CN111932379A - Data processing method and device, electronic equipment and readable storage medium - Google Patents
Data processing method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111932379A CN111932379A CN202011006355.3A CN202011006355A CN111932379A CN 111932379 A CN111932379 A CN 111932379A CN 202011006355 A CN202011006355 A CN 202011006355A CN 111932379 A CN111932379 A CN 111932379A
- Authority
- CN
- China
- Prior art keywords
- data
- feature
- prediction
- prediction model
- target object
- 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.)
- Granted
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
- G06Q40/06—Asset management; Financial planning or analysis
Abstract
The embodiment of the disclosure discloses a data processing method and device, electronic equipment and a readable storage medium. The data processing method comprises the following steps: acquiring historical characteristic data of a plurality of characteristics of a target object; for each feature, determining a target interval of the feature according to a result of prediction based on historical feature data of the feature by using a first prediction model and a result of prediction based on historical feature data of the feature by using a second prediction model; acquiring current feature data of a plurality of features of a target object; calculating characteristic data in a target interval of corresponding characteristics in the current characteristic data according to the characteristic data by using a first prediction model to obtain first prediction data serving as specific prediction data; regarding feature data which is not located in a target interval of corresponding features in the current feature data, taking default prediction data as specific prediction data; first prediction benefit data for the target object is determined based on the particular prediction data.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a data processing method and apparatus, an electronic device, and a readable storage medium.
Background
In the historical investment data analysis, the problems of inaccurate analysis model, large calculation amount, inaccurate prediction data and low utilization efficiency of an investment database exist.
Disclosure of Invention
In order to solve the problems in the related art, embodiments of the present disclosure provide a data processing method, an apparatus, an electronic device, and a readable storage medium.
In a first aspect, an embodiment of the present disclosure provides a data processing method, including:
acquiring historical characteristic data of a plurality of characteristics of a target object;
inputting historical feature data of each feature into a first prediction model and a second prediction model respectively, and determining a target interval of the feature according to a result of prediction based on the historical feature data of the feature by using the first prediction model and a result of prediction based on the historical feature data of the feature by using the second prediction model, wherein in the target interval, the result of prediction based on the historical feature data of the feature by using the first prediction model is better than the result of prediction based on the historical feature data of the feature by using the second prediction model;
acquiring current feature data of the plurality of features of the target object;
inputting feature data in a target interval of corresponding features in the current feature data into the first prediction model, and calculating to obtain first prediction data of the corresponding features as specific prediction data; taking the default prediction data as the specific prediction data according to the feature data which is not located in the target interval of the corresponding feature in the current feature data;
and determining first prediction income data of the target object according to the specific prediction data corresponding to the plurality of characteristics.
With reference to the first aspect, in a first implementation manner of the first aspect, the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes:
and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
With reference to the first aspect, in a second implementation manner of the first aspect, the first prediction model uses a gaussian kernel function transformation manner for data input into the first prediction model; and/or
The second prediction model uses a linear addition mode for data input into the first prediction model; and/or
And determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, wherein the first prediction profit data of the target object is obtained by performing linear summation on the corresponding specific prediction data of the plurality of features.
With reference to the first aspect, in a third implementation manner of the first aspect, the feature data includes at least one of: valuation exposure factor, surplus control exposure factor, unexpected surplus exposure factor, fluidity exposure factor, analyst emotion exposure factor, cash flow exposure factor, position exposure factor, beta exposure factor, and nonlinear market value exposure factor.
With reference to the first aspect, in a fourth implementation manner of the first aspect, the present disclosure further includes:
calculating second predicted revenue data for the target object using a second prediction model based on current feature data for the plurality of features of the target object;
and acquiring actual income data of the target object.
With reference to the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the present disclosure further includes:
calculating a first correlation value between the first income data of the target object and the actual income data of the target object;
calculating a second correlation value between the second revenue data of the target object and the actual revenue data of the target object;
comparing the first correlation value and the second correlation value.
With reference to the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect,
the first correlation value comprises a spearman correlation value; and/or
The second correlation value comprises a spearman correlation value.
In a second aspect, an embodiment of the present disclosure provides a data processing apparatus, including:
a historical feature data acquisition module configured to acquire historical feature data of a plurality of features of a target object;
a target section determination module configured to input, for each feature, historical feature data of the feature into a first prediction model and a second prediction model, respectively, and determine a target section of the feature from a result of prediction based on the historical feature data of the feature using the first prediction model and a result of prediction based on the historical feature data of the feature using the second prediction model, wherein the result of prediction based on the historical feature data of the feature using the first prediction model is better than the result of prediction based on the historical feature data of the feature using the second prediction model in the target section;
a current feature data acquisition module configured to acquire current feature data of the plurality of features of the target object;
the specific prediction data calculation module is configured to input feature data, located in a target interval of corresponding features, in current feature data into the first prediction model according to the feature data, and calculate first prediction data of the corresponding features to obtain specific prediction data; taking the default prediction data as the specific prediction data according to the feature data which is not located in the target interval of the corresponding feature in the current feature data;
a first predicted benefit data determination module configured to determine first predicted benefit data for the target object based on respective particular prediction data for the plurality of features.
With reference to the second aspect, in a first implementation manner of the second aspect, the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes:
and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
With reference to the second aspect, in a second implementation manner of the second aspect, the first prediction model uses a gaussian kernel function transformation manner for data input into the first prediction model; and/or
The second prediction model uses a linear addition mode for data input into the first prediction model; and/or
And determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, wherein the first prediction profit data of the target object is obtained by performing linear summation on the corresponding specific prediction data of the plurality of features.
With reference to the second aspect, in a third implementation manner of the second aspect, the feature data includes at least one of: valuation exposure factor, surplus control exposure factor, unexpected surplus exposure factor, fluidity exposure factor, analyst emotion exposure factor, cash flow exposure factor, position exposure factor, beta exposure factor, and nonlinear market value exposure factor.
With reference to the second aspect, in a fourth implementation manner of the second aspect, the present disclosure further includes:
a second predicted revenue data calculation module configured to calculate second predicted revenue data for the target object using a second prediction model from current feature data of the plurality of features of the target object;
an actual revenue data acquisition module configured to acquire actual revenue data of the target object.
With reference to the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect, the present disclosure further includes:
a first correlation value calculation module configured to calculate a first correlation value between first revenue data of the target object and actual revenue data of the target object;
a second correlation value calculation module configured to calculate a second correlation value between second revenue data of the target object and actual revenue data of the target object;
a correlation value comparison module configured to compare the first correlation value and the second correlation value.
With reference to the fifth implementation manner of the second aspect, in a sixth implementation manner of the second aspect,
the first correlation value comprises a spearman correlation value; and/or
The second correlation value comprises a spearman correlation value.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor; wherein the content of the first and second substances,
the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement the method according to any one of the first aspect, the first implementation manner to the fifth implementation manner of the first aspect.
In a sixth aspect, an embodiment of the present disclosure provides a readable storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the method according to any one of the first aspect, the first implementation manner to the fifth implementation manner of the first aspect.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
according to the technical scheme provided by the embodiment of the disclosure, historical characteristic data of a plurality of characteristics of a target object is obtained; inputting historical feature data of each feature into a first prediction model and a second prediction model respectively, and determining a target interval of the feature according to a result of prediction based on the historical feature data of the feature by using the first prediction model and a result of prediction based on the historical feature data of the feature by using the second prediction model, wherein in the target interval, the result of prediction based on the historical feature data of the feature by using the first prediction model is better than the result of prediction based on the historical feature data of the feature by using the second prediction model; acquiring current feature data of the plurality of features of the target object; inputting feature data in a target interval of corresponding features in the current feature data into the first prediction model, and calculating to obtain first prediction data of the corresponding features as specific prediction data; taking the default prediction data as the specific prediction data according to the feature data which is not located in the target interval of the corresponding feature in the current feature data; and determining first prediction income data of the target object according to the corresponding specific prediction data of the plurality of characteristics, so that the accuracy of an analysis model is improved, the operation complexity is reduced, the accuracy of the prediction data is improved, and the use efficiency of an investment database is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. The following is a description of the drawings.
Fig. 1 shows a flow diagram of a data processing method according to an embodiment of the present disclosure.
Fig. 2 shows a flow diagram of a data processing method according to another embodiment of the present disclosure.
Fig. 3 shows a flow chart of a data processing method according to yet another embodiment of the present disclosure.
Fig. 4a shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
Fig. 4b shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
Fig. 4c shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
Fig. 4d shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
Fig. 5 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure.
Fig. 6 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
FIG. 7 is a schematic block diagram of a computer system suitable for use in implementing a data processing method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of labels, numbers, steps, actions, components, parts, or combinations thereof disclosed in the present specification, and are not intended to preclude the possibility that one or more other labels, numbers, steps, actions, components, parts, or combinations thereof are present or added.
It should be further noted that the embodiments and labels in the embodiments of the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the process of establishing an analysis model for historical data, such as historical investment target data, for analysis and forecasting profits, the traditional model has inaccurate calculation of the benchmark price of the investment target and forecasting of the investment profits, the established model is inaccurate, the calculation complexity is high, and the utilization efficiency of an investment database is low.
In order to solve the above problem, the present disclosure provides a data processing method, an apparatus, an electronic device, and a readable storage medium.
Fig. 1 shows a flow diagram of a data processing method according to an embodiment of the present disclosure.
As shown in fig. 1, the data processing method includes: steps S101, S102, S103, S104, S105.
In step S101, historical feature data of a plurality of features of the target object is acquired.
In step S102, for each feature, the historical feature data of the feature is input into a first prediction model and a second prediction model, and a target section of the feature is determined based on a result of prediction based on the historical feature data of the feature using the first prediction model and a result of prediction based on the historical feature data of the feature using the second prediction model, wherein in the target section, the result of prediction based on the historical feature data of the feature using the first prediction model is better than the result of prediction based on the historical feature data of the feature using the second prediction model.
In step S103, current feature data of the plurality of features of the target object is acquired.
In step S104, feature data in a target interval of a corresponding feature in current feature data is input to the first prediction model, and first prediction data of the corresponding feature is calculated to be used as specific prediction data; and taking the default prediction data as the specific prediction data of the corresponding characteristic according to the characteristic data which is not positioned in the target interval of the corresponding characteristic in the current characteristic data.
In step S105, first prediction benefit data of the target object is determined according to the respective specific prediction data of the plurality of features.
In one embodiment of the present disclosure, in data processing, such as processing of investment data, the target object may be an investment target for stocks, funds, or the like. Historical feature data of a plurality of features of an investment target, such as stock a, may be obtained in an investment database, such as historical feature data of valuation exposure factors, surplus control exposure factors, unexpected surplus exposure factors, liquidity exposure factors, analyst emotional exposure factors, cash flow exposure factors, position exposure factors, beta exposure factors, and non-linear market value exposure factors.
In one embodiment of the present disclosure, for each exposure factor, a target interval range for the exposure factor may be determined. Within the target interval, the result of prediction using the first prediction model is better than the result of prediction using the second prediction model. And when the target interval range of each exposure factor is determined, performing neutralization treatment on all other exposure factors, for example, running along the B index without influencing the income of the A stock. The first predictive model may be an analytical model of the exposure factor by means of a kernel transform, for example a gaussian kernel transform. The second predictive model may be an analytical model of a conventional linear summation approach.
In one embodiment of the present disclosure, the target interval range corresponding to each exposure factor may be calculated separately for each exposure factor.
In one embodiment of the present disclosure, a plurality of current exposure factors for stock a, such as exposure factor for phase T, may be obtained in the investment database. For each current exposure factor, when the value of the current exposure factor is in the corresponding target interval range, the prediction gain obtained by Gaussian kernel transformation is used as the prediction gain of the current exposure factor; and when the value of the current factor is not in the corresponding target interval range, using the default prediction gain of the current factor as the prediction gain of the current factor. The default predicted gain for the current exposure factor may be the gain resulting from neutralizing the current exposure factor. The current exposure factor neutralization process may be to make the profit of the current exposure factor follow the B-index operation, for example, without affecting the profit of the A stock
In one embodiment of the present disclosure, after calculating the predicted revenue for each current exposure factor, the predicted revenue for all current exposure factors is summed to obtain the predicted revenue for stock A, such as the predicted revenue for stage T + 1.
In one embodiment of the present disclosure, the default prediction data may be a prediction gain of the exposure factor obtained by neutralizing the exposure factor when the exposure factor is not located in the target interval of the corresponding feature.
According to the embodiment of the disclosure, historical feature data of a plurality of features of a target object is acquired; inputting historical feature data of each feature into a first prediction model and a second prediction model respectively, and determining a target interval of the feature according to a result of prediction based on the historical feature data of the feature by using the first prediction model and a result of prediction based on the historical feature data of the feature by using the second prediction model, wherein in the target interval, the result of prediction based on the historical feature data of the feature by using the first prediction model is better than the result of prediction based on the historical feature data of the feature by using the second prediction model; acquiring current feature data of the plurality of features of the target object; inputting feature data in a target interval of corresponding features in the current feature data into the first prediction model, and calculating to obtain first prediction data of the corresponding features as specific prediction data; taking the default prediction data as the specific prediction data according to the feature data which is not located in the target interval of the corresponding feature in the current feature data; and determining first prediction income data of the target object according to the corresponding specific prediction data of the plurality of characteristics, so that the accuracy of an analysis model is improved, the operation complexity is reduced, and the accuracy of the prediction data is improved.
According to an embodiment of the present disclosure, the determining, for each feature, a target section of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes: and neutralizing other characteristics except the specific characteristics in the plurality of characteristics, and determining the target interval of the characteristics according to the result of prediction based on the historical characteristic data of the characteristics by using a first prediction model and the result of prediction based on the historical characteristic data of the characteristics by using a second prediction model, so that when the target interval of each exposure factor is determined, the influence of other exposure factors is shielded, the calculation complexity is reduced, and the use efficiency of an investment database is improved.
According to the embodiment of the present disclosure, the first prediction model uses a gaussian kernel function transformation method for data input to the first prediction model; and/or the second predictive model uses a linear summation approach for data input to the second predictive model; and/or determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, including performing linear summation on the corresponding specific prediction data of the plurality of features to obtain the first prediction profit data of the target object, so that a Gaussian kernel transformation mode is accurately compared with a traditional linear summation mode, the accuracy of an analysis model is improved, the operation complexity is reduced, and the accuracy of the prediction data is improved.
According to an embodiment of the present disclosure, the feature data comprises at least one of: the method comprises the steps of estimating exposure factors, surplus control exposure factors, unexpected surplus exposure factors, liquidity exposure factors, analyst emotion exposure factors, cash flow exposure factors, position exposure factors, beta exposure factors and nonlinear market value exposure factors, so that financial elements and market volatility elements of investment targets are comprehensively considered, a more accurate analysis model is established, the accuracy of prediction data is improved, redundancy is reduced by reducing the correlation of different exposure factors as much as possible, the calculation complexity is reduced, and the use efficiency of an investment database is improved.
In one embodiment of the present disclosure, the exposure factor may be a combination of a plurality of sub-exposure factors. For example, the valuation exposure factor may be a combination of a market profitability factor, a net market rate factor, and a market sales rate factor. It will be understood by those of ordinary skill in the art that the exposure factors and sub-exposure factors may not be limited to the above listed exposure factors, and the present disclosure will not be described in detail herein.
Fig. 2 shows a flow diagram of a data processing method according to another embodiment of the present disclosure.
As shown in fig. 2, the data processing method includes steps S201 and S202 in addition to steps S101, S102, S103, S104, and S105 which are the same as those in fig. 1.
In step S201, second prediction benefit data of the target object is calculated using a second prediction model according to current feature data of the plurality of features of the target object.
In step S202, actual profit data of the target object is acquired.
In one embodiment of the present disclosure, the predicted profit of the A stock of the T +1 th period can be predicted by means of linear addition.
In one embodiment of the present disclosure, the real profit of the A stock at stage T +1 may be obtained.
According to an embodiment of the present disclosure, calculating second prediction profit data of the target object by using a second prediction model according to current feature data of the plurality of features of the target object; and acquiring actual income data of the target object, and comparing the income predicted by a Gaussian kernel function mode and a linear addition mode with the real income.
Fig. 3 shows a flow chart of a data processing method according to yet another embodiment of the present disclosure.
As shown in fig. 3, the data processing method includes steps S301, S302, S303, in addition to steps S101, S102, S103, S104, S105, S201, S202 which are the same as those in fig. 2.
In step S301, a first correlation value between the first predicted revenue data of the target object and the actual revenue data of the target object is calculated.
In step S302, a second correlation value between the second predicted revenue data of the target subject and the actual revenue data of the target subject is calculated.
In step S303, the first correlation value and the second correlation value are compared.
In one embodiment of the disclosure, a first correlation value between the T +1 phase return and the T +1 phase real return predicted by the A stock Gaussian kernel mode and a second correlation value between the T +1 phase return and the T +1 phase real return predicted by the A stock linear addition mode can be calculated. By comparing the first correlation value with the second correlation value, and the first correlation value is higher than the second correlation value, the fact that the income of the A stock T +1 period predicted and calculated in the Gaussian kernel function mode is more consistent with the actual income is confirmed, and the prediction accuracy is improved.
According to the embodiment of the disclosure, a first correlation value between the first income data of the target object and the actual income data of the target object is calculated; calculating a second correlation value between the second revenue data of the target object and the actual revenue data of the target object; and comparing the first correlation value with the second correlation value, thereby improving the accuracy of the analysis model, reducing the operation complexity, improving the accuracy of the prediction data and improving the use efficiency of the investment database.
According to an embodiment of the present disclosure, the first correlation value comprises a spearman correlation value; and/or the second correlation value comprises a spearman correlation value, thereby confirming the accuracy of the prediction data in a simpler correlation value calculation manner. The first correlation value and/or the second correlation value may also be correlation values calculated in other manners, which is not described in detail herein.
In an embodiment of the present disclosure, the overall processing method of the data processing manner is
Wherein, E (r)s,T) Is the expected profit of stock A in stage T +1, i is the exposure factor index value, j is the exposure of stock A on factor i, Pi,j,TExpected yield at stage T +1 for the i exposure factor by way of gaussian kernel processing.
Fig. 4a shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
As shown in fig. 4a, when the historical data in the first database is analyzed, when exposure factors other than the cash flow exposure factor are all neutralized and the cash flow exposure factor takes a different value, the a stock predicts earnings. It can be seen that there is not a linear relationship between cash flow exposure factor and A stock predicted revenue.
In one embodiment of the present disclosure, the target interval for estimating the exposure factor is 80-95.
Fig. 4b shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
As shown in fig. 4b, when the estimated exposure factor takes a value of 85, the gaussian kernel exposure factor gain is higher than that of the conventional linear summation mode for most of the time.
Fig. 4c shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
As shown in fig. 4c, when the estimated exposure factor is 95, the gaussian kernel exposure factor gain is higher than that of the conventional linear summation mode for most of the time.
One of ordinary skill in the art will recognize that the target interval for estimating an exposure factor may be other intervals, with other exposure factors having corresponding respective target intervals. The present disclosure is not intended to be limiting.
Fig. 4d shows an exemplary schematic diagram of an implementation scenario of a data processing method according to an embodiment of the present disclosure.
As shown in FIG. 4d, the Gaussian kernel exposure factor correlation value is higher than the conventional correlation value, i.e., the first correlation value between the T +1 phase income predicted by the Gaussian kernel method of A stocks and the T +1 phase real income is higher than the second correlation value between the T +1 phase income predicted by the linear summation method of A stocks and the T +1 phase real income. It can be confirmed from fig. 4d that the calculated income of the stock a in the T +1 phase predicted by the gaussian kernel function method better conforms to the actual income, and the accuracy of prediction is improved.
In an embodiment of the present disclosure, the target object in the data processing method may also be an investment target of fund, futures, and the like, and the exposure factor may also be an exposure factor related to the investment target of fund, futures, and the like, which is not limited in this disclosure.
In an embodiment of the disclosure, by using a gaussian function exposure factor, pricing of an investment target can be more accurate, calculation complexity and use complexity are reduced, use efficiency of an investment database is improved, and convenience of an operator in recommending users and constructing investment combinations is improved.
Fig. 5 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 5, the data processing apparatus 500 includes: a historical feature data obtaining module 501, a target interval determining module 502, a current feature data obtaining module 503, a specific prediction data calculating module 504, and a first prediction profit data determining module 505.
The historical feature data acquisition module 501 is configured to acquire historical feature data of a plurality of features of a target object.
The target section determination module 502 is configured to input, for each feature, the historical feature data of the feature into a first prediction model and a second prediction model, respectively, and determine a target section of the feature in which the result of prediction based on the historical feature data of the feature using the first prediction model is better than the result of prediction based on the historical feature data of the feature using the second prediction model, according to the result of prediction based on the historical feature data of the feature using the first prediction model and the result of prediction based on the historical feature data of the feature using the second prediction model.
The current feature data acquisition module 503 is configured to acquire current feature data of the plurality of features of the target object.
The specific prediction data calculation module 504 is configured to input feature data, which is located in a target interval of a corresponding feature, in current feature data into the first prediction model, and calculate first prediction data of the corresponding feature as specific prediction data; and taking the default prediction data as the specific prediction data of the corresponding characteristic according to the characteristic data which is not positioned in the target interval of the corresponding characteristic in the current characteristic data.
The first predicted benefit data determination module 505 is configured to determine first predicted benefit data for the target object based on respective particular prediction data for the plurality of features.
In one embodiment of the present disclosure, the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes: and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
In one embodiment of the present disclosure, the first prediction model uses a gaussian kernel function transformation manner for data input to the first prediction model; and/or the second predictive model uses a linear summation approach for the data input to the first predictive model.
In one embodiment of the disclosure, the feature data comprises at least one of: valuation exposure factor, surplus control exposure factor, unexpected surplus exposure factor, fluidity exposure factor, analyst emotion exposure factor, cash flow exposure factor, position exposure factor, beta exposure factor, and nonlinear market value exposure factor.
In one embodiment of the present disclosure, the data processing apparatus further includes:
a second predicted revenue data calculation module configured to calculate second predicted revenue data for the target object using a second prediction model from current feature data of the plurality of features of the target object;
an actual revenue data acquisition module configured to acquire actual revenue data of the target object.
In one embodiment of the present disclosure, the data processing apparatus further includes:
a first correlation value calculation module configured to calculate a first correlation value between first benefit data of the target object and an actual result of the target object;
a second correlation value calculation module configured to calculate a second correlation value between second profit data of the target object and an actual result of the target object;
a correlation value comparison module configured to compare the first correlation value and the second correlation value.
In one embodiment of the present disclosure, the first correlation value comprises a spearman correlation value; and/or the second correlation value comprises a spearman correlation value.
Fig. 6 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
The embodiment of the present disclosure also provides an electronic device, as shown in fig. 6, the electronic device 600 includes a processor 601 and a memory 602; wherein the memory 602 stores instructions executable by the at least one processor 601, the instructions being executable by the at least one processor 601 to implement the steps of:
acquiring historical characteristic data of a plurality of characteristics of a target object;
inputting historical feature data of each feature into a first prediction model and a second prediction model respectively, and determining a target interval of the feature according to a result of prediction based on the historical feature data of the feature by using the first prediction model and a result of prediction based on the historical feature data of the feature by using the second prediction model, wherein in the target interval, the result of prediction based on the historical feature data of the feature by using the first prediction model is better than the result of prediction based on the historical feature data of the feature by using the second prediction model;
acquiring current feature data of the plurality of features of the target object;
inputting feature data in a target interval of corresponding features in the current feature data into the first prediction model, and calculating to obtain first prediction data of the corresponding features as specific prediction data; regarding feature data which is not located in a target interval of the corresponding feature in the current feature data, taking default prediction data as the specific prediction data;
determining first predicted revenue data for the target object based on the respective particular prediction data for the plurality of features.
In one embodiment of the present disclosure, the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes:
and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
In one embodiment of the present disclosure, the first prediction model uses a gaussian kernel function transformation manner for data input to the first prediction model; and/or
The second prediction model uses a linear addition mode for data input into the first prediction model; and/or
And determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, wherein the first prediction profit data of the target object is obtained by performing linear summation on the corresponding specific prediction data of the plurality of features.
In one embodiment of the disclosure, the feature data comprises at least one of: valuation exposure factor, surplus control exposure factor, unexpected surplus exposure factor, fluidity exposure factor, analyst emotion exposure factor, cash flow exposure factor, position exposure factor, beta exposure factor, and nonlinear market value exposure factor.
In one embodiment of the disclosure, the instructions are further executable by the at least one processor 601 to implement the steps of:
calculating second predicted revenue data for the target object using a second prediction model based on current feature data for the plurality of features of the target object;
and acquiring actual income data of the target object.
In one embodiment of the disclosure, the instructions are further executable by the at least one processor 601 to implement the steps of:
calculating a first correlation value between the first profit data of the target object and an actual result of the target object;
calculating a second correlation value between second profit data of the target object and an actual result of the target object;
comparing the first correlation value and the second correlation value.
In one embodiment of the present disclosure, the first correlation value comprises a spearman correlation value; and/or
The second correlation value comprises a spearman correlation value.
FIG. 7 is a schematic block diagram of a computer system suitable for use in implementing a data processing method according to an embodiment of the present disclosure.
As shown in fig. 7, the computer system 700 includes a processing unit 701 that can execute various processes in the embodiments shown in the above-described figures according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data necessary for the operation of the system 700 are also stored. The processing unit 701, the ROM702, and the RAM703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary. The processing unit 701 may be implemented as a CPU, a GPU, a TPU, an FPGA, an NPU, or other processing units.
In particular, according to embodiments of the present disclosure, the methods described above with reference to the figures may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program comprising program code for performing the methods of the figures. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the node in the above embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (16)
1. A method of data processing, comprising:
acquiring historical characteristic data of a plurality of characteristics of a target object;
inputting historical feature data of each feature into a first prediction model and a second prediction model respectively, and determining a target interval of the feature according to a result of prediction based on the historical feature data of the feature by using the first prediction model and a result of prediction based on the historical feature data of the feature by using the second prediction model, wherein in the target interval, the result of prediction based on the historical feature data of the feature by using the first prediction model is better than the result of prediction based on the historical feature data of the feature by using the second prediction model;
acquiring current feature data of the plurality of features of the target object;
inputting feature data in a target interval of corresponding features in current feature data into the first prediction model, and calculating to obtain first prediction data of the corresponding features as specific prediction data; taking default prediction data as specific prediction data of the corresponding features according to feature data which are not located in the target interval of the corresponding features in the current feature data;
determining first predicted revenue data for the target object based on the respective particular prediction data for the plurality of features.
2. The method of claim 1,
the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes:
and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
3. The method of claim 1,
the first prediction model uses a Gaussian kernel function transformation mode aiming at data input into the first prediction model; and/or
The second prediction model uses a linear addition mode for data input into the second prediction model; and/or
And determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, wherein the first prediction profit data of the target object is obtained by performing linear summation on the corresponding specific prediction data of the plurality of features.
4. The method of claim 1,
the characteristic data comprises at least one of: valuation exposure factor, surplus control exposure factor, unexpected surplus exposure factor, fluidity exposure factor, analyst emotion exposure factor, cash flow exposure factor, position exposure factor, beta exposure factor, and nonlinear market value exposure factor.
5. The method of claim 1, further comprising:
calculating second predicted revenue data for the target object using a second prediction model based on current feature data for the plurality of features of the target object;
and acquiring actual income data of the target object.
6. The method of claim 5, further comprising:
calculating a first correlation value between the first predicted revenue data of the target object and the actual revenue data of the target object;
calculating a second correlation value between second predicted revenue data of the target object and actual revenue data of the target object;
comparing the first correlation value and the second correlation value.
7. The method of claim 6,
the first correlation value comprises a spearman correlation value; and/or
The second correlation value comprises a spearman correlation value.
8. A data processing apparatus comprising:
a historical feature data acquisition module configured to acquire historical feature data of a plurality of features of a target object;
a target section determination module configured to input, for each feature, historical feature data of the feature into a first prediction model and a second prediction model, respectively, and determine a target section of the feature from a result of prediction based on the historical feature data of the feature using the first prediction model and a result of prediction based on the historical feature data of the feature using the second prediction model, wherein the result of prediction based on the historical feature data of the feature using the first prediction model is better than the result of prediction based on the historical feature data of the feature using the second prediction model in the target section;
a current feature data acquisition module configured to acquire current feature data of the plurality of features of the target object;
the specific prediction data calculation module is configured to input feature data, located in a target interval of a corresponding feature, in current feature data, to use the first prediction model, and calculate first prediction data of the corresponding feature to serve as specific prediction data; taking default prediction data as specific prediction data of the corresponding features according to feature data which are not located in the target interval of the corresponding features in the current feature data;
a first predicted benefit data determination module configured to determine first predicted benefit data for the target object based on respective particular prediction data for the plurality of features.
9. The apparatus of claim 8,
the determining, for each feature, a target interval of the feature according to a result of prediction based on historical feature data of the feature using a first prediction model and a result of prediction based on historical feature data of the feature using a second prediction model includes:
and neutralizing the other features except the targeted feature among the plurality of features, and determining a target section of the feature according to a result of prediction based on the historical feature data of the feature by using a first prediction model and a result of prediction based on the historical feature data of the feature by using a second prediction model.
10. The apparatus of claim 8,
the first prediction model uses a Gaussian kernel function transformation mode aiming at data input into the first prediction model; and/or
The second prediction model uses a linear addition mode for data input into the second prediction model; and/or
And determining first prediction profit data of the target object according to the corresponding specific prediction data of the plurality of features, wherein the first prediction profit data of the target object is obtained by performing linear summation on the corresponding specific prediction data of the plurality of features.
11. The apparatus of claim 8,
the characteristic data comprises at least one of: the method comprises the following steps of evaluating characteristic data, surplus control exposure factors, unexpected surplus exposure factors, fluidity exposure factors, analyst emotion exposure factors, cash flow exposure factors, position exposure factors, beta exposure factors and nonlinear market value exposure factors.
12. The apparatus of claim 8, further comprising:
a second predicted revenue data calculation module configured to calculate second predicted revenue data for the target object using a second prediction model from current feature data of the plurality of features of the target object;
an actual revenue data acquisition module configured to acquire actual revenue data of the target object.
13. The apparatus of claim 12, further comprising:
a first correlation value calculation module configured to calculate a first correlation value between first predicted revenue data of the target object and actual revenue data of the target object;
a second correlation value calculation module configured to calculate a second correlation value between second predicted revenue data of the target object and actual revenue data of the target object;
a correlation value comparison module configured to compare the first correlation value and the second correlation value.
14. The apparatus of claim 13,
the first correlation value comprises a spearman correlation value; and/or
The second correlation value comprises a spearman correlation value.
15. An electronic device comprising a memory and a processor; wherein the content of the first and second substances,
the memory is to store one or more computer instructions, wherein the one or more computer instructions are to be executed by the processor to implement the method of any one of claims 1-7.
16. A readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011006355.3A CN111932379B (en) | 2020-09-23 | 2020-09-23 | Data processing method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011006355.3A CN111932379B (en) | 2020-09-23 | 2020-09-23 | Data processing method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932379A true CN111932379A (en) | 2020-11-13 |
| CN111932379B CN111932379B (en) | 2021-01-29 |
Family
ID=73334041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011006355.3A Active CN111932379B (en) | 2020-09-23 | 2020-09-23 | Data processing method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932379B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021505A (en) * | 2016-05-23 | 2016-10-12 | 百度在线网络技术（北京）有限公司 | Processing method and apparatus of value parameters of big data factors |
| CN106991506A (en) * | 2017-05-16 | 2017-07-28 | 深圳先进技术研究院 | Intelligent terminal and its stock trend forecasting method based on LSTM |
| CN108596393A (en) * | 2018-04-28 | 2018-09-28 | 国信优易数据有限公司 | A kind of training method and device of Electronic Finance resources model |
| CN109584076A (en) * | 2018-12-06 | 2019-04-05 | 平安科技（深圳）有限公司 | Stock factor income analysis method, apparatus, computer equipment and storage medium |
| CN109584042A (en) * | 2018-10-25 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment obtaining resource return ratio |
| CN109919349A (en) * | 2017-12-12 | 2019-06-21 | 黄浩霆 | Financial Risk Forecast system and method |
| US20190370902A1 (en) * | 2018-05-30 | 2019-12-05 | Shine We Development Inc. | Method for price prediction of financial products based on deep learning model |
| KR20200039037A (en) * | 2018-09-28 | 2020-04-16 | 광운대학교 산학협력단 | Apparatus for predicting stock price using neural network and method thereof |
| CN111489259A (en) * | 2020-04-16 | 2020-08-04 | 江苏知诺智能科技有限公司 | Stock market risk prediction intelligent implementation method based on deep learning |
| CN111563821A (en) * | 2020-05-12 | 2020-08-21 | 电子科技大学 | Financial stock fluctuation prediction method based on quantitative investment of support vector machine |
-
2020
- 2020-09-23 CN CN202011006355.3A patent/CN111932379B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021505A (en) * | 2016-05-23 | 2016-10-12 | 百度在线网络技术（北京）有限公司 | Processing method and apparatus of value parameters of big data factors |
| CN106991506A (en) * | 2017-05-16 | 2017-07-28 | 深圳先进技术研究院 | Intelligent terminal and its stock trend forecasting method based on LSTM |
| CN109919349A (en) * | 2017-12-12 | 2019-06-21 | 黄浩霆 | Financial Risk Forecast system and method |
| CN108596393A (en) * | 2018-04-28 | 2018-09-28 | 国信优易数据有限公司 | A kind of training method and device of Electronic Finance resources model |
| US20190370902A1 (en) * | 2018-05-30 | 2019-12-05 | Shine We Development Inc. | Method for price prediction of financial products based on deep learning model |
| KR20200039037A (en) * | 2018-09-28 | 2020-04-16 | 광운대학교 산학협력단 | Apparatus for predicting stock price using neural network and method thereof |
| CN109584042A (en) * | 2018-10-25 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment obtaining resource return ratio |
| CN109584076A (en) * | 2018-12-06 | 2019-04-05 | 平安科技（深圳）有限公司 | Stock factor income analysis method, apparatus, computer equipment and storage medium |
| CN111489259A (en) * | 2020-04-16 | 2020-08-04 | 江苏知诺智能科技有限公司 | Stock market risk prediction intelligent implementation method based on deep learning |
| CN111563821A (en) * | 2020-05-12 | 2020-08-21 | 电子科技大学 | Financial stock fluctuation prediction method based on quantitative investment of support vector machine |
Non-Patent Citations (2)
| Title |
|---|
| MUSTAFA GOCKEN 等: "Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction", 《EXPERT SYSTEMS WITH APPLICATIONS》 * |
| 高雯: "基于支持向量机参数优化算法的股票智能投顾策略研究", 《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932379B (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Warusawitharana | Research and development, profits, and firm value: A structural estimation | |
| Tecles et al. | Determinants of bank efficiency: The case of Brazil | |
| Chou et al. | The economic value of volatility timing using a range-based volatility model | |
| Kim et al. | The structural break in the equity premium | |
| JP2002537601A (en) | Computerized system and method for optimizing after-tax revenue including options | |
| WO2001093164A1 (en) | Method and system for analyzing performance of an investment portfolio together with associated risk | |
| Blake et al. | Improved inference in the evaluation of mutual fund performance using panel bootstrap methods | |
| Choi | Market uncertainty and trading volume around earnings announcements | |
| US20160307272A1 (en) | System for reducing computational costs associated with predicting demand for products | |
| US8924275B2 (en) | Hybrid multi-thread and multi-process computer simulation system and method | |
| Pan et al. | Can risk-neutral skewness and kurtosis subsume the information content of historical jumps? | |
| US20090240557A1 (en) | Method, apparatus and computer program product for valuing a technological innovation | |
| CN111932379B (en) | Data processing method and device, electronic equipment and readable storage medium | |
| Bester et al. | Cash mergers and the volatility smile | |
| Indrawan et al. | Factors Affect Tax Avoidance (Empirical Study On The Mining Sector And Component Listed In The Indonesia Stock Exchange Throughout 2016-2019) | |
| Sudarsanam et al. | Rational expectations, analysts' forecasts of earnings and sources of value gains for takeover targets | |
| CN115004182A (en) | Data quantization method based on determined value and estimated value | |
| Ferreira | Forecasting the comovements of spot interest rates | |
| Gallagher et al. | Style factor timing: An application to the portfolio holdings of US fund managers | |
| KR101953771B1 (en) | Method for estimating principal and interest and apparatus for estimating principal and interest | |
| Larasati et al. | Analysis of the Single Index Model and Markowitz in Optimal Portfolio Selection in the Telecommunications Sub-Sector Listed on the Indonesia Stock Exchange for the Period 2020-2022 | |
| Wang et al. | Dividend Forecasting in the Age of Machine Learning | |
| US20170039653A1 (en) | Data analytics and predictive method | |
| Nonejad | Point forecasts of the price of crude oil: an attempt to “beat” the end-of-month random-walk benchmark | |
| Öhrner et al. | Relative or Discounted Cash Flow Valuation on the Fifty Largest US-Based Corporations on Nasdaq: Which of these valuation methods provides the most accurate valuation forecast? |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |