CN118350854A - Investor behavior data analysis method and system - Google Patents
Investor behavior data analysis method and system Download PDFInfo
- Publication number
- CN118350854A CN118350854A CN202410764588.1A CN202410764588A CN118350854A CN 118350854 A CN118350854 A CN 118350854A CN 202410764588 A CN202410764588 A CN 202410764588A CN 118350854 A CN118350854 A CN 118350854A
- Authority
- CN
- China
- Prior art keywords
- investment
- investor
- different
- investors
- behavior data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000007405 data analysis Methods 0.000 title claims description 10
- 230000006399 behavior Effects 0.000 claims description 133
- 230000008859 change Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 6
- 230000007774 longterm Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 description 11
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a method and a system for analyzing investor behavior data, which belong to the technical field of data processing and specifically comprise the following steps: the method comprises the steps of determining the behavior similarity of investors in different effective investment targets and different preset images and the matched preset images based on the investment behavior data of the investors in different effective investment targets, determining the matching degree of the investment behavior data of the investors and the different preset images and the behavior matching images by combining the reliability of the investment behavior data of the different effective investment targets, and constructing the investment images of the investors according to the behavior matching images of the investors and the matching degree of the different behavior matching images, so that the construction accuracy of the investment images of the investors is ensured.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a method and a system for analyzing investor behavior data.
Background
Because of the deviation of basic investment knowledge, character and the like, different investors often have different investment preferences, and for different investors with different investment preferences, financial service institutions often have corresponding financial service packages, so how to accurately realize accurate evaluation of the investment preferences of the investors becomes a technical problem to be solved.
In order to solve the above technical problems, in the invention CN201910048848.4, "a method, an apparatus, a device, and a medium for classifying investors", image data of the investors and behavior data of the investors on the financial service platform are classified according to a target dimension, and classification processing of the investors is performed according to a result of cluster analysis, but the following technical problems are found by analysis:
The investment preference of the investor is not constant, and the investment behaviors of the investor may change to a certain extent along with the increase of the personal investment experience and the change of the investment thinking, so that the accuracy of the evaluation of the investment preference cannot be ensured if the screening of the effective behavior data cannot be performed according to the identification results of the similarity of the investment behaviors of the investor in different time periods.
Aiming at the technical problems, the invention provides a method and a system for analyzing investor behavior data.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the present invention, a person classification recognition method is provided.
An investor behavior data analysis method specifically comprises the following steps:
S1, acquiring basic information data of an investor in different dimensions, and determining similarity between the investor and different preset portraits and matched preset portraits of the investor based on the basic information data;
S2, acquiring investment behavior data of the investor, determining reliability of the investment behavior data of the investor in different investment targets according to similar conditions and data amounts of the investment behavior data of the different investment targets in different dividing time periods, and entering a next step when determining that the investor has an effective investment target based on the reliability;
S3, determining the behavior similarity of the investor with different preset images and matched preset images of different effective investment targets based on the investment behavior data of the investor with different effective investment targets, and determining the matching degree of the investment behavior data of the investor with different preset images and the behavior matched images by combining the reliability of the investment behavior data of the different effective investment targets;
s4, constructing the investment portrait of the investor through the matching degree of the behavior matching portrait of the investor and different behavior matching portraits.
The invention has the beneficial effects that:
1. According to the similarity condition of the investment behavior data of different investment targets in different dividing time periods and the data quantity, the reliability of the investment behavior data of the investor in the different investment targets is determined, the difference of the reliability of the investment behavior data caused by the difference of the similarity condition of the investment behavior data of the different investment targets is singly considered, and meanwhile, the reliability of the investment behavior data caused by the difference of the data quantity of the investment behavior data of the investment targets is further combined, so that the reliability of the investment behavior data is accurately estimated.
2. The construction of the investment portrait of the investor is carried out through the behavior matching portrait of the investor and the matching degree of different behavior matching portraits, so that the construction of the investment portrait of the investor from the angle of the matching condition of the investment behavior data of the investor and different behavior matching portraits is realized, the difference of the matching degree of the investment behavior data of the investor and different preset portraits is fully considered, and the construction accuracy of the investment portrait of the investor is ensured.
Further technical solutions are that the dimensions of the basic information data include the occupation, age, month income, investment years and academia.
Further technical scheme is that the preset portrait comprises an ultra-short line investor, a short line investor and a long-term value investor.
A further technical solution is to determine the investment target as an effective investment target when the reliability of the investment behavior data of the investment target meets the requirements.
A further technical solution is that when the investor does not have a valid investment target, the matched preset representation of the investor is taken as the investment representation of the investor.
The further technical scheme is that when the behavior similarity between the preset portrait and the effective investment target meets the requirement, the preset portrait is determined to be the matched preset portrait.
The further technical proposal is that the method for constructing the investment portrait of the investor comprises the following steps:
And taking the behavior matching image of the investor with the largest matching degree as a candidate investment image, and constructing the investment image of the investor based on the candidate investment image.
In a second aspect, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, the processor executing one of the investor behavior data analysis methods described above when the computer program is run.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention as set forth hereinafter.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings;
FIG. 1 is a flow chart of a method of investor behavior data analysis;
FIG. 2 is a flow chart of a method of determining the similarity of an investor to the preset representation;
FIG. 3 is a flow chart of a method of determining reliability of investment behavior data of an investor in an investment target;
FIG. 4 is a flow chart of a method of determining behavioral similarity of an effective investment goal to a preset image;
FIG. 5 is a flow chart of a method of construction of an investment representation of an investor;
FIG. 6 is a block diagram of a computer system.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
Financial service institutions often need to analyze the investment preference of investors for services and provide targeted financial services according to the analysis results, but the investment behavior data of investors is not constant, so that the similarity of the investment behaviors of investors in different time periods needs to be integrated to construct a user portrait, otherwise, the accuracy of the evaluation of the investment preference of the user is difficult to ensure.
In order to solve the technical problems, the invention screens the effective investment behaviors by combining the evaluation results of the similarity of the investment behaviors of the users in different time periods, and builds the portrait of the users according to the effective investment behaviors and the matching conditions of the basic information of the users and different preset portraits.
As will be further described below.
To solve the above problems, according to an aspect of the present invention, as shown in fig. 1, there is provided an investor behavior data analyzing method, which specifically includes:
S1, acquiring basic information data of an investor in different dimensions, and determining similarity between the investor and different preset portraits and matched preset portraits of the investor based on the basic information data;
specifically, the dimensions of the basic information data include occupation, age, monthly income, investment years, and academia.
Further, the preset portraits include an ultra short line investor, a short line investor, and a long term value investor.
Specifically, as shown in fig. 2, the method for determining the similarity between the investor and the preset portrait includes:
taking a historical investor divided into preset images as an investor to be matched, and determining the basic information similarity of the investor and different investors to be matched according to basic information data of different dimensionalities of the investor;
dividing the investors to be matched into similar investors and deviation investors based on the basic information similarity, and determining the comprehensive similarity of the similar investors through the number of the similar investors and the basic information similarity of different similar investors and the investors;
determining a comprehensive deviation amount of the deviation investors based on the number of the deviation investors and the basic information similarity of different deviation investors to the investors;
and determining the similarity between the investors and the preset portrait according to the comprehensive similarity and the comprehensive deviation of the similar investors.
Further, when the similarity between the preset portrait and the investor meets the requirement, the preset portrait is determined to be the matched preset portrait of the investor.
In another embodiment, the method for determining the similarity between the investor and the preset portrait comprises the following steps:
The method comprises the steps of taking a historical investor divided into preset images as an investor to be matched, determining basic information similarity between the investor and different investors to be matched according to basic information data of different dimensionalities of the investor, judging whether the investor to be matched with the basic information similarity meeting requirements exists or not, if yes, entering the next step, and if not, determining that the preset images do not belong to the matched preset images of the investor;
dividing the investors to be matched into similar investors and deviation investors based on the basic information similarity, judging whether the number of the similar investors is larger than the number of preset investors, if so, entering the next step, and if not, determining that the preset portrait does not belong to the matched preset portraits of the investors;
determining the comprehensive similarity of the similar investors according to the number of the similar investors and the basic information similarity of different similar investors and the investors, judging whether the comprehensive similarity of the similar investors meets the requirement, if so, entering the next step, and if not, determining that the preset portrait does not belong to the matched preset portrait of the investors;
and determining the comprehensive deviation amount of the deviation investors based on the number of the deviation investors and the basic information similarity between different deviation investors and the investors, and determining the similarity between the investors and the preset image according to the comprehensive similarity and the comprehensive deviation amount of the similar investors.
In another embodiment, the method for determining the similarity between the investor and the preset portrait comprises the following steps:
The method comprises the steps of taking a historical investor divided into preset images as an investor to be matched, determining basic information similarity between the investor and different investors to be matched according to basic information data of different dimensionalities of the investor, judging whether an average value of the basic information similarity between the investor and different investors to be matched meets requirements, if so, determining the preset images as matched preset images of the investors, and if not, entering a next step;
Dividing the investors to be matched into similar investors and deviation investors based on the basic information similarity, judging whether the quantity ratio of the deviation investors is smaller than a preset quantity ratio, if so, determining that the preset image is a matched preset image of the investors, and if not, entering the next step;
Determining the comprehensive deviation amount of the deviation investors based on the number of the deviation investors, the number proportion of the deviation investors and the basic information similarity of different deviation investors and the investors, judging whether the comprehensive deviation amount meets the requirement, if so, determining that the preset image is a matched preset image of the investors, and if not, entering the next step;
determining the comprehensive similarity of the similar investors through the number of the similar investors and the basic information similarity of different similar investors and the investors;
and determining the comprehensive deviation amount of the deviation investors based on the number of the deviation investors and the basic information similarity between different deviation investors and the investors, and determining the similarity between the investors and the preset image according to the comprehensive similarity and the comprehensive deviation amount of the similar investors.
S2, acquiring investment behavior data of the investor, determining reliability of the investment behavior data of the investor in different investment targets according to similar conditions and data amounts of the investment behavior data of the different investment targets in different dividing time periods, and entering a next step when determining that the investor has an effective investment target based on the reliability;
Further, the investment behavior data includes a number of holding-up changing operations and a time interval between different holding-up changing operations.
Specifically, as shown in fig. 3, the method for determining the reliability of the investment behavior data of the investor in the investment target is as follows:
Determining the number of the warehouse holding variation operation times of the investor in the investment targets in different dividing time periods based on the investment behavior data of the investor in the investment targets, and performing the basic reliability of the investment behavior data of the investor according to the number of the warehouse holding variation operation times of the investor in the investment targets in different dividing time periods;
Determining the number of the operation time of the change of the holding bin in different time intervals by the time interval between the different operation time of the change of the holding bin, and determining the operational data credibility of the different time intervals of the division by combining the change of the holding quantity of the different operation time of the change of the holding bin in different time intervals of the division and the time interval between the different operation time of the change of the holding bin;
the reliability of the investment behavior data of the investment target is determined based on the basic reliability of the investment behavior data of the investment target and the operational data reliability of the different divided time intervals.
Further, the dividing time interval is determined according to preset time intervals of the number of the holding variation operations corresponding to different preset images.
When the reliability of the investment behavior data of the investment target meets the requirement, the investment target is determined to be an effective investment target.
Further, when the investor does not have a valid investment target, the matched preset portrait of the investor is taken as the investment portrait of the investor.
In another embodiment, the method for determining the reliability of the investment behavior data of the investor in the investment target is as follows:
Determining the number of the warehouse holding variation times of the investment target based on the investment behavior data of the investors in the investment target, judging whether the number of the warehouse holding variation times of the investment target meets the requirement, if so, entering the next step, and if not, determining that the investment target does not belong to an effective investment target;
Acquiring the number of the warehouse-holding variation of the investor in the investment target in the latest preset time period, judging whether the number of the warehouse-holding variation of the investor in the investment target in the latest preset time period meets the requirement, if so, entering the next step, and if not, determining that the investment target does not belong to the effective investment target;
according to the operation times of the investors for carrying out the warehouse holding fluctuation of the investment targets in different dividing time periods, the basic reliability of the investment behavior data of the investment targets is judged whether to meet the requirement, if so, the next step is carried out, and if not, the investment targets are determined not to belong to the effective investment targets;
Determining the number of the operation time of the change of the holding bin in different time intervals by the time interval between the different operation time of the change of the holding bin, and determining the operational data credibility of the different time intervals of the division by combining the change of the holding quantity of the different operation time of the change of the holding bin in different time intervals of the division and the time interval between the different operation time of the change of the holding bin;
the reliability of the investment behavior data of the investment target is determined based on the basic reliability of the investment behavior data of the investment target and the operational data reliability of the different divided time intervals.
In another embodiment, the method for determining the reliability of the investment behavior data of the investor in the investment target is as follows:
Determining the number of the warehouse holding fluctuation times of the investment target based on the investment behavior data of the investor in the investment target, and determining whether the basic reliability meets the requirement or not according to the basic reliability of the investment behavior data of the investment target in different dividing time periods, if so, entering the next step, and if not, determining that the investment target does not belong to an effective investment target;
Determining the number of the operation time of the bin holding variation in different dividing time intervals through the time intervals among the operation time of the different bin holding variation, determining the operational data credibility of the different dividing time intervals by combining the variation of the bin holding quantity of the different operation time of the bin holding variation in different dividing time intervals and the time intervals among the operation time of the different bin holding variation, judging whether a plurality of operation data credibility meets the dividing time intervals required, if yes, determining that the investment target does not belong to the effective investment target, and if not, entering the next step;
determining the deviation amount of the operation data credibility of different dividing time intervals according to the operation data credibility of the different dividing time intervals, judging whether the dividing time intervals with the deviation amount within a preset deviation range exist or not, if yes, determining that the investment target does not belong to the effective investment target, and if not, entering the next step;
the reliability of the investment behavior data of the investment target is determined based on the basic reliability of the investment behavior data of the investment target and the operational data reliability of the different divided time intervals.
S3, determining the behavior similarity of the investor with different preset images and matched preset images of different effective investment targets based on the investment behavior data of the investor with different effective investment targets, and determining the matching degree of the investment behavior data of the investor with different preset images and the behavior matched images by combining the reliability of the investment behavior data of the different effective investment targets;
Specifically, as shown in fig. 4, the method for determining the behavioral similarity between the effective investment target and the preset image includes:
Determining the operation data similarity of different warehouse holding variation operation times of the investors in the effective investment targets and the preset portrait based on the investment behavior data of the investors in the effective investment targets, and dividing the warehouse holding variation operation times into similar operation times and deviation operation times through the operation data similarity;
Determining similarity evaluation amounts in different divided time periods by the similar operation times in different divided time periods and the operation data similarity of different similar operation times, the deviation operation times and the operation data similarity of different deviation operation times;
And determining the behavior similarity of the effective investment target and a preset image based on the similarity evaluation quantity in different dividing time periods.
Further, when the behavior similarity between the preset portrait and the effective investment target meets the requirement, determining that the preset portrait is a matched preset portrait.
In another embodiment, the method for determining the behavioral similarity between the effective investment target and the preset image is as follows:
Determining the operation data similarity of different storage variation operation times of the investor in the effective investment target and the preset portrait based on the investment behavior data of the investor in the effective investment target, judging whether the average value of the operation data similarity of the different storage variation operation times of the investor in the effective investment target and the preset portrait meets the requirement, if so, entering the next step, and if not, determining that the preset portrait does not belong to the matched preset portrait;
Dividing the operation frequency of the warehouse holding variation into similar operation frequency and deviation operation frequency through the operation data similarity, judging whether the deviation operation frequency meets the requirement, if so, entering the next step, and if not, determining that the preset portrait does not belong to the matched preset portrait;
acquiring deviation operation times in different dividing time periods, judging whether the number of dividing time periods with the deviation operation times not meeting the requirement meets the requirement, if so, entering the next step, and if not, determining that the preset portrait does not belong to the matched preset portrait;
Determining similarity evaluation amounts in different dividing time periods through similar operation times in different dividing time periods and operation data similarity of different similar operation times, deviation operation times and operation data similarity of different deviation operation times, judging whether the number of dividing time periods, of which the similarity evaluation amounts do not meet the requirements, meets the requirements or not, if yes, entering the next step, and if no, determining that the preset portrait does not belong to the matched preset portrait;
And determining the behavior similarity of the effective investment target and a preset image based on the similarity evaluation quantity in different dividing time periods.
Specifically, the method for determining the matching degree between the investment behavior data of the investor and the preset portrait comprises the following steps:
Determining the number of the effective investment targets matched with the preset portraits based on the matched preset portraits of different effective investment targets, and determining the matching degree of the investment behavior data of the investor and the preset portraits by combining the reliability of the investment behavior data of the different effective investment targets matched with the preset portraits.
Further, when the matching degree of the preset portrait and the investment behavior data of the investor is larger than a preset matching degree threshold, determining that the preset portrait is a behavior matching portrait.
S4, constructing the investment portrait of the investor through the matching degree of the behavior matching portrait of the investor and different behavior matching portraits.
Specifically, as shown in fig. 5, the method for constructing the investment portrait of the investor comprises the following steps:
Taking the behavior matching image of the investor with the largest matching degree as an investment image to be selected, judging whether the matching degree of the investment image to be selected is within a preset matching degree range, if so, constructing the investment image of the investor based on the investment image to be selected, and if not, entering the next step;
Taking other behavior matching images except the investment image to be selected as other matching images, determining whether other matching images with the deviation within a preset deviation range exist according to the deviation of the matching degree of the other matching images and the investment image to be selected, if so, entering the next step, and if not, constructing the investment image of the investor based on the investment image to be selected;
And taking other matching images with the deviation within a preset deviation range as similar matching images, determining the credibility of the investment image to be selected of the investor according to the quantity of the similar matching images, the matching degree of different similar matching images and the matching degree of the investment image to be selected, and determining whether the investment image to be selected is the investment image of the investor based on the credibility.
Further, when the candidate investment portrait does not belong to the investment portrait of the investor, the matched preset portrait of the investor is used as the investment portrait of the investor.
In another embodiment, the method for constructing the investment portrait of the investor comprises the following steps:
And taking the behavior matching image of the investor with the largest matching degree as a candidate investment image, and constructing the investment image of the investor based on the candidate investment image.
In another aspect, as shown in FIG. 6, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, the processor executing one of the investor behavior data analysis methods described above when the computer program is run.
The above-mentioned investor behavior data analysis method specifically includes:
basic information data of investors in different dimensions are obtained, and the similarity between the investors and different preset portraits and the matched preset portraits of the investors are determined based on the basic information data;
acquiring investment behavior data of the investor, determining reliability of the investment behavior data of the investor in different investment targets according to similar conditions and data amounts of the investment behavior data of the different investment targets in different dividing time periods, and entering a next step when determining that the investor has an effective investment target based on the reliability;
Determining the operation data similarity of different warehouse holding variation operation times of the investors in the effective investment targets and the preset portrait based on the investment behavior data of the investors in the effective investment targets, and dividing the warehouse holding variation operation times into similar operation times and deviation operation times through the operation data similarity;
Determining similarity evaluation amounts in different divided time periods by the similar operation times in different divided time periods and the operation data similarity of different similar operation times, the deviation operation times and the operation data similarity of different deviation operation times;
Determining the behavior similarity of the effective investment targets and the preset images based on the similarity evaluation amounts in different dividing time periods, and determining the matching degree of the investment behavior data of the investors and the different preset images and the behavior matching portraits by combining the reliability of the investment behavior data of the different effective investment targets;
Taking the behavior matching image of the investor with the largest matching degree as an investment image to be selected, judging whether the matching degree of the investment image to be selected is within a preset matching degree range, if so, constructing the investment image of the investor based on the investment image to be selected, and if not, entering the next step;
Taking other behavior matching images except the investment image to be selected as other matching images, determining whether other matching images with the deviation within a preset deviation range exist according to the deviation of the matching degree of the other matching images and the investment image to be selected, if so, entering the next step, and if not, constructing the investment image of the investor based on the investment image to be selected;
And taking other matching images with the deviation within a preset deviation range as similar matching images, determining the credibility of the investment image to be selected of the investor according to the quantity of the similar matching images, the matching degree of different similar matching images and the matching degree of the investment image to be selected, and determining whether the investment image to be selected is the investment image of the investor based on the credibility.
Through the above embodiments, the present invention has the following beneficial effects:
1. According to the similarity condition of the investment behavior data of different investment targets in different dividing time periods and the data quantity, the reliability of the investment behavior data of the investor in the different investment targets is determined, the difference of the reliability of the investment behavior data caused by the difference of the similarity condition of the investment behavior data of the different investment targets is singly considered, and meanwhile, the reliability of the investment behavior data caused by the difference of the data quantity of the investment behavior data of the investment targets is further combined, so that the reliability of the investment behavior data is accurately estimated.
2. The construction of the investment portrait of the investor is carried out through the behavior matching portrait of the investor and the matching degree of different behavior matching portraits, so that the construction of the investment portrait of the investor from the angle of the matching condition of the investment behavior data of the investor and different behavior matching portraits is realized, the difference of the matching degree of the investment behavior data of the investor and different preset portraits is fully considered, and the construction accuracy of the investment portrait of the investor is ensured.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (10)
1. The investor behavior data analysis method is characterized by comprising the following steps of:
basic information data of investors in different dimensions are obtained, and the similarity between the investors and different preset portraits and the matched preset portraits of the investors are determined based on the basic information data;
acquiring investment behavior data of the investor, determining reliability of the investment behavior data of the investor in different investment targets according to similar conditions and data amounts of the investment behavior data of the different investment targets in different dividing time periods, and entering a next step when determining that the investor has an effective investment target based on the reliability;
determining the behavior similarity of the investor with different preset images and matched preset images of different effective investment targets based on the investment behavior data of the investor with different effective investment targets, and determining the matching degree of the investment behavior data of the investor with different preset images and the behavior matched images by combining the reliability of the investment behavior data of the different effective investment targets;
And constructing the investment portrait of the investor through the matching degree of the behavior matching portrait of the investor and different behavior matching portraits.
2. The investor behavior data analyzing method of claim 1, wherein dimensions of the basic information data include occupation, age, month income, investment years, and academia.
3. The investor behavior data analyzing method of claim 1, wherein the preset portraits include ultra-short line investors, and long term value investors.
4. The method for analyzing the behavior data of investors according to claim 1, wherein the method for determining the similarity between the investors and the preset portraits comprises the steps of:
taking a historical investor divided into preset images as an investor to be matched, and determining the basic information similarity of the investor and different investors to be matched according to basic information data of different dimensionalities of the investor;
dividing the investors to be matched into similar investors and deviation investors based on the basic information similarity, and determining the comprehensive similarity of the similar investors through the number of the similar investors and the basic information similarity of different similar investors and the investors;
determining a comprehensive deviation amount of the deviation investors based on the number of the deviation investors and the basic information similarity of different deviation investors to the investors;
and determining the similarity between the investors and the preset portrait according to the comprehensive similarity and the comprehensive deviation of the similar investors.
5. The investor behavior data analyzing method of claim 4, wherein when the similarity of the preset portraits to the investor meets a requirement, then determining the preset portraits as matching preset portraits of the investor.
6. The investor behavior data analysis method of claim 1, wherein the investment behavior data comprises a number of change-over operations and a time interval between different change-over operations.
7. The method for analyzing the behavior data of investors according to claim 1, wherein the method for determining the reliability of the investment behavior data of investors at investment goals is as follows:
Determining the number of the warehouse holding variation operation times of the investor in the investment targets in different dividing time periods based on the investment behavior data of the investor in the investment targets, and performing the basic reliability of the investment behavior data of the investor according to the number of the warehouse holding variation operation times of the investor in the investment targets in different dividing time periods;
Determining the number of the operation time of the change of the holding bin in different time intervals by the time interval between the different operation time of the change of the holding bin, and determining the operational data credibility of the different time intervals of the division by combining the change of the holding quantity of the different operation time of the change of the holding bin in different time intervals of the division and the time interval between the different operation time of the change of the holding bin;
the reliability of the investment behavior data of the investment target is determined based on the basic reliability of the investment behavior data of the investment target and the operational data reliability of the different divided time intervals.
8. The method for analyzing investor behavior data according to claim 7, wherein the dividing time interval is determined according to a preset time interval of the number of holding variation operations corresponding to different preset portraits.
9. The investor behavior data analyzing method of claim 7, wherein said investment target is determined to be an effective investment target when reliability of investment behavior data of said investment target meets a requirement.
10. A computer system, comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: the processor, when executing the computer program, performs a method of investor behavior data analysis according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410764588.1A CN118350854B (en) | 2024-06-14 | 2024-06-14 | Investor behavior data analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410764588.1A CN118350854B (en) | 2024-06-14 | 2024-06-14 | Investor behavior data analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118350854A true CN118350854A (en) | 2024-07-16 |
| CN118350854B CN118350854B (en) | 2024-08-27 |
Family
ID=91824980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410764588.1A Active CN118350854B (en) | 2024-06-14 | 2024-06-14 | Investor behavior data analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118350854B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118657619A (en) * | 2024-08-22 | 2024-09-17 | 深圳市艾德网络科技发展有限公司 | Investment behavior analysis system based on social network gathering and distributing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140136446A1 (en) * | 2012-04-03 | 2014-05-15 | Ronen Golan | Method and computer readable medium for managing investment portfolios |
| CN110147813A (en) * | 2019-04-04 | 2019-08-20 | 深圳价值在线信息科技股份有限公司 | A kind of user draws a portrait construction method, device, storage medium and server |
| US20190287178A1 (en) * | 2015-09-09 | 2019-09-19 | Francesco Maria Gaini | Personalized investment portfolio |
| CN110990446A (en) * | 2019-12-19 | 2020-04-10 | 国网区块链科技(北京)有限公司 | Intelligent investment and customer retrieval method and device based on investor portrait |
| CN111292118A (en) * | 2020-01-10 | 2020-06-16 | 上海财经大学 | Investor portrait construction method and device based on deep learning |
| CN116797371A (en) * | 2023-05-31 | 2023-09-22 | 河海大学 | Fund combination recommendation method and system based on fund double-portrait mechanism |
-
2024
- 2024-06-14 CN CN202410764588.1A patent/CN118350854B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140136446A1 (en) * | 2012-04-03 | 2014-05-15 | Ronen Golan | Method and computer readable medium for managing investment portfolios |
| US20190287178A1 (en) * | 2015-09-09 | 2019-09-19 | Francesco Maria Gaini | Personalized investment portfolio |
| CN110147813A (en) * | 2019-04-04 | 2019-08-20 | 深圳价值在线信息科技股份有限公司 | A kind of user draws a portrait construction method, device, storage medium and server |
| CN110990446A (en) * | 2019-12-19 | 2020-04-10 | 国网区块链科技(北京)有限公司 | Intelligent investment and customer retrieval method and device based on investor portrait |
| CN111292118A (en) * | 2020-01-10 | 2020-06-16 | 上海财经大学 | Investor portrait construction method and device based on deep learning |
| CN116797371A (en) * | 2023-05-31 | 2023-09-22 | 河海大学 | Fund combination recommendation method and system based on fund double-portrait mechanism |
Non-Patent Citations (2)
| Title |
|---|
| 段刚龙: "基于投资者画像的股票个性化推荐模型研究", 中国博士学位论文全文数据库 信息科技辑, no. 03, 15 March 2024 (2024-03-15) * |
| 熊贇等: "【交易技术前沿】投资者行为数据表示与画像", Retrieved from the Internet <URL:https://www.sohu.com/a/393567170_100006100> * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118657619A (en) * | 2024-08-22 | 2024-09-17 | 深圳市艾德网络科技发展有限公司 | Investment behavior analysis system based on social network gathering and distributing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118350854B (en) | 2024-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118350854B (en) | Investor behavior data analysis method and system | |
| Maldonado et al. | Profit-based feature selection using support vector machines–General framework and an application for customer retention | |
| US11093845B2 (en) | Tree pathway analysis for signature inference | |
| CN107633030B (en) | Credit evaluation method and device based on data model | |
| CN109960808B (en) | Text recognition method, device and equipment and computer readable storage medium | |
| CN111932269B (en) | Equipment information processing method and device | |
| US20120323760A1 (en) | Dynamic loan service monitoring system and method | |
| US20140324752A1 (en) | Data Analysis Computer System and Method For Fast Discovery Of Multiple Markov Boundaries | |
| US10528889B2 (en) | Stereoscopic learning for classification | |
| US20220207420A1 (en) | Utilizing machine learning models to characterize a relationship between a user and an entity | |
| US20210357699A1 (en) | Data quality assessment for data analytics | |
| CN112102049A (en) | Model training method, business processing method, device and equipment | |
| CN114175063B (en) | System and method for adaptive training of machine learning systems | |
| Thakkar et al. | Clairvoyant: AdaBoost with Cost‐Enabled Cost‐Sensitive Classifier for Customer Churn Prediction | |
| CN113159213A (en) | Service distribution method, device and equipment | |
| CN111784053A (en) | Transaction risk detection method, device and readable storage medium | |
| CN111325344A (en) | Method and apparatus for evaluating model interpretation tools | |
| US20230385664A1 (en) | A computer-implemented method for deriving a data processing and inference pipeline | |
| CN118134652A (en) | Asset configuration scheme generation method and device, electronic equipment and medium | |
| CN107274043B (en) | Quality evaluation method and device of prediction model and electronic equipment | |
| CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
| CN115577287B (en) | Data processing method, apparatus and computer readable storage medium | |
| US8744987B1 (en) | Count estimation via machine learning | |
| CN115170838A (en) | Data screening method and device | |
| CN115034400B (en) | Service data processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |