CN113052706A - Fund risk grade prediction method and device - Google Patents

Fund risk grade prediction method and device Download PDF

Info

Publication number
CN113052706A
CN113052706A CN202110480056.1A CN202110480056A CN113052706A CN 113052706 A CN113052706 A CN 113052706A CN 202110480056 A CN202110480056 A CN 202110480056A CN 113052706 A CN113052706 A CN 113052706A
Authority
CN
China
Prior art keywords
fund
information corresponding
prediction
total information
prediction period
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110480056.1A
Other languages
Chinese (zh)
Inventor
滕建德
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202110480056.1A priority Critical patent/CN113052706A/en
Publication of CN113052706A publication Critical patent/CN113052706A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Educational Administration (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a fund risk level prediction method and a fund risk level prediction device, wherein the method comprises the following steps: acquiring a plurality of pieces of information of fund types in a mobile phone bank in a prediction period, and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information; inputting the total information and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted. The fund risk level is predicted based on the fund type information, and the fund type information is some predictions of future forms of professionals in the industry or important news capable of influencing fund market change, so that the fund risk level can be accurately predicted in the future, valuable information reference is provided for users, user experience is improved, and user service of a mobile banking is improved. The invention is used in the field of artificial intelligence.

Description

Fund risk grade prediction method and device
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a fund risk grade prediction method and device.
Background
At present, when a large part of users of a mobile banking trade funds in the mobile banking, future risk levels cannot be predicted on fund products, so that the users do not have any valuable information reference when conducting fund trading, are lost, and have poor user experience, and the users of the mobile banking are easy to lose after a long time.
Disclosure of Invention
The embodiment of the invention provides a fund risk grade prediction method, which is used for predicting the future risk grade of a fund product and improving the user experience and comprises the following steps:
acquiring a plurality of pieces of information of fund types in a mobile phone bank in a prediction period, and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
In a specific embodiment, the fund risk level prediction model is pre-established according to the following method:
acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
In the specific implementation process, the process of pre-establishing the fund risk level prediction model further comprises the following steps:
performing data cleaning on the total information corresponding to each historical prediction period, and performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period;
and (3) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model, wherein the risk grade prediction model comprises the following steps:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) classification algorithm, and training to obtain a fund risk level prediction model.
In an embodiment, the data cleaning of the total information corresponding to each historical prediction period includes:
and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period.
In a specific implementation process, data feature extraction is performed on the total information corresponding to each washed historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period, and the method comprises the following steps:
determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
The embodiment of the invention also provides a fund risk level prediction device, which is used for predicting the future risk level of a fund product and improving the user experience, and comprises the following steps:
the information integration module is used for acquiring a plurality of pieces of information of fund types in the mobile phone bank in the prediction period and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
the risk grade prediction module is used for inputting the total information corresponding to the prediction period and the fund to be predicted into a fund risk grade prediction model established in advance to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
and the risk reminding module is used for sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
The device for predicting the fund risk level provided by the specific embodiment of the invention further comprises: a model pre-building module to:
the fund risk level prediction model is established in advance according to the following method:
acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
In a specific implementation process, the model pre-establishing module is further configured to:
performing data cleaning on the total information corresponding to each historical prediction period, and performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period;
the model pre-building module is specifically configured to:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) classification algorithm, and training to obtain a fund risk level prediction model.
In a specific embodiment, the model pre-establishing module is specifically configured to:
and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period.
In a specific implementation process, the model pre-establishing module is specifically configured to:
determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the fund risk level prediction method when executing the computer program.
An embodiment of the present invention also provides a computer-readable storage medium storing a computer program for executing the aforementioned fund risk level prediction method.
In the embodiment of the invention, a plurality of pieces of information of fund types in a mobile phone bank in a prediction period are acquired, and the plurality of pieces of information are integrated into total information corresponding to the prediction period according to the release time of each piece of information; inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period; and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted. The fund risk level is predicted based on the fund type information, and the fund type information is some predictions of future forms of professionals in the industry or important news capable of influencing fund market change, so that the fund risk level can be accurately predicted in the future, valuable information reference is provided for users, user experience is improved, and user service of a mobile banking is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a fund risk level prediction method in an embodiment of the invention.
FIG. 2 is a schematic diagram of a process for pre-establishing a fund risk level prediction model according to an embodiment of the present invention.
FIG. 3 is a schematic diagram of a process for pre-establishing a fund risk level prediction model according to another embodiment of the present invention.
Fig. 4 is a schematic diagram of an implementation method of step 301 in the embodiment of the present invention.
FIG. 5 is a diagram illustrating a screenshot of fund classification information of a certain mobile banking APP in an embodiment of the present invention.
FIG. 6 is a schematic diagram of a fund risk level prediction apparatus according to an embodiment of the present invention.
FIG. 7 is a schematic diagram of a fund risk level prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a fund risk level prediction method, which is used for predicting future risk levels of fund products and improving user experience, and as shown in figure 1, the method comprises the following steps:
step 101: acquiring a plurality of pieces of information of fund types in a mobile phone bank in a prediction period, and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
step 102: inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
step 103: and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
As can be seen from the flow shown in fig. 1, in the embodiment of the present invention, by obtaining multiple pieces of information of fund types in the mobile phone bank in the prediction period, according to the release time of each piece of information, the multiple pieces of information are integrated into a total information corresponding to the prediction period; inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period; and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted. The fund risk level is predicted based on the fund type information, and the fund type information is some predictions of future forms of professionals in the industry or important news capable of influencing fund market change, so that the fund risk level can be accurately predicted in the future, valuable information reference is provided for users, user experience is improved, and user service of a mobile banking is improved.
When the method is implemented, firstly, a plurality of pieces of information of fund types in the mobile phone bank in the prediction period are obtained, and the plurality of pieces of information are integrated into total information corresponding to the prediction period according to the release time of each piece of information. The prediction period is generally set to be one month, and the fund risk level of the month is predicted according to the information of the previous month. Arranging a plurality of pieces of information according to the sequence of the release time before and after the release time and the release time before, and integrating the plurality of pieces of information into total information corresponding to a prediction period.
And after integrating the total information corresponding to the prediction period, inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted. And after the risk grade prediction result of the fund to be predicted is obtained, sending a fund risk prompt to the user according to the risk grade prediction result of the fund to be predicted.
The fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period. In the specific embodiment, as shown in fig. 2, a fund risk level prediction model is established in advance according to the following method:
step 201: acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
step 202: determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
step 203: and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
In an embodiment, for the total information corresponding to each month, the fluctuation range of a fund corresponding to the next month is found, and the total information corresponding to each month is given by: high, medium and low risk grade labels. Wherein the mark with the range of fluctuation amplitude more than or equal to 10 is high, the mark with the range of fluctuation amplitude more than or equal to 2 and less than 10 is medium, and the mark with the range of fluctuation amplitude less than 2 is low. If the information of the fund types in the mobile phone bank in 4 months in 2020 is integrated into a total information, and the fluctuation range of a fund in 5 months in 2020 is checked to be 12, marking the total information as: a high risk level.
As shown in fig. 3, the process of establishing a fund risk level prediction model in advance further includes, on the basis of fig. 2:
step 301: and carrying out data cleaning on the total information corresponding to each historical prediction period, and carrying out data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain the data features corresponding to the total information corresponding to each historical prediction period.
Accordingly, step 203 is embodied as a process comprising:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) (support Vector machine) classification algorithm, and training to obtain a fund risk level prediction model.
In an embodiment, the data cleaning of the total information corresponding to each historical prediction period includes: and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period. In a specific implementation, jieba can be used for performing word segmentation and word deactivation on the text in the total information corresponding to each historical prediction period, wherein jieba is the best Python Chinese word segmentation component.
In a specific implementation process, data feature extraction is performed on the total information corresponding to each washed historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period, as shown in fig. 4, the data feature extraction method includes:
step 401: determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
step 402: obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
step 403: and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
TF-IDF is a statistical method for evaluating the importance of a word to one of a set of documents or a corpus. The importance of a word increases in proportion to the number of times it appears in a document, but at the same time decreases in inverse proportion to the frequency with which it appears in the corpus. The information gain is an important index for feature selection, and is defined as how much information a feature can bring to a classification system, and the more information the information is brought, the more important the feature is, the larger the corresponding information gain is. The principal component analysis method is a statistical method, and converts a group of variables possibly having correlation into a group of linearly uncorrelated variables through orthogonal transformation, wherein the group of converted variables are called principal components.
A specific example is given below to illustrate how embodiments of the present invention may perform fund risk level prediction. The embodiment is based on fund information and combined with a product historical fluctuation training model, but not based on the attribute of the financial product. Because fund information is important news for the professional in the industry to comment on fund development and deal with fund development, the fund information is equivalent to the risk level prediction of fund products standing on the shoulders of the giant.
Firstly, all information with fund type in the APP of the mobile phone bank is collected and sorted according to the month, and the information in one month is integrated into one piece of information according to the information release time. The mobile banking APP generally classifies information, and arranges the information under the fund classification according to months, and the information of each month is arranged into a total information. The information in the fund category is related to, for example, the stock market index change condition, the digital currency development condition, the bank policy, and other related information, and as shown in fig. 5, is a fund classification information screenshot of a certain mobile banking APP.
Then, for the total information corresponding to each month, finding the fluctuation range of a fund corresponding to the next month, and adding the following information to the total information corresponding to each month: high, medium and low risk grade labels. Wherein the mark with the range of fluctuation amplitude more than or equal to 10 is high, the mark with the range of fluctuation amplitude more than or equal to 2 and less than 10 is medium, and the mark with the range of fluctuation amplitude less than 2 is low. If the information of the fund types in the mobile phone bank in 4 months in 2020 is integrated into a total information, and the fluctuation range of a fund in 5 months in 2020 is checked to be 12, marking the total information as: a high risk level.
The marked data is divided into two parts, wherein 80% of the marked data is used for training the model and 20% of the marked data is used for testing the model.
Data cleaning: and performing word segmentation and word deactivation on the text by using jieba on the marked information data.
Feature extraction: and (3) performing feature extraction on the cleaned data, and dividing the data into the following two parts:
(1) TF-IDF: first, the TF-IDF function is used to convert the data-cleaned information into weight. If there are 500 pieces of information, the total number of words is 1000 after being segmented, and the style after TF-IDF processing is shown in Table 1:
TABLE 1
Word segmentation 1 Word segmentation 2 Word segmentation 3 Word segmentation 4 …… Participle 1000 Fund risk rating
Information 1 0.15 0.35 0.2 0.1 …… 0.1 In
Information 2 0.5 0.1 0.15 0.15 …… 0.05 Height of
Information 3 0 0 0.1 0 …… 0 Is low in
…… …… …… …… …… …… …… ……
Information 500 0 0.05 0 0 …… 0.2 Height of
(2) Information gain: and (4) extracting the data features after TF-IDF processing by using an information gain function, sequencing the obtained information gain values according to the size, and selecting the first 50 features. After feature extraction, 50 features are retained, and the style is shown in table 2:
TABLE 2
Word segmentation 1 Word segmentation 2 Word segmentation 3 Word segmentation 4 …… Participle 50 Fund risk rating
Information 1 0.15 0.35 0.2 0.1 …… 0.05 In
Information 2 0.5 0.1 0.15 0.15 …… 0.01 Height of
Information 3 0 0 0.1 0 …… 0.02 Is low in
…… …… …… …… …… …… …… ……
Information 500 0 0.05 0 0 …… 0.03 Height of
And (3) reducing the dimensionality: and (3) performing dimensionality reduction processing on the data features subjected to the information gain processing by using a principal component analysis method, and finally reserving 30 features. The data pattern after dimension reduction is shown in table 3:
TABLE 3
Word segmentation 1 Word segmentation 2 Word segmentation 3 Word segmentation 4 …… Participle 30 Fund risk rating
Information 1 0.15 0.35 0.2 0.1 …… 0.05 In
Information 2 0.5 0.1 0.15 0.15 …… 0.01 Height of
Information 3 0 0 0.1 0 …… 0.03 Is low in
…… …… …… …… …… …… …… ……
Information 500 0 0.05 0 0 0.06 Height of
In specific implementation, the final segmentation after dimensionality reduction is, for example, quotation, callback, difficulty, foreign exchange, concussion, and the like.
And carrying out model training on the data features subjected to dimensionality reduction by using an SVM classification algorithm, wherein the high, medium and low risk grades are classified respectively. And testing the correctness of the model by using 20% of data, and continuously optimizing to finally obtain a model with higher correctness.
And predicting the risk level of a fund according to the information of the new month by using the obtained model, wherein the model outputs one of three risk level results of high risk level, medium risk level and low risk level. And pushing the risk level prediction result output by the model to a user of the mobile banking in a message pushing mode.
And aiming at different funds, continuously repeating the process to obtain the risk grade prediction results of all the funds in the mobile phone bank APP and pushing the risk grade prediction results to the user.
By predicting according to the information of each month, the risk level of the fund in the next month is predicted, the user is informed in advance, the user service is improved, and more user resources are pulled.
The implementation of the above specific application is only an example, and the rest of the embodiments are not described in detail.
Based on the same inventive concept, embodiments of the present invention further provide a fund risk level prediction apparatus, and since the principle of the problem solved by the fund risk level prediction apparatus is similar to that of the fund risk level prediction method, the implementation of the fund risk level prediction apparatus may refer to the implementation of the fund risk level prediction method, and repeated parts are not repeated, and the specific structure is as shown in fig. 6:
the information integration module 601 is used for acquiring a plurality of pieces of information of fund types in the mobile phone bank in the prediction period, and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
the risk level prediction module 602 is configured to input the total information corresponding to the prediction period and the fund to be predicted into a fund risk level prediction model established in advance to obtain a risk level prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
and the risk reminding module 603 is used for sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
As shown in fig. 7, the fund risk level prediction apparatus according to the embodiment of the present invention further includes, on the basis of fig. 6: a model pre-building module 701 configured to:
a fund risk level prediction model is established in advance according to the following method:
acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
In a specific implementation process, the model pre-establishing module 701 is further configured to:
performing data cleaning on the total information corresponding to each historical prediction period, and performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period;
accordingly, the model pre-establishing module 701 is specifically configured to:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) classification algorithm, and training to obtain a fund risk level prediction model.
In a specific embodiment, the model pre-establishing module 701 is specifically configured to:
and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period.
In a specific implementation process, the model pre-establishing module 701 is further specifically configured to:
determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the fund risk level prediction method when executing the computer program.
An embodiment of the present invention also provides a computer-readable storage medium storing a computer program for executing the aforementioned fund risk level prediction method.
In summary, the fund risk level prediction method and device provided by the embodiment of the invention have the following advantages:
integrating a plurality of pieces of information into total information corresponding to a prediction period according to the release time of each piece of information by acquiring a plurality of pieces of information of fund types in a mobile phone bank in the prediction period; inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period; and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted. The fund risk level is predicted based on the fund type information, and the fund type information is some predictions of future forms of professionals in the industry or important news capable of influencing fund market change, so that the fund risk level can be accurately predicted in the future, valuable information reference is provided for users, user experience is improved, and user service of a mobile banking is improved.
Although the present invention provides method steps as described in the examples or flowcharts, more or fewer steps may be included based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, apparatus (system) or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In this document, relational terms such as first and second, and the like may be 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. Also, 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. The terms "upper", "lower", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are intended to be inclusive and mean, for example, that they may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention is not limited to any single aspect, nor is it limited to any single embodiment, nor is it limited to any combination and/or permutation of these aspects and/or embodiments. Moreover, each aspect and/or embodiment of the present invention may be utilized alone or in combination with one or more other aspects and/or embodiments thereof.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.

Claims (12)

1. A fund risk level prediction method is characterized by comprising the following steps:
acquiring a plurality of pieces of information of fund types in a mobile phone bank in a prediction period, and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
inputting the total information corresponding to the prediction period and the fund to be predicted into a pre-established fund risk grade prediction model to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
and sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
2. The fund risk level prediction method according to claim 1, wherein the fund risk level prediction model is pre-established according to the following method:
acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
3. The fund risk level prediction method according to claim 2, wherein the process of pre-establishing the fund risk level prediction model further comprises:
performing data cleaning on the total information corresponding to each historical prediction period, and performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period;
and (3) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model, wherein the risk grade prediction model comprises the following steps:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) classification algorithm, and training to obtain a fund risk level prediction model.
4. The method of predicting the risk level of a fund as set forth in claim 3, wherein the step of performing data cleaning on the total information corresponding to each historical prediction period comprises the steps of:
and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period.
5. The fund risk level prediction method according to claim 4, wherein the step of performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period comprises the steps of:
determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
6. A fund risk level prediction apparatus, comprising:
the information integration module is used for acquiring a plurality of pieces of information of fund types in the mobile phone bank in the prediction period and integrating the plurality of pieces of information into total information corresponding to the prediction period according to the release time of each piece of information;
the risk grade prediction module is used for inputting the total information corresponding to the prediction period and the fund to be predicted into a fund risk grade prediction model established in advance to obtain a risk grade prediction result of the fund to be predicted; the fund risk level prediction model is used for predicting the risk level of the fund according to the information in the prediction period;
and the risk reminding module is used for sending fund risk reminding to the user according to the risk grade prediction result of the fund to be predicted.
7. The fund risk level prediction apparatus according to claim 6, further comprising: a model pre-building module to:
the fund risk level prediction model is established in advance according to the following method:
acquiring total information corresponding to a plurality of historical prediction periods and the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
determining a risk grade label for the total information corresponding to each historical prediction period according to the falling and rising amplitude data of the fund to be predicted corresponding to each historical prediction period;
and (4) taking the risk grade label of the total information corresponding to each historical prediction period as output, and taking the total information corresponding to each historical prediction period as input, and establishing a fund risk grade prediction model.
8. The fund risk level prediction apparatus according to claim 7, wherein the model pre-building module is further configured to:
performing data cleaning on the total information corresponding to each historical prediction period, and performing data feature extraction on the cleaned total information corresponding to each historical prediction period to obtain data features corresponding to the total information corresponding to each historical prediction period;
the model pre-building module is specifically configured to:
and classifying the data characteristics corresponding to the total information corresponding to each historical prediction period by using a Support Vector Machine (SVM) classification algorithm, and training to obtain a fund risk level prediction model.
9. The fund risk level prediction apparatus according to claim 8, wherein the model pre-building module is specifically configured to:
and performing text word segmentation and word deactivation on the total information corresponding to each historical prediction period to obtain the word segmentation of the total information corresponding to each historical prediction period.
10. The fund risk level prediction apparatus according to claim 9, wherein the model pre-building module is specifically configured to:
determining the weight of each word segmentation of the total information corresponding to each historical prediction period by using a TF-IDF function;
obtaining initial data characteristics according to the weight and the information gain function of each word segmentation of the total information corresponding to each historical prediction period;
and reducing the dimension of the initial data characteristics by using a principal component analysis method to obtain the data characteristics corresponding to the total information corresponding to each historical prediction period.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
CN202110480056.1A 2021-04-30 2021-04-30 Fund risk grade prediction method and device Pending CN113052706A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110480056.1A CN113052706A (en) 2021-04-30 2021-04-30 Fund risk grade prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110480056.1A CN113052706A (en) 2021-04-30 2021-04-30 Fund risk grade prediction method and device

Publications (1)

Publication Number Publication Date
CN113052706A true CN113052706A (en) 2021-06-29

Family

ID=76517812

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110480056.1A Pending CN113052706A (en) 2021-04-30 2021-04-30 Fund risk grade prediction method and device

Country Status (1)

Country Link
CN (1) CN113052706A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110222895A (en) * 2019-06-10 2019-09-10 上海时廊人工智能科技有限公司 A kind of shares changing tendency prediction technique, device, computer equipment and storage medium
CN110555541A (en) * 2018-05-31 2019-12-10 国信优易数据有限公司 Risk prediction system and method
CN111932267A (en) * 2020-07-27 2020-11-13 中国工商银行股份有限公司 Enterprise financial service risk prediction method and device
CN112527866A (en) * 2020-06-09 2021-03-19 中国人民大学 Stock trend prediction method and system based on text abstract emotion mining

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110555541A (en) * 2018-05-31 2019-12-10 国信优易数据有限公司 Risk prediction system and method
CN110222895A (en) * 2019-06-10 2019-09-10 上海时廊人工智能科技有限公司 A kind of shares changing tendency prediction technique, device, computer equipment and storage medium
CN112527866A (en) * 2020-06-09 2021-03-19 中国人民大学 Stock trend prediction method and system based on text abstract emotion mining
CN111932267A (en) * 2020-07-27 2020-11-13 中国工商银行股份有限公司 Enterprise financial service risk prediction method and device

Similar Documents

Publication Publication Date Title
CN109522556B (en) Intention recognition method and device
CN110909165B (en) Data processing method, device, medium and electronic equipment
WO2021164382A1 (en) Method and apparatus for performing feature processing for user classification model
US11915104B2 (en) Normalizing text attributes for machine learning models
CN113590764B (en) Training sample construction method and device, electronic equipment and storage medium
CN107545038B (en) Text classification method and equipment
CN112070138A (en) Multi-label mixed classification model construction method, news classification method and system
CN113283795B (en) Data processing method and device based on two-classification model, medium and equipment
CN111931809A (en) Data processing method and device, storage medium and electronic equipment
US10977290B2 (en) Transaction categorization system
CN107203772B (en) User type identification method and device
CN111967521A (en) Cross-border active user identification method and device
CN112434862B (en) Method and device for predicting financial dilemma of marketing enterprises
CN111949770A (en) Document classification method and device
CN113052706A (en) Fund risk grade prediction method and device
CN107957944B (en) User data coverage rate oriented test case automatic generation method
CN114637917A (en) Information head bar recommendation method and device based on artificial intelligence
CN113239280A (en) Financial information recommendation method and device
CN113011503A (en) Data evidence obtaining method of electronic equipment, storage medium and terminal
CN113934833A (en) Training data acquisition method, device and system and storage medium
CN113239126A (en) Business activity information standardization scheme based on BOR method
CN112835810A (en) Interface testing method and device based on log analysis
CN112948583A (en) Data classification method and device, storage medium and electronic device
CN112732908A (en) Test question novelty evaluation method and device, electronic equipment and storage medium
CN115511635A (en) Loss-prevention hang ticket prompting method and device

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