CN117726461A - Financial risk prediction method and system for electronic recruitment assistance - Google Patents
Financial risk prediction method and system for electronic recruitment assistance Download PDFInfo
- Publication number
- CN117726461A CN117726461A CN202410173040.XA CN202410173040A CN117726461A CN 117726461 A CN117726461 A CN 117726461A CN 202410173040 A CN202410173040 A CN 202410173040A CN 117726461 A CN117726461 A CN 117726461A
- Authority
- CN
- China
- Prior art keywords
- data
- risk prediction
- financial risk
- wolf
- gray wolf
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 103
- 230000007115 recruitment Effects 0.000 title claims abstract description 54
- 241000282461 Canis lupus Species 0.000 claims abstract description 214
- 238000005457 optimization Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 59
- 238000004364 calculation method Methods 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 13
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004220 aggregation Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000010998 test method Methods 0.000 claims description 6
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000010832 independent-sample T-test Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013058 risk prediction model Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a financial risk prediction method and a financial risk prediction system for electronic recruitment assistance. The invention relates to the technical field of financial risk prediction, in particular to a financial risk prediction method and a financial risk prediction system for electronic recruitment assistance, wherein the method of combining saliency analysis and standardization processing with oversampling processing is adopted to perform data preprocessing, so that the structure and the content of data are adjusted, and meanwhile, the quality of the data is improved; selecting data characteristics more useful for prediction from the optimized data by adopting a binary gray wolf optimization algorithm to reduce the difficulty of a subsequent learning task and improve the model efficiency; the financial risk prediction is carried out by adopting the method based on the extreme learning prediction model improved by the binary gray wolf optimization algorithm, and the inherent defect of the extreme learning method applied to the financial risk prediction is overcome.
Description
Technical Field
The invention relates to the technical field of financial risk prediction, in particular to a financial risk prediction method and a financial risk prediction system for electronic recruitment assistance.
Background
The electronic bidding purchasing is a manner of purchasing through a network platform, and enterprises may involve a certain financial risk when performing electronic bidding purchasing, so as to assist the enterprises in predicting and managing the financial risk better in the decision process, and an enterprise financial risk prediction system for assisting the electronic bidding purchasing can be developed.
However, in the existing financial risk prediction method, the technical problems that the data types are complex and the contents are various, the difficulty for financial prediction is high, and meanwhile, the data types are unbalanced, so that the prediction accuracy is affected exist; in the existing financial risk prediction method, the model efficiency of the financial risk prediction is low, and meanwhile, the technical problem of high learning difficulty is caused by various and complex features; in the existing financial risk prediction method, the classical extreme learning method has the technical problem that the accuracy of a model is affected due to the fact that the randomness is high, the correlation between data is poor.
Disclosure of Invention
Aiming at the problems that in the existing financial risk prediction method, the data type is complex, the content is various, the difficulty for financial prediction is high, meanwhile, the data type is unbalanced, and the prediction accuracy is influenced, the scheme creatively adopts a method of combining significance analysis and standardization processing with oversampling processing to perform data preprocessing, adjusts the structure and the content of data, and improves the quality of the data; aiming at the technical problems that in the existing financial risk prediction method, the model efficiency of financial risk prediction is low, and meanwhile, the learning difficulty is high due to various and complex features, the scheme creatively adopts a binary gray wolf optimization algorithm to select data features which are more useful for prediction from optimized data so as to reduce the difficulty of subsequent learning tasks and improve the model efficiency; aiming at the technical problems that in the existing financial risk prediction method, the classical extreme learning method has higher randomness and poorer correlation among data, and the model accuracy is affected instead, the scheme creatively adopts the method based on the extreme learning prediction model improved by the binary gray wolf optimization algorithm to carry out financial risk prediction, and preferentially selects more useful features and data through feature extraction, thereby improving the controllable randomness of the prediction result while keeping the randomness, and overcoming the inherent defects of the extreme learning method applied to the financial risk prediction.
The technical scheme adopted by the invention is as follows: the invention provides a financial risk prediction method for electronic recruitment assistance, which comprises the following steps:
step S1: collecting data;
step S2: preprocessing data;
step S3: identifying an optimal financial risk prediction factor;
step S4: financial risk prediction;
step S5: and E, electronic recruitment decision support.
Further, in step S1, the data collection is configured to collect financial data of an enterprise, specifically, financial risk prediction raw data is obtained by collection from historical data of the enterprise, where the financial risk prediction raw data includes historical financial data, supply chain data and market data.
Further, in step S2, the data preprocessing is configured to convert enterprise financial data into a unified data structure for automatic analysis, specifically, perform data preprocessing on the financial risk prediction raw data by using saliency analysis, normalization processing and oversampling processing operations, to obtain optimized financial risk prediction data, and includes the following steps:
step S21: the significance analysis is used for screening data remarkably related to financial risks of enterprises from the data, specifically, aggregating the financial risk prediction original data into two types of aggregation samples, wherein the two types of aggregation samples comprise significant risk warning data and non-significant risk warning data, performing difference identification operation on the two types of aggregation samples in the financial risk prediction original data by adopting a T test method, and classifying the two types of aggregation samples to obtain binary financial risk prediction data;
The T test method specifically refers to an independent sample T test, and is used for comparing whether the two independent samples have significant differences, specifically, calculating a T value by calculating the mean value difference and the standard error of the two samples, and obtaining a comparison result by comparing the T value with a difference critical value;
step S22: the normalization processing is used for performing normalization processing on the original data, converting the original data into a numerical value between 0 and 1, and specifically calculating a positive index normalization numerical value and a negative index normalization numerical value in the binary financial risk prediction data to obtain normalized financial risk prediction data, and comprises the following steps of:
step S221: calculating a standardized value of the positive index, wherein the calculation formula is as follows:
；
wherein P is ij Is a standardized value of the positive index, i is an enterprise index, j is an index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
step S222: calculating a standardized value of the negative index, wherein the calculation formula is as follows:
；
wherein N is ij Is a standardized value of negative index, i is enterprise index, j is index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
step S23: the oversampling process is used for solving the influence of unbalanced class on the prediction performance, specifically, the oversampling process is carried out on the standardized financial risk prediction data by adopting a random linear interpolation method to obtain optimized financial risk prediction data, and the method comprises the following steps:
Step S231: the number of the synthesized samples is calculated, and the calculation formula is as follows:
N t =N 0 +N 1 ；
wherein N is t Is the number of synthesized samples, N 0 Is a small number of samples, N 1 Is the number of samples, where N 0 And N 1 Satisfy N 0 >>N 1 ；
Step S232: the Euclidean distance between any two few samples is calculated, and the calculation formula is as follows:
；
in the method, in the process of the invention,is the euclidean distance between two minority samples, < >>Is a few samples->Index data vector,/-, of (2)>Is a few samples->Index data vector,/-, of (2)>Is the first few sample index,/->Is the second few sample index, q is the total index data number, k is the index data index,/>Is a few samples->Data with index k ++>Is a few samples->Data with index k;
step S233: obtaining a few samples, and obtaining the few samples by calculating the number of the synthesized samples and calculating the Euclidean distance between any two few samples;
step S234: generating a virtual minority group sample, specifically generating a virtual minority group sample according to the minority sample;
step S235: synthetic samples, in particular synthetic N t A sample number;
step S236: iterative generation for balancing the number of minority samples and majority samples, in particular repeating steps S233 and S234 until the number of minority samples is enlarged to N 0 And the data balance is achieved with the number of most samples, so that the optimized financial risk prediction data is obtained.
Further, in step S3, the identifying of the optimal financial risk predictor is used for selecting, through feature selection, data features more useful for prediction from the optimized data to reduce the difficulty of the subsequent learning task and improve the model efficiency, specifically, adopting a binary gray wolf optimization algorithm, and identifying the optimal financial risk predictor according to the optimized financial risk prediction data to obtain the optimized prediction features;
the binary wolf optimization algorithm comprises a wolf algorithm basic model and a crossover operator;
the gray wolf algorithm basic model is used for representing a basic gray wolf algorithm to solve a problem to be solved, and the problem to be solved specifically refers to an optimal solution problem of a financial risk prediction factor;
the crossing operator is used for optimizing the gray wolf algorithm basic model, and specifically, optimizing the gray wolf algorithm basic model by calculating various factors;
the step of adopting a binary gray wolf optimization algorithm to identify the optimal financial risk prediction factor according to the optimal financial risk prediction data to obtain the optimal prediction characteristic comprises the following steps:
step S31: constructing a gray wolf algorithm basic model, wherein the calculation formula is as follows:
X(t+1)=X p (t)-A·D；
Wherein X () is a gray wolf position calculation function for representing a gray wolf algorithm basic model, the gray wolf position is used for representing a solution of a problem to be solved, specifically a solution of a financial risk prediction factor, t is the iteration number, X (t+1) is the gray wolf position at the t-th iteration, and X p () The method comprises the steps that the method is a function for calculating the position of a prey, the position of the prey is used for expressing the optimal solution of a problem to be solved, and particularly the optimal solution of a financial risk prediction factor, A is a step length vector for updating the position of the wealth, and D is a distance vector between the wealth and the position of the prey;
step S32: calculating a continuous value step comprising the steps of:
step S321: calculating the continuous value step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 1 Is the continuous value step of the first wolf, A is the position update step vector of the wolf, D 1 Is the distance vector of the first gray wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S322: calculating the continuous value step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 2 Is the continuous value step of the second wolf, A is the position update step vector of the wolf, D 2 Is the distance vector of the second wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
Step S322: calculating the continuous value step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 3 Is the continuous value step of the third wolf, A is the position update step vector of the wolf, D 3 Is the distance vector of the third wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S33: calculating a binary step size, comprising the following steps:
step S331: calculating the binary step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 1 Is the binary step length of the first gray wolf, ctap 1 Is the continuous value step length of the first gray wolf, R 1 Is a first wolf binary step random parameter threshold, and the value range of the first wolf binary step random parameter threshold is [0,1 ]]；
Step S332: calculating the binary step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 2 Is the binary step length of the second gray wolf, ctap 2 Is the continuous value step length of the second gray wolf, R 2 Is a second gray wolf binary step random parameter threshold value, and the value range of the second gray wolf binary step random parameter threshold value is [0,1 ]]；
Step S333: calculating the binary step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 3 Is the binary step length of the third gray wolf, ctap 3 Is the continuous value step of the third wolf Long, R 3 Is a third wolf binary step random parameter threshold, and the value range of the third wolf binary step random parameter threshold is [0,1 ]]；
Step S34: calculating a crossover operator discrimination vector, comprising the steps of:
step S341: calculating a first gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the first gray wolf crossing operator, X 1 Is the position of the first wolf, bstep 1 Is the binary step length of the first gray wolf;
step S342: calculating a second gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the second gray wolf crossing operator, X 2 Is the position of the second wolf, bstep 2 Is the binary step length of the second gray wolf;
step S343: calculating a third gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the third gray wolf crossing operator, X 3 Is the position of the third wolf, bstep 3 Is the binary step length of the third gray wolf;
step S35: constructing a crossing operator for updating the position of the gray wolf, specifically constructing the crossing operator through the step length of the calculated continuous value and the step length of the calculated binary value, wherein the calculating formula of the crossing operator is as follows:
；
in the method, in the process of the invention,is to update the gray wolf position calculation function, t is the number of iterations, +. >Is the first gray wolf crossing operator discrimination vector,>is the second gray wolf crossing operator discrimination vector,>is the discrimination vector of a third gray wolf crossing operator, R 4 Is a crossover operator random parameter threshold;
step S36: optimizing the gray wolf algorithm, and optimizing the basic Model of the gray wolf algorithm by constructing a crossover operator to obtain a Model of a binary gray wolf optimization algorithm W ；
Step S37: identification of optimal financial risk prediction factors, in particular to Model adopting the binary gray wolf optimization algorithm Model W And carrying out optimal prediction factor identification operation on the optimal financial risk prediction data to obtain optimal prediction characteristics.
Further, in step S4, the financial risk prediction is used for performing financial risk prediction, specifically, a method based on an extreme learning prediction model improved by a binary gray wolf optimization algorithm is adopted, and prediction is performed according to the optimized financial risk prediction data and in combination with the optimized prediction features, so as to obtain financial risk prediction data;
the extreme learning prediction model comprises a basic model and a binary gray wolf optimization operator;
the basic model is used for performing model training and comprises an input layer, a hidden layer and an output layer;
the binary gray wolf optimizing operator is used for optimizing weight and bias items of a hidden layer of the Model, and specifically adopts the binary gray wolf optimizing algorithm Model in the step S3 W Optimizing input weights and bias terms of hidden layer neurons of the basic model;
the method for adopting the extreme learning prediction model based on the improvement of the binary gray wolf optimization algorithm carries out prediction according to the optimized financial risk prediction data and combines the optimized prediction characteristics to obtain financial risk prediction data, and comprises the following steps:
step S41: constructing an input layer, in particular constructing the input layer for generating random input layer weights;
step S42: constructing a hidden layer, specifically generating a random hidden layer bias item, and constructing the hidden layer by constructing a hidden layer output matrix, wherein the calculation formula of the hidden layer output matrix is as follows:
；
wherein H is the hidden layer output matrix, f () is the activation function, ω is the random input layer weight, L is the hidden layer node number, x is the input samples, N is the total number of input samples of the input layer, b is the random hidden layer bias term, and T is the transpose operator;
step S43: the output layer is constructed, specifically, the output layer is constructed through the input layer weight, the hidden layer bias item, the output function and the activation function, and the calculation formula of the output function is as follows:
；
where y is the value of the output function, h () is the mapping function of the input layer data to the feature space, x is the input sample, o is the input sample index, Is a connection weight matrix of the hidden layer and the output layer;
step S44: a binary gray wolf optimization operator is constructed,in particular to a Model adopting a binary gray wolf optimization algorithm Model in the step S3 W Optimizing input weights and bias terms of hidden layer neurons of the basic model;
step S45: training a risk prediction Model, namely training the Model through the construction input layer, the construction hidden layer, the construction output layer and the construction binary gray wolf optimizing operator to obtain an improved extreme learning prediction Model EL ；
Step S46: financial risk prediction, in particular using the improved extreme learning prediction Model EL And according to the optimized financial risk prediction data, carrying out financial risk prediction by combining the optimized prediction characteristics to obtain financial risk prediction data.
Further, in step S5, the electronic recruitment decision support is configured to provide decision support for electronic bidding purchase according to a financial risk prediction result, specifically, perform electronic recruitment decision support according to the financial risk prediction data, so as to obtain an electronic recruitment planning policy.
The invention provides a financial risk prediction system for electronic recruitment assistance, which comprises a data acquisition module, a data preprocessing module, an optimal financial risk prediction factor identification module, a financial risk prediction module and an electronic recruitment decision support module;
The data acquisition module is used for collecting enterprise financial data, acquiring financial risk prediction original data through data acquisition, and sending the financial risk prediction original data to the data preprocessing module;
the data preprocessing module is used for converting enterprise financial data into a unified data structure which can be automatically analyzed, obtaining optimized financial risk prediction data through data preprocessing, and sending the optimized financial risk prediction data to the optimal financial risk prediction factor identification module and the financial risk prediction module;
the optimal financial risk prediction factor identification module is used for selecting data features which are more useful for prediction from the optimal data through feature selection to reduce the difficulty of subsequent learning tasks and improve model efficiency, identifying the optimal financial risk prediction factors to obtain optimal prediction features, and sending the optimal prediction features to the financial risk prediction module;
the financial risk prediction module is used for performing financial risk prediction, obtaining financial risk prediction data by performing financial risk prediction according to the optimized financial risk prediction data and combining the optimized prediction characteristics, and sending the financial risk prediction data to the electronic recruitment decision support module;
The electronic recruitment decision support module is used for providing decision support for electronic recruitment according to the financial risk prediction result, and obtaining an electronic recruitment planning strategy through the electronic recruitment decision support.
By adopting the scheme, the beneficial effects obtained by the invention are as follows:
(1) Aiming at the technical problems that in the existing financial risk prediction method, the data types are complex and the contents are various, the difficulty for financial prediction is high, meanwhile, the data types are unbalanced, and the prediction accuracy is influenced, the scheme creatively adopts a method of combining significance analysis and standardization processing with oversampling processing to perform data preprocessing, adjusts the structure and the content of the data, and improves the quality of the data;
(2) Aiming at the technical problems that in the existing financial risk prediction method, the model efficiency of financial risk prediction is low, and meanwhile, the learning difficulty is high due to various and complex features, the scheme creatively adopts a binary gray wolf optimization algorithm to select data features which are more useful for prediction from optimized data so as to reduce the difficulty of subsequent learning tasks and improve the model efficiency;
(3) Aiming at the technical problems that in the existing financial risk prediction method, the classical extreme learning method has higher randomness and poorer correlation among data, and the model accuracy is affected instead, the scheme creatively adopts the method based on the extreme learning prediction model improved by the binary gray wolf optimization algorithm to carry out financial risk prediction, and preferentially selects more useful features and data through feature extraction, thereby improving the controllable randomness of the prediction result while keeping the randomness, and overcoming the inherent defects of the extreme learning method applied to the financial risk prediction.
Drawings
FIG. 1 is a schematic flow chart of a financial risk prediction method for electronic recruitment assistance provided by the invention;
FIG. 2 is a schematic diagram of a financial risk prediction system for electronic recruitment assistance provided by the present invention;
FIG. 3 is a flow chart of step S2;
FIG. 4 is a flow chart of step S3;
fig. 5 is a flow chart of step S4.
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "top," "bottom," "inner," "outer," and the like indicate orientation or positional relationships based on those shown in the drawings, merely to facilitate description of the invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
Referring to fig. 1, the present invention provides a financial risk prediction method for electronic recruitment assistance, which includes the following steps:
step S1: collecting data;
step S2: preprocessing data;
step S3: identifying an optimal financial risk prediction factor;
step S4: financial risk prediction;
step S5: and E, electronic recruitment decision support.
In a second embodiment, referring to fig. 1 and fig. 2, in step S1, the data collection is used to collect financial data of an enterprise, specifically, financial risk prediction raw data is obtained from historical data of the enterprise through collection, where the financial risk prediction raw data includes historical financial data, supply chain data and market data.
Referring to fig. 1, 2 and 3, in this embodiment, in step S2, the data preprocessing is used to convert enterprise financial data into a unified data structure for automatic analysis, specifically, performing data preprocessing on the financial risk prediction raw data by using saliency analysis, normalization processing and oversampling processing operations, to obtain optimized financial risk prediction data, and includes the following steps:
step S21: the significance analysis is used for screening data remarkably related to financial risks of enterprises from the data, specifically, aggregating the financial risk prediction original data into two types of aggregation samples, wherein the two types of aggregation samples comprise significant risk warning data and non-significant risk warning data, performing difference identification operation on the two types of aggregation samples in the financial risk prediction original data by adopting a T test method, and classifying the two types of aggregation samples to obtain binary financial risk prediction data;
The T test method specifically refers to an independent sample T test, and is used for comparing whether the two independent samples have significant differences, specifically, calculating a T value by calculating the mean value difference and the standard error of the two samples, and obtaining a comparison result by comparing the T value with a difference critical value;
step S22: the normalization processing is used for performing normalization processing on the original data, converting the original data into a numerical value between 0 and 1, and specifically calculating a positive index normalization numerical value and a negative index normalization numerical value in the binary financial risk prediction data to obtain normalized financial risk prediction data, and comprises the following steps of:
step S221: calculating a standardized value of the positive index, wherein the calculation formula is as follows:
；
wherein P is ij Is a standardized value of the positive index, i is an enterprise index, j is an index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
step S222: calculating a standardized value of the negative index, wherein the calculation formula is as follows:
；
wherein N is ij Is a standardized value of negative index, i is enterprise index, j is index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
step S23: the oversampling process is used for solving the influence of unbalanced class on the prediction performance, specifically, the oversampling process is carried out on the standardized financial risk prediction data by adopting a random linear interpolation method to obtain optimized financial risk prediction data, and the method comprises the following steps:
Step S231: the number of the synthesized samples is calculated, and the calculation formula is as follows:
N t =N 0 +N 1 ；
wherein N is t Is the number of synthesized samples, N 0 Is a small number of samples, N 1 Is the number of samples, where N 0 And N 1 Satisfy N 0 >>N 1 ；
Step S232: the Euclidean distance between any two few samples is calculated, and the calculation formula is as follows:
；
in the method, in the process of the invention,is the euclidean distance between two minority samples, < >>Is a few samples->Index data vector,/-, of (2)>Is a few samples->Index data vector,/-, of (2)>Is the first few sample index,/->Is the second few sample index, q is the total index data number, k is the index data index,/>Is a few samples->Data with index k ++>Is a few samples->Data with index k;
step S233: obtaining a few samples, and obtaining the few samples by calculating the number of the synthesized samples and calculating the Euclidean distance between any two few samples;
step S234: generating a virtual minority group sample, specifically generating a virtual minority group sample according to the minority sample;
step S235: synthetic samples, in particular synthetic N t A sample number;
step S236: iterative generation for making a few samplesAnd the number of the majority samples reach balance, in particular, the steps S233 and S234 are repeated until the number of the minority samples is enlarged to N 0 And the data balance is achieved with the number of most samples, so that the optimized financial risk prediction data is obtained.
By executing the operation, aiming at the technical problems that in the existing financial risk prediction method, the data types are complex and the contents are various, the difficulty for financial prediction is high, meanwhile, the data types are unbalanced, and the prediction accuracy is affected, the scheme creatively adopts a method of combining significance analysis and standardization processing with oversampling processing to perform data preprocessing, adjusts the structure and the content of the data, and improves the quality of the data.
Referring to fig. 1, fig. 2, and fig. 4, in this embodiment, in step S3, the optimal financial risk prediction factor is identified, so that the difficulty of a subsequent learning task is reduced and the model efficiency is improved by selecting data features more useful for prediction from the optimized data through feature selection, specifically, a binary gray wolf optimization algorithm is adopted, and the optimal financial risk prediction factor is identified according to the optimized financial risk prediction data, so as to obtain an optimized prediction feature;
the binary wolf optimization algorithm comprises a wolf algorithm basic model and a crossover operator;
The gray wolf algorithm basic model is used for representing a basic gray wolf algorithm to solve a problem to be solved, and the problem to be solved specifically refers to an optimal solution problem of a financial risk prediction factor;
the crossing operator is used for optimizing the gray wolf algorithm basic model, and specifically, optimizing the gray wolf algorithm basic model by calculating various factors;
the step of adopting a binary gray wolf optimization algorithm to identify the optimal financial risk prediction factor according to the optimal financial risk prediction data to obtain the optimal prediction characteristic comprises the following steps:
step S31: constructing a gray wolf algorithm basic model, wherein the calculation formula is as follows:
X(t+1)=X p (t)-A·D；
where, X () is a gray wolf position calculation function,the method is used for representing a gray wolf algorithm basic model, the gray wolf position is used for representing a solution of a problem to be solved, particularly a solution of a financial risk prediction factor, t is the iteration number, X (t+1) is the gray wolf position at the t-th iteration, and X p () The method comprises the steps that the method is a function for calculating the position of a prey, the position of the prey is used for expressing the optimal solution of a problem to be solved, and particularly the optimal solution of a financial risk prediction factor, A is a step length vector for updating the position of the wealth, and D is a distance vector between the wealth and the position of the prey;
step S32: calculating a continuous value step comprising the steps of:
Step S321: calculating the continuous value step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 1 Is the continuous value step of the first wolf, A is the position update step vector of the wolf, D 1 Is the distance vector of the first gray wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S322: calculating the continuous value step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 2 Is the continuous value step of the second wolf, A is the position update step vector of the wolf, D 2 Is the distance vector of the second wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S322: calculating the continuous value step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 3 Is the continuous value step of the third wolf, A is the position update step vector of the wolf, D 3 Is the distance vector of the third wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S33: calculating a binary step size, comprising the following steps:
step S331: calculating the binary step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 1 Is the binary step length of the first gray wolf, ctap 1 Is the continuous value step length of the first gray wolf, R 1 Is a first wolf binary step random parameter threshold, and the value range of the first wolf binary step random parameter threshold is [0,1 ] ]；
Step S332: calculating the binary step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 2 Is the binary step length of the second gray wolf, ctap 2 Is the continuous value step length of the second gray wolf, R 2 Is a second gray wolf binary step random parameter threshold value, and the value range of the second gray wolf binary step random parameter threshold value is [0,1 ]]；
Step S333: calculating the binary step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 3 Is the binary step length of the third gray wolf, ctap 3 Is the continuous value step length of the third gray wolf, R 3 Is a third wolf binary step random parameter threshold, and the value range of the third wolf binary step random parameter threshold is [0,1 ]]；
Step S34: calculating a crossover operator discrimination vector, comprising the steps of:
step S341: calculating a first gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the first gray wolf crossing operator, X 1 Is the position of the first wolf, bstep 1 Is the binary step length of the first gray wolf;
step S342: calculating a second gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the second gray wolf crossing operator, X 2 Is the position of the second wolf, bstep 2 Is the binary step length of the second gray wolf;
Step S343: calculating a third gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the third gray wolf crossing operator, X 3 Is the position of the third wolf, bstep 3 Is the binary step length of the third gray wolf;
step S35: constructing a crossing operator for updating the position of the gray wolf, specifically constructing the crossing operator through the step length of the calculated continuous value and the step length of the calculated binary value, wherein the calculating formula of the crossing operator is as follows:
；
in the method, in the process of the invention,is to update the gray wolf position calculation function, t is the number of iterations, +.>Is the first gray wolf crossing operator discrimination vector,>is the second gray wolf crossing operator discrimination vector,>is the discrimination vector of a third gray wolf crossing operator, R 4 Is a crossover operator random parameter threshold;
step S36: optimizing the gray wolf algorithm, and optimizing the basic Model of the gray wolf algorithm by constructing a crossover operator to obtain a Model of a binary gray wolf optimization algorithm W ；
Step S37: identification of optimal financial risk prediction factors, in particular to Model adopting the binary gray wolf optimization algorithm Model W And carrying out optimal prediction factor identification operation on the optimal financial risk prediction data to obtain optimal prediction characteristics.
By executing the operation, the model efficiency of the financial risk prediction is lower in the existing financial risk prediction method, and meanwhile, the technical problem of high learning difficulty is caused by various and complex features.
Referring to fig. 1, 2 and 5, in the embodiment, in step S4, the financial risk prediction is used for performing financial risk prediction, specifically, a method based on an extreme learning prediction model improved by a binary gray wolf optimization algorithm is adopted, and prediction is performed according to the optimized financial risk prediction data and in combination with the optimized prediction features to obtain financial risk prediction data;
the extreme learning prediction model comprises a basic model and a binary gray wolf optimization operator;
the basic model is used for performing model training and comprises an input layer, a hidden layer and an output layer;
the binary gray wolfAn optimizing operator for optimizing the weight and bias items of the hidden layer of the Model, specifically, adopting the binary gray wolf optimizing algorithm Model in the step S3 W Optimizing input weights and bias terms of hidden layer neurons of the basic model;
the method for adopting the extreme learning prediction model based on the improvement of the binary gray wolf optimization algorithm carries out prediction according to the optimized financial risk prediction data and combines the optimized prediction characteristics to obtain financial risk prediction data, and comprises the following steps:
step S41: constructing an input layer, in particular constructing the input layer for generating random input layer weights;
Step S42: constructing a hidden layer, specifically generating a random hidden layer bias item, and constructing the hidden layer by constructing a hidden layer output matrix, wherein the calculation formula of the hidden layer output matrix is as follows:
；
wherein H is the hidden layer output matrix, f () is the activation function, ω is the random input layer weight, L is the hidden layer node number, x is the input samples, N is the total number of input samples of the input layer, b is the random hidden layer bias term, and T is the transpose operator;
step S43: the output layer is constructed, specifically, the output layer is constructed through the input layer weight, the hidden layer bias item, the output function and the activation function, and the calculation formula of the output function is as follows:
；
where y is the value of the output function, h () is the mapping function of the input layer data to the feature space, x is the input sample, o is the input sample index,is a connection weight matrix of the hidden layer and the output layer;
step S44: constructing a binary gray wolf optimization operator, specifically adopting the step S3Binary gray wolf optimization algorithm Model W Optimizing input weights and bias terms of hidden layer neurons of the basic model;
step S45: training a risk prediction Model, namely training the Model through the construction input layer, the construction hidden layer, the construction output layer and the construction binary gray wolf optimizing operator to obtain an improved extreme learning prediction Model EL ；
Step S46: financial risk prediction, in particular using the improved extreme learning prediction Model EL And according to the optimized financial risk prediction data, carrying out financial risk prediction by combining the optimized prediction characteristics to obtain financial risk prediction data.
Aiming at the technical problems that in the existing financial risk prediction method, the classical extreme learning method has higher randomness and poorer correlation among data, and the model accuracy is affected instead, the scheme creatively adopts the method based on the extreme learning prediction model improved by the binary gray wolf optimization algorithm to carry out financial risk prediction, and preferentially selects more useful features and data through feature extraction, thereby improving the controllable randomness of the prediction result while keeping the randomness, and overcoming the inherent defects of the extreme learning method applied to the financial risk prediction.
In step S5, the electronic recruitment decision support is used to provide decision support for electronic bidding purchase according to the financial risk prediction result, specifically, electronic recruitment decision support is performed according to the financial risk prediction data, so as to obtain an electronic recruitment planning strategy.
An embodiment seven, referring to fig. 2, based on the foregoing embodiment, the financial risk prediction system for electronic recruitment assistance provided by the present invention includes a data acquisition module, a data preprocessing module, an optimal financial risk prediction factor identification module, a financial risk prediction module, and an electronic recruitment decision support module;
the data acquisition module is used for collecting enterprise financial data, acquiring financial risk prediction original data through data acquisition, and sending the financial risk prediction original data to the data preprocessing module;
the data preprocessing module is used for converting enterprise financial data into a unified data structure which can be automatically analyzed, obtaining optimized financial risk prediction data through data preprocessing, and sending the optimized financial risk prediction data to the optimal financial risk prediction factor identification module and the financial risk prediction module;
the optimal financial risk prediction factor identification module is used for selecting data features which are more useful for prediction from the optimal data through feature selection to reduce the difficulty of subsequent learning tasks and improve model efficiency, identifying the optimal financial risk prediction factors to obtain optimal prediction features, and sending the optimal prediction features to the financial risk prediction module;
The financial risk prediction module is used for performing financial risk prediction, obtaining financial risk prediction data by performing financial risk prediction according to the optimized financial risk prediction data and combining the optimized prediction characteristics, and sending the financial risk prediction data to the electronic recruitment decision support module;
the electronic recruitment decision support module is used for providing decision support for electronic recruitment according to the financial risk prediction result, and obtaining an electronic recruitment planning strategy through the electronic recruitment decision support.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (10)
1. A financial risk prediction method for electronic recruitment assistance is characterized in that: the method comprises the following steps:
step S1: collecting data;
step S2: preprocessing data;
step S3: identifying an optimal financial risk prediction factor;
step S4: financial risk prediction;
step S5: electronic recruitment decision support;
in step S1, acquiring financial risk prediction original data through data acquisition;
In step S2, the data preprocessing is used for converting enterprise financial data into a unified data structure capable of being automatically analyzed, specifically, performing data preprocessing on the financial risk prediction original data by adopting significance analysis, standardization processing and oversampling processing operation, so as to obtain optimized financial risk prediction data;
in step S3, the identifying of the optimal financial risk prediction factor is used for selecting data features more useful for prediction from the optimized data through feature selection to reduce the difficulty of subsequent learning tasks and improve the model efficiency, specifically, a binary gray wolf optimization algorithm is adopted, and the identifying of the optimal financial risk prediction factor is performed according to the optimized financial risk prediction data to obtain the optimized prediction feature;
the binary wolf optimization algorithm comprises a wolf algorithm basic model and a crossover operator;
the gray wolf algorithm basic model is used for representing a basic gray wolf algorithm to solve a problem to be solved, and the problem to be solved specifically refers to an optimal solution problem of a financial risk prediction factor;
the crossing operator is used for optimizing the gray wolf algorithm basic model, and specifically, optimizing the gray wolf algorithm basic model by calculating various factors;
In step S4, the financial risk prediction is used for performing financial risk prediction, specifically, a method based on an extreme learning prediction model improved by a binary gray wolf optimization algorithm is adopted, and prediction is performed according to the optimized financial risk prediction data and in combination with the optimized prediction features to obtain financial risk prediction data;
in step S5, the electronic recruitment decision support is configured to obtain an electronic recruitment planning policy according to the financial risk prediction result.
2. A financial risk prediction method for electronic recruitment assistance according to claim 1, wherein: in step S2, the data preprocessing includes the following steps:
step S21: the significance analysis is used for screening data remarkably related to financial risks of enterprises from the data, specifically, aggregating the financial risk prediction original data into two types of aggregation samples, wherein the two types of aggregation samples comprise significant risk warning data and non-significant risk warning data, performing difference identification operation on the two types of aggregation samples in the financial risk prediction original data by adopting a T test method, and classifying the two types of aggregation samples to obtain binary financial risk prediction data;
The T test method specifically refers to an independent sample T test, and is used for comparing whether the two independent samples have significant differences, specifically, calculating a T value by calculating the mean value difference and the standard error of the two samples, and obtaining a comparison result by comparing the T value with a difference critical value;
step S22: the normalization processing is used for performing normalization processing on the original data, converting the original data into values between 0 and 1, and specifically calculating a positive index normalization value and a negative index normalization value in the binary financial risk prediction data to obtain normalized financial risk prediction data;
step S23: and the oversampling processing is used for solving the influence of the unbalanced class problem on the prediction performance, and particularly, the oversampling processing is carried out on the standardized financial risk prediction data by adopting a random linear interpolation method to obtain the optimized financial risk prediction data.
3. A financial risk prediction method for electronic recruitment assistance according to claim 1, wherein: in step S22, the normalization process specifically includes the following steps:
step S221: calculating a standardized value of the positive index, wherein the calculation formula is as follows:
；
wherein P is ij Is a standardized value of the positive index, i is an enterprise index, j is an index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
step S222: calculating a standardized value of the negative index, wherein the calculation formula is as follows:
；
wherein N is ij Is a standardized value of negative index, i is enterprise index, j is index, V ij Is the value of the j index of the i enterprise, and n is the total number of samples;
in step S23, the oversampling process specifically includes the steps of:
step S231: the number of the synthesized samples is calculated, and the calculation formula is as follows:
N t =N 0 +N 1 ；
wherein N is t Is the number of synthesized samples, N 0 Is a small number of samples, N 1 Is the number of samples, where N 0 And N 1 Satisfy N 0 >>N 1 ；
Step S232: the Euclidean distance between any two few samples is calculated, and the calculation formula is as follows:
；
in the method, in the process of the invention,is the euclidean distance between two minority samples, < >>Is a few samples->Index data vector,/-, of (2)>Is a few samples->Index data vector,/-, of (2)>Is the first few sample index,/->Is the second few sample index, q is the total index data number, k is the index data index,/>Is a few samples->Is the data with the index of k,/>is a few samples->Data with index k;
step S233: obtaining a few samples, and obtaining the few samples by calculating the number of the synthesized samples and calculating the Euclidean distance between any two few samples;
Step S234: generating a virtual minority group sample, specifically generating a virtual minority group sample according to the minority sample;
step S235: synthetic samples, in particular synthetic N t A sample number;
step S236: iterative generation for balancing the number of minority samples and majority samples, in particular repeating steps S233 and S234 until the number of minority samples is enlarged to N 0 And the data balance is achieved with the number of most samples, so that the optimized financial risk prediction data is obtained.
4. A financial risk prediction method for electronic recruitment assistance according to claim 3, wherein: in step S3, the step of identifying the optimal financial risk prediction factor according to the optimal financial risk prediction data by adopting a binary gray wolf optimization algorithm to obtain an optimal prediction feature includes:
step S31: constructing a gray wolf algorithm basic model, wherein the calculation formula is as follows:
X(t+1)=X p (t)-A·D；
wherein X () is a gray wolf position calculation function for representing a gray wolf algorithm basic model, the gray wolf position is used for representing a solution of a problem to be solved, specifically a solution of a financial risk prediction factor, t is the iteration number, X (t+1) is the gray wolf position at the t-th iteration, and X p () Is a function for calculating the position of a prey for expressing the optimal solution of a problem to be solved, particularly the optimal solution of a financial risk prediction factor, A is the step length direction of the position update of the gray wolfThe quantity, D, is the distance vector of the wolf from the prey location;
step S32: calculating a continuous value step comprising the steps of:
step S321: calculating the continuous value step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 1 Is the continuous value step of the first wolf, A is the position update step vector of the wolf, D 1 Is the distance vector of the first gray wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S322: calculating the continuous value step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 2 Is the continuous value step of the second wolf, A is the position update step vector of the wolf, D 2 Is the distance vector of the second wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
step S322: calculating the continuous value step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, ctap 3 Is the continuous value step of the third wolf, A is the position update step vector of the wolf, D 3 Is the distance vector of the third wolf and the position of the prey, exp () is an exponential function based on natural familiar e;
Step S33: calculating a binary step size, comprising the following steps:
step S331: calculating the binary step length of the first gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 1 Is the binary step length of the first gray wolf, ctap 1 Is the continuous value step length of the first gray wolf, R 1 Is a first wolf binary step random parameter threshold, and the value range of the first wolf binary step random parameter threshold is [0,1 ]]；
Step S332: calculating the binary step length of the second gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 2 Is the binary step length of the second gray wolf, ctap 2 Is the continuous value step length of the second gray wolf, R 2 Is a second gray wolf binary step random parameter threshold value, and the value range of the second gray wolf binary step random parameter threshold value is [0,1 ]]；
Step S333: calculating the binary step length of the third gray wolf, wherein the calculation formula is as follows:
；
in the formula, bstep 3 Is the binary step length of the third gray wolf, ctap 3 Is the continuous value step length of the third gray wolf, R 3 Is a third wolf binary step random parameter threshold, and the value range of the third wolf binary step random parameter threshold is [0,1 ]]；
Step S34: calculating a crossover operator discrimination vector, comprising the steps of:
step S341: calculating a first gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
In the method, in the process of the invention,is the judgment of the first gray wolf crossing operatorOther vectors, X 1 Is the position of the first wolf, bstep 1 Is the binary step length of the first gray wolf;
step S342: calculating a second gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the second gray wolf crossing operator, X 2 Is the position of the second wolf, bstep 2 Is the binary step length of the second gray wolf;
step S343: calculating a third gray wolf crossing operator discrimination vector, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,is the discrimination vector of the third gray wolf crossing operator, X 3 Is the position of the third wolf, bstep 3 Is the binary step length of the third gray wolf;
step S35: constructing a crossing operator for updating the position of the gray wolf, specifically constructing the crossing operator through the step length of the calculated continuous value and the step length of the calculated binary value, wherein the calculating formula of the crossing operator is as follows:
；
in the method, in the process of the invention,is to update the gray wolf position calculation function, t is the number of iterations, +.>Is the first gray wolf cross operator discrimination vector,is the second gray wolf crossing operator discrimination vector,>is the discrimination vector of a third gray wolf crossing operator, R 4 Is a crossover operator random parameter threshold;
step S36: optimizing the gray wolf algorithm, and optimizing the basic Model of the gray wolf algorithm by constructing a crossover operator to obtain a Model of a binary gray wolf optimization algorithm W ；
Step S37: identification of optimal financial risk prediction factors, in particular to Model adopting the binary gray wolf optimization algorithm Model W And carrying out optimal prediction factor identification operation on the optimal financial risk prediction data to obtain optimal prediction characteristics.
5. A financial risk prediction method for electronic recruitment assistance according to claim 4, wherein: in step S4, the extreme learning prediction model includes a basic model and a binary gray wolf optimization operator; the basic model is used for performing model training and comprises an input layer, a hidden layer and an output layer;
the binary gray wolf optimizing operator is used for optimizing weight and bias items of a hidden layer of the Model, and specifically adopts the binary gray wolf optimizing algorithm Model in the step S3 W And optimizing the input weight and bias term of hidden layer neurons of the basic model.
6. A financial risk prediction method for electronic recruitment assistance according to claim 5, wherein: in step S4, the method of adopting the extreme learning prediction model improved based on the binary gray wolf optimization algorithm, according to the optimized financial risk prediction data, predicts by combining with the optimized prediction feature, and obtains financial risk prediction data, includes:
Step S41: constructing an input layer, in particular constructing the input layer for generating random input layer weights;
step S42: constructing a hidden layer, specifically generating a random hidden layer bias item, and constructing the hidden layer by constructing a hidden layer output matrix, wherein the calculation formula of the hidden layer output matrix is as follows:
；
wherein H is the hidden layer output matrix, f () is the activation function, ω is the random input layer weight, L is the hidden layer node number, x is the input samples, N is the total number of input samples of the input layer, b is the random hidden layer bias term, and T is the transpose operator;
step S43: the output layer is constructed, specifically, the output layer is constructed through the input layer weight, the hidden layer bias item, the output function and the activation function, and the calculation formula of the output function is as follows:
；
where y is the value of the output function, h () is the mapping function of the input layer data to the feature space, x is the input sample, o is the input sample index,is a connection weight matrix of the hidden layer and the output layer;
step S44: constructing a binary wolf optimization operator, in particular adopting a binary wolf optimization algorithm Model in the step S3 W Optimizing input weights and bias terms of hidden layer neurons of the basic model;
Step S45: training a risk prediction Model, namely training the Model through the construction input layer, the construction hidden layer, the construction output layer and the construction binary gray wolf optimizing operator to obtain an improved extreme learning prediction Model EL ；
Step (a)S46: financial risk prediction, in particular using the improved extreme learning prediction Model EL And according to the optimized financial risk prediction data, carrying out financial risk prediction by combining the optimized prediction characteristics to obtain financial risk prediction data.
7. A financial risk prediction method for electronic recruitment assistance according to claim 6, wherein: in step S5, the electronic recruitment decision support is configured to provide decision support for electronic bidding purchasing according to a financial risk prediction result, specifically, perform electronic recruitment decision support according to the financial risk prediction data, so as to obtain an electronic recruitment planning strategy.
8. A financial risk prediction method for electronic recruitment assistance according to claim 7, wherein: in step S1, the data collection is configured to collect financial data of an enterprise, specifically, financial risk prediction raw data obtained by collection from historical data of the enterprise, where the financial risk prediction raw data includes historical financial data, supply chain data and market data.
9. A financial risk prediction system for electronic recruitment assistance to implement a financial risk prediction method for electronic recruitment assistance according to any one of claims 1-8, wherein: the system comprises a data acquisition module, a data preprocessing module, an optimal financial risk prediction factor identification module, a financial risk prediction module and an electronic recruitment decision support module.
10. A financial risk prediction system for electronic recruitment assistance according to claim 9, wherein: the data acquisition module is used for collecting enterprise financial data, acquiring financial risk prediction original data through data acquisition, and sending the financial risk prediction original data to the data preprocessing module;
the data preprocessing module is used for converting enterprise financial data into a unified data structure which can be automatically analyzed, obtaining optimized financial risk prediction data through data preprocessing, and sending the optimized financial risk prediction data to the optimal financial risk prediction factor identification module and the financial risk prediction module;
the optimal financial risk prediction factor identification module is used for selecting data features which are more useful for prediction from the optimal data through feature selection to reduce the difficulty of subsequent learning tasks and improve model efficiency, identifying the optimal financial risk prediction factors to obtain optimal prediction features, and sending the optimal prediction features to the financial risk prediction module;
The financial risk prediction module is used for performing financial risk prediction, obtaining financial risk prediction data by performing financial risk prediction according to the optimized financial risk prediction data and combining the optimized prediction characteristics, and sending the financial risk prediction data to the electronic recruitment decision support module;
the electronic recruitment decision support module is used for providing decision support for electronic recruitment according to the financial risk prediction result, and obtaining an electronic recruitment planning strategy through the electronic recruitment decision support.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173040.XA CN117726461A (en) | 2024-02-07 | 2024-02-07 | Financial risk prediction method and system for electronic recruitment assistance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173040.XA CN117726461A (en) | 2024-02-07 | 2024-02-07 | Financial risk prediction method and system for electronic recruitment assistance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117726461A true CN117726461A (en) | 2024-03-19 |
Family
ID=90207292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410173040.XA Pending CN117726461A (en) | 2024-02-07 | 2024-02-07 | Financial risk prediction method and system for electronic recruitment assistance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117726461A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022517A (en) * | 2016-05-17 | 2016-10-12 | 温州大学 | Risk prediction method and device based on nucleus limit learning machine |
| CN107908688A (en) * | 2017-10-31 | 2018-04-13 | 温州大学 | A kind of data classification Forecasting Methodology and system based on improvement grey wolf optimization algorithm |
| US20200103894A1 (en) * | 2018-05-07 | 2020-04-02 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for computerized maintenance management system using the industrial internet of things |
| CN112947300A (en) * | 2021-02-22 | 2021-06-11 | 西安交通大学 | Virtual measuring method, system, medium and equipment for processing quality |
| CN114863226A (en) * | 2022-04-26 | 2022-08-05 | 江西理工大学 | Network physical system intrusion detection method |
| CN115963407A (en) * | 2022-12-17 | 2023-04-14 | 福州大学 | ICGWO (intensive care unit) optimization ELM (element-based robust model) based lithium battery SOC estimation method |
| CN116993490A (en) * | 2023-08-15 | 2023-11-03 | 广州佳新智能科技有限公司 | Automatic bank scene processing method and system based on artificial intelligence |
-
2024
- 2024-02-07 CN CN202410173040.XA patent/CN117726461A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022517A (en) * | 2016-05-17 | 2016-10-12 | 温州大学 | Risk prediction method and device based on nucleus limit learning machine |
| CN107908688A (en) * | 2017-10-31 | 2018-04-13 | 温州大学 | A kind of data classification Forecasting Methodology and system based on improvement grey wolf optimization algorithm |
| US20200103894A1 (en) * | 2018-05-07 | 2020-04-02 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for computerized maintenance management system using the industrial internet of things |
| CN112947300A (en) * | 2021-02-22 | 2021-06-11 | 西安交通大学 | Virtual measuring method, system, medium and equipment for processing quality |
| CN114863226A (en) * | 2022-04-26 | 2022-08-05 | 江西理工大学 | Network physical system intrusion detection method |
| CN115963407A (en) * | 2022-12-17 | 2023-04-14 | 福州大学 | ICGWO (intensive care unit) optimization ELM (element-based robust model) based lithium battery SOC estimation method |
| CN116993490A (en) * | 2023-08-15 | 2023-11-03 | 广州佳新智能科技有限公司 | Automatic bank scene processing method and system based on artificial intelligence |
Non-Patent Citations (4)
| Title |
|---|
| 于学超: "基于极点对称模态分解的风电短期功率预测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, 15 January 2021 (2021-01-15), pages 13 - 34 * |
| 何成;刘长春;武洋;吴涛;陈童;: "改进灰狼优化算法医疗锂电池剩余寿命预测", 重庆师范大学学报(自然科学版), no. 03, 9 May 2019 (2019-05-09) * |
| 徐辰华;李成县;王尤军;林小峰;: "基于混沌灰狼优化算法的氧化铝质量指标预测模型", 广西大学学报(自然科学版), no. 06, 25 December 2016 (2016-12-25) * |
| 王田田;王艳;纪志成;: "基于改进极限学习机的滚动轴承故障诊断", 系统仿真学报, no. 11, 6 September 2018 (2018-09-06) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106599935B (en) | Three decision unbalanced data oversampler methods based on Spark big data platform | |
| Li et al. | A classification surrogate-assisted multi-objective evolutionary algorithm for expensive optimization | |
| Arqawi et al. | Predicting Employee Attrition and Performance Using Deep Learning | |
| CN111798062B (en) | Financial data prediction system based on block chain and big data | |
| CN111079074A (en) | Method for constructing prediction model based on improved sine and cosine algorithm | |
| Gu et al. | An improved bagging ensemble surrogate-assisted evolutionary algorithm for expensive many-objective optimization | |
| CN113011559A (en) | Automatic machine learning method and system based on kubernets | |
| CN117196418B (en) | Reading teaching quality assessment method and system based on artificial intelligence | |
| CN117634693A (en) | Carbon emission prediction method based on energy data | |
| CN117726461A (en) | Financial risk prediction method and system for electronic recruitment assistance | |
| CN116503026B (en) | Operation and maintenance risk assessment method, system and storage medium for science and technology items | |
| CN117371511A (en) | Training method, device, equipment and storage medium for image classification model | |
| CN111738870A (en) | Method and platform for identifying insurance risk of engineering performance guarantee based on characteristic engineering | |
| CN112465253B (en) | Method and device for predicting links in urban road network | |
| CN117010538A (en) | Method and system for predicting agricultural machinery service resource spare parts | |
| Zhu et al. | Hybrid Ensemble Pruning Using Coevolution Binary Glowworm Swarm Optimization and Reduce‐Error | |
| CN110728292A (en) | Self-adaptive feature selection algorithm under multi-task joint optimization | |
| CN117648646B (en) | Drilling and production cost prediction method based on feature selection and stacked heterogeneous integrated learning | |
| CN117493982B (en) | Semiconductor resistance value prediction method and system based on machine learning | |
| CN115131155B (en) | Cloud platform based on investment management | |
| US20240119314A1 (en) | Gene coding breeding prediction method and device based on graph clustering | |
| CN116992098B (en) | Quotation network data processing method and system | |
| CN116070120B (en) | Automatic identification method and system for multi-tag time sequence electrophysiological signals | |
| CN117291845B (en) | Point cloud ground filtering method, system, electronic equipment and storage medium | |
| CN115115873A (en) | Image classification method and device based on differentiable network structure search |
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 |