pressure scene and the stock business data under the pressure scene are obtained by respectively processing according to the scene parameters, and the prediction financial data under the pressure scene is obtained according to the prediction business data under the pressure scene and the stock business data under the pressure scene. The financial data is predicted in different pressure scenes to simulate the situation of a financial institution under different pressure scenes, so that an emergency plan is set in advance conveniently.

According to the technical scheme of the embodiment, the interest balance data of the stock business, the stock conversion business and the newly added business in the prediction time range are respectively determined based on the basic business data, and then the financial data is predicted based on the stock business, the stock conversion business and the newly added business, so that the reference to the stock conversion business and the newly added business is increased, the predicted financial data is predicted from three business types of the stock business, the stock conversion business and the newly added business, and the prediction accuracy is improved; meanwhile, the predicted financial data under different pressure scenes can be predicted by configuring different pressure scenes, and the predicted financial data under different pressure scenes can be analyzed.

On the basis of the above embodiment, an embodiment of the present invention further provides a preferred example of a method for predicting financial data, in this embodiment, basic service data of inventory services in a data warehouse is read through a data interface, interest cash flows of the inventory services in a prediction time range are obtained by splitting cash flows based on the basic service data, and multi-dimensional aggregation and accumulation are performed on the interest cash flows to obtain inventory service data of the inventory services in the prediction time range. Illustratively, the formula for calculating the inventory business data is as follows:

stock traffic data = ∑ (a certain stock traffic stock amount x number of days during the ith re-pricing period within the prediction time range/360 × r), where r represents interest rate.

In the embodiment, the predicted service data is determined based on the predicted service information; specifically, the prediction service data comprises stock conversion service data and newly added service data, for the stock conversion service data, basic service data of the stock service is extracted to obtain prediction reference data, and prediction is performed based on the prediction reference data to obtain the stock conversion service data within a prediction time range; and predicting the newly added service data based on the configured product attributes to obtain the newly added service data within the prediction time range. Illustratively, the calculation formula of the predicted service data is as follows:

predicted traffic data = [ daily increment amount of a certain type of predicted traffic × number of days of i-th revaluation period of a certain type of predicted traffic within a predicted time range/360 × r), where r represents interest rate.

In this embodiment, the prediction processing of the financial data is performed on the predicted business data and the stock business data, so as to obtain the predicted financial data within the prediction time range.

For example, assuming the prediction time range is within the year, the measurement time range is divided into two parts: inventory history period and future reckoning period, for example: by predicting NIM and net interest income of 2020 year all year with inventory business from 1 month to 3 months and 31 days of 2020 year, the inventory history period is from 1 month to 3 months and 31 days of 2020 year, and the future calculation period is from 1 month to 12 months and 31 days of 2020 year 4 month.

(1) Interest balance during reckoning = interest balance data of the stock business having occurred + interest balance data of the stock business during future reckoning + interest balance data of the stock conversion business during future reckoning + interest balance data of the new business during future reckoning. The interest balance data herein may be interest balance.

(2) Annual interest balance = interest balance/duration of measurement during measurement 360.

(3) The daily average balance of the measuring period = (daily average balance of the inventory history period:inventoryhistory time length + inventory service at the prediction time point of the inventory service:futuremeasuring period + (inventory conversion service + new service) (prediction cutoff date-incremental service generation date))/prediction total time length.

(4) Predicted financial data = (annual interest income on assets-annual interest expenditure on liabilities)/total daily average balance of assets.

Assuming that the prediction time range is the next year, the balance and interest rate at the end of the year are predicted, and then the predicted financial data of the next year are predicted according to the end of the year. The prediction method is generally the same, with the inventory history period equal to 0.

(1) The balance of the last time point of the year = balance of the current predicted time point + the expected new scale of the year.

(2) Interest rate = (annual interest balance from forecast time point to end of year + annual interest balance of newly added scale of this year)/time point balance of this year (note: newly added scale includes newly added service and stock conversion service).

(3) The interest balance during the calculation = interest balance data of the stock business during the future calculation + interest balance data of the stock conversion business during the future calculation + interest balance data of the new business during the future calculation.

(4) Annual interest balance = interest balance/duration of measurement during measurement 360.

(5) The measurement period daily average balance = (the balance of the stock service at the prediction time point = the future measurement period + (stock conversion service + new service) (prediction deadline-incremental service generation date))/the prediction total time length.

(6) Predicted financial data = (annual interest income on assets-annual interest expenditure on liabilities)/total daily average balance of assets.

On the basis of the foregoing embodiment, optionally, the method further includes: acquiring a pressure scene in a prediction process; correspondingly, the predicting the financial data based on the predicted business data and the stock business data to obtain the predicted financial data in the prediction time range includes: and under the pressure scene, performing pressure prediction processing on one or more items in the predicted business data and the stock business data to obtain predicted financial data under the pressure scene.

In this embodiment, a pressure scenario is set for a prediction process of predicting financial data, the predicted financial data is predicted in the pressure scenario, specifically, the pressure scenario in the prediction process is obtained, and in the pressure scenario, pressure prediction processing is performed on one or more of the predicted business data and stock business data to obtain the predicted financial data in the pressure scenario.

It should be noted that, the terms explained in the above embodiments are not repeated in this embodiment.

According to the technical scheme of the embodiment, the forecast financial data is forecasted through three service types, namely the stock conversion service, the stock conversion service and the newly added service, so that references to the stock conversion service and the newly added service are increased, and the forecasting accuracy is improved; meanwhile, the predicted financial data are obtained through prediction under the pressure situation, and the predicted financial data under different pressure situations can be analyzed.

Example two

Fig. 2 is a schematic structural diagram of a financial data prediction system according to a second embodiment of the present invention, and as shown in fig. 2, the system specifically includes:

an inventory business metering module 210 for determining inventory business data of the inventory business within a prediction time range;

a service prediction module 220, configured to determine predicted service data within the prediction time range;

the financial data prediction module 230 is connected to the stock business metering module 210 and the business prediction module 220, respectively, and receives the stock business data and the predicted business data, and performs prediction processing on the financial data based on the predicted business data and the stock business data to obtain predicted financial data within a prediction time range.

Optionally, the service prediction module 220 includes an inventory conversion service prediction sub-module 221 and a new service prediction sub-module 222; correspondingly, the forecast service data comprises stock conversion service data and newly added service data;

an inventory conversion service prediction sub-module 221, configured to determine inventory conversion service data within the prediction time range based on the inventory service;

and the new service predicting sub-module 222 is configured to predict new service data within the prediction time range based on a preconfigured product attribute.

Optionally, the system is connected to a data warehouse, and basic service data of stock service is stored in the data warehouse;

the inventory business metering module 210 reads basic business data of each inventory business from the data warehouse and determines the inventory business data of the inventory business in a prediction time range based on the basic business data;

and the stock conversion service prediction sub-module 221 reads basic service data of each stock service from the data warehouse, and predicts the stock conversion service data within the prediction time range based on the basic service data.

Optionally, the stock conversion service prediction sub-module 221 extracts prediction reference data from the basic service data, and inputs the prediction reference data of each stock service into the conversion service prediction model to obtain the stock conversion service data output by the conversion service prediction model.

Optionally, the system is in communication connection with a client;

the stock conversion service prediction submodule displays at least part of basic service data of each stock service through a client, receives the stock conversion service fed back by the client and predicts the stock conversion service data of the stock conversion service in a prediction time range.

Optionally, the newly added service prediction sub-module 222 is configured to: reading the product attributes of various types of products, and inputting the product attributes of various types of products into a newly added service prediction model to obtain newly added service data within the prediction time range;

or reading the product attributes of the products of each type, respectively predicting the product attributes of the products of each type based on the newly added service prediction model to obtain newly added service information corresponding to the products of each type, and predicting newly added service data within the prediction time range of the newly added service information corresponding to the products of each type.

Optionally, the prediction time range includes a first prediction time range before the financial parameter changing node and a second prediction time range after the financial parameter changing node;

the system further comprises a financial parameter prediction module for predicting predicted financial parameters within the second predicted time range;

a business inventory metering module 210 that determines business inventory data within the first prediction time range based on known financial parameters; and/or determining inventory business data within the second predicted time range based on the predicted financial parameters;

a traffic prediction module 220 for determining predicted traffic data within the first predicted time range based on known financial parameters; and/or determining predicted business data within the second predicted time range based on the predicted financial parameter.

Optionally, the predicted financial data is net interest balance data, and the financial parameter includes interest rate.

Optionally, the system further includes:

a scene simulation module 240 configured to configure a pressure scenario in the prediction process;

and the pressure prediction module 250 of the financial data is configured to perform pressure prediction processing on one or more of the predicted business data and the stock business data under the pressure scenario to obtain predicted financial data under the pressure scenario.

Optionally, the pressure scenario includes one or more of: financial parameter float scenario, user financial behavior scenario.

Optionally, the scene simulation module 240 displays a pressure scenario configuration interface through the client, and receives a pressure scenario fed back by the client, where the pressure scenario includes scenario parameters.

The financial data prediction device provided by the embodiment of the invention can execute the financial data prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the financial data prediction method.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a prediction method of financial data.

In some embodiments, the prediction method of financial data may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the prediction method of financial data described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the prediction method of the financial data by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable financial data forecasting apparatus such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

Example four

An embodiment of the present invention further provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are used to enable a processor to execute a method for predicting financial data, where the method includes:

acquiring basic service data of stock service, and determining the stock service data of the stock service in a prediction time range; determining predicted service data in the prediction time range; and performing prediction processing on financial data based on the predicted business data and the stock business data to obtain predicted financial data within a prediction time range.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

EXAMPLE five

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 method for predicting financial data according to any embodiment of the present invention.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting financial data, comprising:

determining predicted service data in the prediction time range;

2. The method of claim 1, wherein the forecast service data includes inventory conversion service data and new service data;

determining inventory conversion service data within the prediction time range based on the inventory service; and/or predicting the newly added service data in the prediction time range based on the pre-configured product attributes.

3. The method of claim 2, wherein said determining inventory conversion traffic data within said predicted time horizon based on said inventory traffic comprises:

4. The method of claim 3, wherein reading base business data for each inventory business from a data warehouse and predicting inventory conversion business data within the prediction time range based on the base business data comprises:

5. The method of claim 3, wherein reading base business data for each inventory business from a data warehouse and predicting inventory conversion business data within the prediction time horizon based on the base business data comprises:

at least part of basic service data of each stock quantity service is displayed through a client, stock quantity conversion service fed back by the client is received, and the stock quantity conversion service data of the stock quantity conversion service in a prediction time range are predicted.

6. The method of claim 2, wherein predicting new service data within the prediction time horizon based on preconfigured product attributes comprises:

reading the product attributes of each type of product, and inputting the product attributes of each type of product into a newly added service prediction model to obtain newly added service data within the prediction time range;

7. The method of claim 1, wherein the predicted time range comprises a first predicted time range before a financial parameter altering node, a second predicted time range after a financial parameter altering node;

the method further comprises the following steps:

predicting a predicted financial parameter within the second predicted time range;

correspondingly, the determining of the inventory business data of the inventory business in the prediction time range comprises the following steps:

determining inventory business data within the first prediction time range based on known financial parameters; and/or determining inventory business data in the second prediction time range based on the predicted financial parameters;

and the number of the first and second groups,

determining predicted business data within the first predicted time range based on known financial parameters; and/or determining predicted business data within the second predicted time range based on the predicted financial parameter.

8. The method of claim 1, wherein the predicted financial data is net interest balance data and the financial parameter comprises interest rate.

9. The method of claim 1, further comprising:

configuring a pressure scenario in a prediction process;

and under the pressure scene, performing pressure prediction processing on one or more items in the predicted business data and the stock business data to obtain predicted financial data under the pressure scene.

10. The method of claim 9, wherein the pressure scenario comprises one or more of: financial parameter floating scenes and user financial behavior scenes.

11. The method of claim 9, wherein configuring the stress scenario in the prediction process comprises:

the method comprises the steps of displaying a pressure scenario configuration interface through a client, and receiving a pressure scenario fed back by the client, wherein the pressure scenario comprises scenario parameters.

12. A system for forecasting financial data, comprising:

the stock business metering module is used for determining stock business data of the stock business within a prediction time range;

and the financial data prediction module is respectively connected with the stock business metering module and the business prediction module, receives the stock business data and the predicted business data, and performs prediction processing on the financial data based on the predicted business data and the stock business data to obtain predicted financial data in a prediction time range.

13. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of predicting financial data of any one of claims 1-11.

14. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of predicting financial data of any one of claims 1-11 when executed.

15. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out a method of prediction of financial data according to any one of claims 1-11.