CN116645217A - Method and device for determining fund fixed casting strategy - Google Patents
Method and device for determining fund fixed casting strategy Download PDFInfo
- Publication number
- CN116645217A CN116645217A CN202310629199.3A CN202310629199A CN116645217A CN 116645217 A CN116645217 A CN 116645217A CN 202310629199 A CN202310629199 A CN 202310629199A CN 116645217 A CN116645217 A CN 116645217A
- Authority
- CN
- China
- Prior art keywords
- fixed
- casting
- fixed casting
- index
- strategy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005266 casting Methods 0.000 title claims abstract description 257
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 60
- 230000008901 benefit Effects 0.000 claims abstract description 34
- 238000012360 testing method Methods 0.000 claims description 45
- 230000009467 reduction Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 230000006872 improvement Effects 0.000 claims description 8
- 230000010365 information processing Effects 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003442 weekly effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
Abstract
The application discloses a method and a device for determining a fixed-casting strategy of a foundation, which can be applied to the field of artificial intelligence and the field of finance, and the method and the device can determine the combined data of a fixed-casting index and benefits according to the fixed-casting strategy information by acquiring the fixed-casting strategy information; training a prediction model by utilizing GA and stacking according to the combined data; predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products; and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy. Therefore, based on a large amount of historical fund transaction data in the system, GA and stacking integrated learning is fused, fund allocation strategies are recommended efficiently, an investment scheme of default optimal benefits is recommended to a user in combination with the risk bearing capacity of the user, the investment scheme is displayed back to a front page, and the user can select default settings through one key or adjust according to own preferences.
Description
Technical Field
The application relates to the technical field of computers, in particular to a method and a device for determining a fund fixed casting strategy.
Background
In the traditional fund financing process, background data analysis and financial condition analysis are carried out on investors by fund managers to formulate an investment risk strategy for each individual investor, and fund combinations conforming to the investment strategy are manually calculated and selected according to the strategy to be recommended to clients.
Currently, for the traditional old policy determination method, when investors perform fund fixed casting, the fixed casting policy is usually set by themselves according to real-time quotation and self experience, so that the method is time-consuming and labor-consuming, and misjudgment is often generated due to insufficient personal experience values; or selecting some fund fixed-throw items set by the APP and selecting fixed-throw strategies recommended by the APP, wherein the fixed-throw strategies are set by the background completely, the data transparency is low, the investment strategies are unclear, and the user experience is poor. The common fixed-throw mode is too simple, and when market fluctuation is large, the risk born by investors is large.
Disclosure of Invention
In view of this, the embodiment of the application provides a method and a device for determining a fund casting strategy, which aim to realize efficient selection of test basis.
In a first aspect, a method for determining a fund routing strategy includes:
the method comprises the steps of obtaining fixed casting strategy information, wherein the fixed casting strategy information is used for representing fixed casting indexes and index ranges selected by a user, and the index types of the fixed casting indexes comprise reduction proportion indexes and improvement proportion indexes;
determining the combination data of the fixed casting index and the benefit according to the fixed casting strategy information;
training a prediction model by utilizing GA and stacking according to the combined data;
predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products;
and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy.
Optionally, the determining, according to the fixed-throw policy information, the combined data of the fixed-throw index and the benefit includes:
acquiring a basic fixed deposit amount set by a user;
determining fixed-throwing strategy information and income information corresponding to the fixed-throwing index selected by the user according to the basic fixed-throwing amount;
and determining the combination data of each fixed casting index and the benefit according to the fixed casting amount and the benefit information.
Optionally, the determining, according to the basic fixed deposit amount, the fixed deposit amount and the profit value corresponding to the fixed deposit index selected by the user includes:
acquiring the number of the fixed throwing indexes;
when the number of the fixed casting indexes is 1, a first fixed casting proportion is obtained according to a first fixed casting index and an index range of the first fixed casting index;
and determining the product of the first fixed proportion and the basic fixed amount as the fixed amount.
Optionally, after the number of the fixed throw indexes is obtained, the method further includes:
when the number of the fixed casting indexes is 2, obtaining a first fixed casting ratio according to a first fixed casting index and an index range of the first fixed casting index;
acquiring a second fixed casting ratio according to the second fixed casting index and the index range of the second fixed casting index;
determining the average value of the first fixed casting ratio and the second fixed casting ratio as a first actual fixed casting ratio;
and determining the product of the first actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount.
Optionally, after the number of the fixed throw indexes is obtained, the method further includes:
when the number of the fixed casting indexes is 3, obtaining the index type and the fixed casting proportion of each fixed casting index;
responding to the condition that the second fixed casting index and the third fixed casting index are the reduction proportion indexes, and acquiring the average value of the second fixed casting index and the third fixed casting index as a second actual fixed casting proportion;
and determining the product of the second actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount.
Optionally, the determining, according to the fixed-throw policy information and the benefit value, the combined data of each fixed-throw index and the benefit includes:
the data cleaning is used for processing the fixed casting strategy information and the profit information, and the abnormal information is deleted;
and carrying out feature extraction on the processed fixed casting strategy information and the profit information according to the fixed casting indexes to obtain the combined data of each fixed casting index and the profit.
Optionally, the training the prediction model according to the combined data using GA and stacking includes:
obtaining a standardized training sample set and a standardized test sample set:
building a Stacking learner:
inputting the standardized training sample set into a Stacking learner to perform training by using a cross-validation method, so as to obtain a trained Stacking learner;
and inputting the standardized test sample set into a trained Stacking integrated classifier for prediction to obtain a prediction result output by the Stacking integrated classifier.
Optionally, the obtaining the standardized training sample set and the test sample set includes:
selecting each fixed casting strategy information of the second product and a benefit value corresponding to each fixed casting strategy information to form an original training sample set; selecting each fixed casting strategy information corresponding to the first product and a benefit value corresponding to each fixed casting strategy information to form an original test sample set;
based on each profit value in the original training sample set and the original test sample set, extracting each fixed casting index as a characteristic to obtain a training sample set and a test sample set which are composed of characteristic vectors;
and normalizing the training and testing sample set obtained by the feature extraction according to the columns to obtain a normalized training sample set and a normalized testing sample set.
Optionally, after the determining that the fixed-throw policy with the highest profit value in the profit value set is the recommended policy, the method further includes:
and responding to the application of the recommendation strategy by the user, acquiring a fixed casting strategy parameter corresponding to the recommendation strategy, and generating a prompt message according to the fixed casting strategy parameter.
In a second aspect, an embodiment of the present application provides a fund fixed-casting policy determining apparatus, where the apparatus includes:
the system comprises a fixed casting strategy information acquisition module, a fixed casting strategy information processing module and a fixed casting strategy information processing module, wherein the fixed casting strategy information is used for representing a fixed casting index and an index range selected by a user, and the index type of the fixed casting index comprises a reduction proportion index and an improvement proportion index;
the combined data determining module is used for determining combined data of the fixed casting index and the benefit according to the fixed casting strategy information;
the prediction model training module is used for training a prediction model by utilizing GA and stacking according to the combined data;
the profit value set determining module is used for predicting the corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products;
and the recommendation strategy determining module is used for determining that the fixed-throwing strategy with the highest profit value in the profit value set is the recommendation strategy.
The embodiment of the application provides a method and a device for determining a fund fixed casting strategy. When the method is executed, fixed casting strategy information is obtained, the fixed casting strategy information is used for representing fixed casting indexes and index ranges selected by a user, and the index types of the fixed casting indexes comprise a reduction proportion index and an improvement proportion index; determining the combination data of the fixed casting index and the benefit according to the fixed casting strategy information; training a prediction model by utilizing GA and stacking according to the combined data; predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products; and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy. Based on a large amount of historical fund transaction data in the system, GA and stacking integrated learning is fused, fund fixed-throwing strategies are recommended, and an investment scheme of default optimal benefits is recommended to a user in combination with the risk bearing capacity of the user, and the investment scheme is displayed back to a front page, so that the user can select default settings by one key or adjust according to own preferences.
Drawings
In order to more clearly illustrate this embodiment or the technical solutions of the prior art, the drawings that are required for the description of the embodiment or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a fund allocation strategy according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for determining a fund allocation strategy according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a device for determining a fund allocation strategy according to an embodiment of the present application;
fig. 4 is a schematic diagram of a flow concept provided in an embodiment of the present application.
Detailed Description
In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As described above, the product functions perform the flow case authoring in the minimum test case set based on the requirements document. And writing an interface test case according to the interface document. However, the inventor finds through research that the existing scheme depends on the correctness of the document and the familiarity of case writers to products, the situations that transaction links are repeatedly covered for a plurality of times and the transaction links are missed in the flow test cases can occur, and the generated test case set is not necessarily optimal; both the accuracy and the comprehensiveness of the interface document may affect the accuracy and comprehensiveness of the interface test cases in the minimum set of test cases.
To solve this problem, a global serial number is acquired when the method is executed, and a transaction panorama is determined according to the global serial number; and determining a test basis according to the transaction panorama. Therefore, according to the node and the transaction link panorama in the transaction panorama, the compiling of the flow test cases and the interface test cases is carried out, and the comprehensiveness and the accuracy of the minimum case set can be ensured. The minimum redundancy of the minimum set of test cases can be ensured based on the number of times the node and transaction link are covered. Through discernment global serial number, record and generate end to end transaction panorama, when node information changes, consult end to end transaction panorama and carry out the delineation of product scope, product inside node scope and end to end transaction panorama, provide reliable test basis for test analysis, avoid the test omission, promote product quality.
The method provided by the embodiment of the application is executed by a bank background system, for example, the method can be executed by a bank background server. The bank background server can be a server device or a server cluster consisting of a plurality of servers.
The fund setting strategy determination method provided by the application is described below through an embodiment. Referring to fig. 1, fig. 1 is a flowchart of a method for determining a fund allocation policy according to an embodiment of the present application, including:
s101: and acquiring the fixed casting strategy information.
The fixed casting strategy information is used for representing the fixed casting indexes and the index ranges selected by the user, and the index types of the fixed casting indexes comprise a reduction proportion index and an improvement proportion index.
When a user selects a certain fund product, the fixed-throwing rule can be defined according to the user requirement and the personal requirement, and the fixed-throwing rule information defined by the current user according to the product is fixed-throwing strategy information.
In an actual application scenario, the user may select a fixed-throw period for the product, which may be divided into daily, weekly, biweekly, monthly, quarterly, etc., and the user may set a specific date for fixed-throw according to personal needs.
S102: and determining the combination data of the fixed casting index and the benefit according to the fixed casting strategy information.
And determining combined data of the fixed casting indexes and the profit values according to the fixed casting strategy information, carrying out unified conversion loading operation on the data, carrying out feature extraction to construct combined data, wherein the combined data is a combined form of the fixed casting indexes and the profit values, and is a presentation form of the fixed casting indexes-the profit, such as characteristic projects and combined characteristic projects of fixed casting period-the profit, fixed casting amount-the profit, average difference-the profit between the fixed casting amount-the profit and a similar product, recent fluctuation-the profit of the foundation, and the like, and then loading the data into a data warehouse.
S103: and training a prediction model according to the combined data by utilizing GA and stacking.
And (3) carrying out model training by combining GA and stacking, combining the trained model with indexes such as mean value difference and the like of similar products of the product recently selected by a user, predicting the recent profit situation of the product under different dosing strategies, and selecting the dosing strategy S with the highest predicted profit for recommending to the user.
Stacking is a hierarchical model integration framework. Taking two layers as an example, firstly, a data set is divided into a training set and a testing set, a plurality of primary learners are obtained by training the training set, then the primary learners are used for predicting the testing set, an output value is used as an input value of training in the next stage, and a final label is used as an output value for training a secondary learner (usually, the last stage uses Logistic regression). Because the training data used twice is different, overfitting can be prevented to some extent. The GA genetic algorithm has good global searching capability, and can quickly search out all solutions in the solution space.
Regarding the predictive model construction and training process in the present application, it can be achieved by: acquiring a standardized training sample set and a standardized test sample set; building a Stacking learner: inputting the standardized training sample set into a Stacking learner to perform training by using a cross-validation method, so as to obtain a trained Stacking learner; and inputting the standardized test sample set into a trained Stacking integrated classifier for prediction to obtain a prediction result output by the Stacking integrated classifier.
Specifically, selecting each fixed casting strategy information of the second product and a benefit value corresponding to each fixed casting strategy information to form an original training sample set; and selecting each fixed casting strategy information corresponding to the first product and the benefit value corresponding to each fixed casting strategy information to form an original test sample set. Based on each profit value in the original training sample set and the original test sample set, extracting each fixed casting index as a characteristic to obtain a training sample set and a test sample set which are composed of characteristic vectors; and normalizing the training and testing sample set obtained by the feature extraction according to the columns to obtain a normalized training sample set and a normalized testing sample set.
In application, the system acquires a standardized training sample set and a standardized test sample set, and the Stacking is a layered model integration framework. Taking two layers as an example, firstly, a data set is divided into a training set and a testing set, a plurality of primary learners are obtained by training the training set, and then the testing set is predicted by the primary learners.
And constructing a Stacking learner, inputting the standardized training sample set into the Stacking learner, and training by using a cross-validation method to obtain the trained Stacking learner. And inputting the standardized test sample set into a trained Stacking integrated classifier for prediction to obtain a prediction result output by the Stacking integrated classifier.
S104: and predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products.
The method comprises the steps that a trained model is combined with indexes such as average value difference of similar products recently selected by a user, recent income conditions of the product under different regular casting strategies are predicted, the regular casting strategy S with highest predicted income is selected to be recommended to the user, when a new user or a stock user selects a new product to invest, the system automatically recommends the regular casting strategy S of the current product as default options, including parameters such as regular casting period, regular casting amount and regular casting proportion, and backfills to a regular casting scheme setting page, and the user can select the default option to be used as a regular casting scheme before trading or modify according to own conditions.
S105: and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy.
In an actual application scene, when a user applies a strategy recommended by a system, the system acquires a fixed-throwing strategy parameter corresponding to the recommended strategy, and generates a prompt message according to the fixed-throwing strategy parameter.
The method for determining the fund casting strategy provided by the embodiment of the application is described in detail below. Referring to fig. 2, fig. 2 is another flow chart of a method for determining a fund allocation policy according to an embodiment of the present application. The specific process is as follows:
s201: and acquiring the fixed casting strategy information.
The fixed casting strategy information is used for representing fixed casting indexes and index ranges selected by a user, and the index types of the fixed casting indexes comprise a reduction proportion index and an improvement proportion index.
S202: a base fixed deposit amount set by the user is obtained.
The user selects a certain fund and defines the rules of throwing. The user selects a fixed casting period which is divided into daily, weekly, biweekly, monthly and quarterly; the user sets a base fixed deposit amount x.
S203: and obtaining the number of the fixed throwing indexes.
The user may select one or more of the indicators to set according to personal habits.
Executing step S204 when the number of the fixed throwing indexes is 1;
executing step S206 when the number of the fixed throwing indexes is 2;
and in response to the fixed number of indicators being 3, executing step S210.
In some possible implementations, the number of custom-made indices is generally described as the user selecting a certain fund, custom-made rules. The user selects a fixed casting period which is divided into daily, weekly, biweekly, monthly and quarterly; setting a basic fixed deposit amount x by a user; the user then selects a dosing regimen.
The optional indexes when setting the fixed-throw scheme are as follows: the foundation product has the advantages that the yield rate, the average value difference with similar products, the historical average value difference with reference indexes and the like, and a user can select one or more indexes for setting according to personal habits; the user also needs to set an index range and a fixed casting ratio w when setting the fixed casting scheme; when a user selects a plurality of indexes at the same time, under the condition of setting a plurality of indexes, when certain indexes correspond to the fixed casting ratio w1>1 and certain indexes correspond to the fixed casting ratio w2<1, if the number of the indexes set by the user is an odd number, taking average by an index weight trend larger than 1/2, and if the number of the indexes is an even number, directly taking average for the fixed casting ratio; finally, the user may choose to apply the targeting scheme to the current fund, a designated plurality of funds, or all of the funds currently held.
S204: and obtaining a first certain casting ratio according to the first certain casting index and the index range of the first certain casting index.
Assuming that the next certain casting date is T days, the user selects an index, namely the yield of the foundation product, and when the yield of the foundation reaches n1% -n2% in a time period T1 before T days, the fixed casting proportion is w1.
S205: and determining the product of the first fixed proportion and the basic fixed amount as the fixed amount.
The fixed amount is the product of the fixed amount and the fixed ratio, namely x is w1.
Step S213 is performed.
S206: and obtaining a first certain casting ratio according to the first certain casting index and the index range of the first certain casting index.
The user can select other indexes at the same time, and when the foundation yield reaches n1% -n2% (the index range of the first certain casting index), the certain casting ratio is w1 (the first certain casting ratio) by taking the steps as the basis for example.
S207: and obtaining a second fixed casting ratio according to the second fixed casting index and the index range of the second fixed casting index.
In a time period T2 before T days, when the mean value difference range of the foundation and the like products reaches m1% -m2% (the index range of the second fixed casting index), setting a fixed casting ratio w2 (the second fixed casting ratio).
S208: and determining the average value of the first fixed proportion and the second fixed proportion as a first actual fixed proportion.
On day T-1, w1>1 and w2<1 are calculated, and the actual fixed ratio w= (w1+w2)/2.
S209: and determining the product of the first actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount.
The product is the fixed amount, in this example x w2. Step S213 is performed.
S210: and obtaining the index type and the fixed casting proportion of each fixed casting index.
And obtaining the types and the proportions of the three fixed casting indexes.
S211: responding to the condition that the second fixed casting index and the third fixed casting index are the reduction proportion indexes, and acquiring the average value of the second fixed casting index and the third fixed casting index as a second actual fixed casting proportion;
in a period T3 before T days, when the range of the difference between the historical average value of the foundation and the reference index reaches k1% -k2%, setting a fixed casting proportion w3, and setting the fixed casting amount as x w3.
On the T-1 day, calculating to obtain w1>1, w2<1, w3<1, wherein the investment proportion tends to be reduced by both index 2 and index 3, and the actual fixed proportion w= (w2+w3)/2 is obtained, and the fixed amount is x w;
if the obtained x is w < = minimum investment amount, the actual fixed deposit amount is the minimum investment amount, and if the obtained x is w > = maximum investment amount, the actual fixed deposit amount is the maximum investment amount.
S212: and determining the product of the second actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount. Step S213 is performed.
S213: and cleaning the fixed casting strategy information and the benefit information by using data, and deleting abnormal information.
For the collected data such as user investment strategies, benefits and the like, as the original data usually has noise and poor formatting, no method is available for directly carrying out data mining and processing, and in order to improve the quality of the data and ensure the prediction accuracy, the collected original data needs to be preprocessed. Firstly, abnormal values, missing values, logic error values and the like in data are collected through data cleaning processing. And carrying out unified conversion loading operation on the data, carrying out feature extraction, constructing feature engineering such as fixed casting period-benefit, fixed casting amount-benefit, average difference-benefit with similar products, recent fluctuation-benefit of funds and the like, and combining the feature engineering, and then loading the data into a data warehouse.
S214: and carrying out feature extraction on the processed fixed casting strategy information and the profit information according to the fixed casting indexes to obtain the combined data of each fixed casting index and the profit.
And carrying out unified conversion loading operation on the data, carrying out feature extraction, constructing feature engineering such as fixed casting period-benefit, fixed casting amount-benefit, average difference-benefit with similar products, recent fluctuation-benefit of funds and the like, and combining the feature engineering, and then loading the data into a data warehouse.
S215: training a prediction model by utilizing GA and stacking according to the combined data;
the training step is described in the first embodiment, and will not be described here.
S216: and predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products.
And predicting the recent income condition of the product under different fixed throwing strategies by combining the trained model with indexes such as average value difference and the like of the recent similar products of the product selected by the user.
S217: and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy.
And when a new product is selected for investment by a subsequent new user or stock user, the system automatically recommends the current fixed-cast strategy S of the product as a default option.
In an actual application scenario, a user can choose to use a default option as a fixed-throw scheme before trading or modify the fixed-throw scheme according to the situation of the user.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a foundation casting policy determining device according to an embodiment of the application.
In this embodiment, the apparatus may include:
the system comprises a fixed casting strategy information acquisition module, a fixed casting strategy information processing module and a fixed casting strategy information processing module, wherein the fixed casting strategy information is used for representing a fixed casting index and an index range selected by a user, and the index type of the fixed casting index comprises a reduction proportion index and an improvement proportion index;
the combined data determining module is used for determining combined data of the fixed casting index and the benefit according to the fixed casting strategy information;
the prediction model training module is used for training a prediction model by utilizing GA and stacking according to the combined data;
the profit value set determining module is used for predicting the corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products;
and the recommendation strategy determining module is used for determining that the fixed-throwing strategy with the highest profit value in the profit value set is the recommendation strategy.
Optionally, the combined data determining module includes:
the basic fixed deposit amount acquisition module is used for acquiring the basic fixed deposit amount set by the user;
the fixed-throwing strategy information and benefit information determining module is used for determining fixed-throwing strategy information and benefit information corresponding to the fixed-throwing index selected by the user according to the basic fixed-throwing amount;
and the combined data determining module is used for determining the combined data of each fixed casting index and the benefit according to the fixed casting amount and the benefit information.
Optionally, the apparatus further includes:
the first fixed casting ratio acquisition module is used for acquiring a first fixed casting ratio according to a first fixed casting index and an index range of the first fixed casting index when the fixed casting index number is 2;
the second fixed casting ratio acquisition module is used for acquiring a second fixed casting ratio according to a second fixed casting index and an index range of the second fixed casting index;
the first actual fixed casting ratio determining module is used for determining that the average value of the first fixed casting ratio and the second fixed casting ratio is the first actual fixed casting ratio;
and the first fixed deposit amount determining module is used for determining that the product of the first actual fixed deposit proportion and the basic fixed deposit amount is the fixed deposit amount.
Optionally, the apparatus further includes:
the index obtaining module is used for obtaining the index type and the fixed casting proportion of each fixed casting index when the fixed casting index number is 3;
the second actual fixed casting ratio determining module is used for responding to the condition that the second fixed casting index and the third fixed casting index are the reduction ratio indexes, and obtaining that the average value of the second fixed casting index and the third fixed casting index is the second actual fixed casting ratio;
and the second fixed deposit amount determining module is used for determining that the product of the second actual fixed deposit proportion and the basic fixed deposit amount is the fixed deposit amount.
Optionally, the prediction model training module includes:
the sample acquisition module is used for acquiring a standardized training sample set and a standardized test sample set:
the learning period construction module is used for constructing a Stacking learner:
the learning period training module is used for inputting the standardized training sample set into the Stacking learner to perform training by using a cross-validation method, so as to obtain a trained Stacking learner;
the prediction result acquisition module is used for inputting the standardized test sample set into the trained Stacking integrated classifier for prediction to obtain a prediction result output by the Stacking integrated classifier.
Optionally, the apparatus further includes:
the prompt message generation module is used for responding to the application of the recommendation strategy by the user, obtaining the fixed-throwing strategy parameters corresponding to the recommendation strategy and generating the prompt message according to the fixed-throwing strategy parameters.
It should be noted that the method and the device for determining the fund fixed casting strategy provided by the application can be used in the artificial intelligence field and the financial field. The foregoing is merely an example, and the application fields of the method and the device for determining the fund casting policy provided by the present application are not limited.
The method and the device for determining the fund throwing strategy provided by the application are described in detail. In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the application can be made without departing from the principles of the application and these modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
Claims (10)
1. A method for determining a fund allocation strategy, comprising:
the method comprises the steps of obtaining fixed casting strategy information, wherein the fixed casting strategy information is used for representing fixed casting indexes and index ranges selected by a user, and the index types of the fixed casting indexes comprise reduction proportion indexes and improvement proportion indexes;
determining the combination data of the fixed casting index and the benefit according to the fixed casting strategy information;
training a prediction model by utilizing GA and stacking according to the combined data;
predicting a corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products;
and confirming that the fixed casting strategy with the highest profit value in the profit value set is a recommended strategy.
2. The method of claim 1, wherein determining combined data of the fixed bid index and the benefit based on the fixed bid strategy information comprises:
acquiring a basic fixed deposit amount set by a user;
determining fixed-throwing strategy information and income information corresponding to the fixed-throwing index selected by the user according to the basic fixed-throwing amount;
and determining the combination data of each fixed casting index and the benefit according to the fixed casting amount and the benefit information.
3. The method according to claim 2, wherein determining, according to the basic fixed amount, fixed-throw policy information and benefit information corresponding to the fixed-throw index selected by the user includes:
acquiring the number of the fixed throwing indexes;
when the number of the fixed casting indexes is 1, a first fixed casting proportion is obtained according to a first fixed casting index and an index range of the first fixed casting index;
and determining the product of the first fixed proportion and the basic fixed amount as the fixed amount.
4. The method of claim 3, wherein after the obtaining the number of indicators, further comprising:
when the number of the fixed casting indexes is 2, obtaining a first fixed casting ratio according to a first fixed casting index and an index range of the first fixed casting index;
acquiring a second fixed casting ratio according to the second fixed casting index and the index range of the second fixed casting index;
determining the average value of the first fixed casting ratio and the second fixed casting ratio as a first actual fixed casting ratio;
and determining the product of the first actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount.
5. The method of claim 4, wherein after the obtaining the number of indicators, further comprising:
when the number of the fixed casting indexes is 3, obtaining the index type and the fixed casting proportion of each fixed casting index;
responding to the condition that the second fixed casting index and the third fixed casting index are the reduction proportion indexes, and acquiring the average value of the second fixed casting index and the third fixed casting index as a second actual fixed casting proportion;
and determining the product of the second actual fixed casting proportion and the basic fixed casting amount as the fixed casting amount.
6. The method of claim 2, wherein determining combined data of each fixed bid index and benefit based on the fixed bid strategy information and the benefit value comprises:
the data cleaning is used for processing the fixed casting strategy information and the profit information, and the abnormal information is deleted;
and carrying out feature extraction on the processed fixed casting strategy information and the profit information according to the fixed casting indexes to obtain the combined data of each fixed casting index and the profit.
7. The method of claim 2, wherein training a predictive model using GA and stacking based on the combined data comprises:
obtaining a standardized training sample set and a standardized test sample set:
building a Stacking learner:
inputting the standardized training sample set into a Stacking learner to perform training by using a cross-validation method, so as to obtain a trained Stacking learner;
and inputting the standardized test sample set into a trained Stacking integrated classifier for prediction to obtain a prediction result output by the Stacking integrated classifier.
8. The method of claim 7, wherein obtaining the normalized training sample set and the test sample set comprises:
selecting each fixed casting strategy information of the second product and a benefit value corresponding to each fixed casting strategy information to form an original training sample set; selecting each fixed casting strategy information corresponding to the first product and a benefit value corresponding to each fixed casting strategy information to form an original test sample set;
based on each profit value in the original training sample set and the original test sample set, extracting each fixed casting index as a characteristic to obtain a training sample set and a test sample set which are composed of characteristic vectors;
and normalizing the training and testing sample set obtained by the feature extraction according to the columns to obtain a normalized training sample set and a normalized testing sample set.
9. The method of claim 7, wherein after the determining that the bid strategy with the highest profit value in the profit value set is the recommended strategy, further comprising:
and responding to the application of the recommendation strategy by the user, acquiring a fixed casting strategy parameter corresponding to the recommendation strategy, and generating a prompt message according to the fixed casting strategy parameter.
10. A fund routing strategy determination device, comprising:
the system comprises a fixed casting strategy information acquisition module, a fixed casting strategy information processing module and a fixed casting strategy information processing module, wherein the fixed casting strategy information is used for representing a fixed casting index and an index range selected by a user, and the index type of the fixed casting index comprises a reduction proportion index and an improvement proportion index;
the combined data determining module is used for determining combined data of the fixed casting index and the benefit according to the fixed casting strategy information;
the prediction model training module is used for training a prediction model by utilizing GA and stacking according to the combined data;
the profit value set determining module is used for predicting the corresponding profit value set of the first product under different fixed casting strategies by combining the prediction model and the average value difference of the similar products;
and the recommendation strategy determining module is used for determining that the fixed-throwing strategy with the highest profit value in the profit value set is the recommendation strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310629199.3A CN116645217A (en) | 2023-05-30 | 2023-05-30 | Method and device for determining fund fixed casting strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310629199.3A CN116645217A (en) | 2023-05-30 | 2023-05-30 | Method and device for determining fund fixed casting strategy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116645217A true CN116645217A (en) | 2023-08-25 |
Family
ID=87618420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310629199.3A Pending CN116645217A (en) | 2023-05-30 | 2023-05-30 | Method and device for determining fund fixed casting strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116645217A (en) |
-
2023
- 2023-05-30 CN CN202310629199.3A patent/CN116645217A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11354747B2 (en) | Real-time predictive analytics engine | |
| US9990678B1 (en) | Systems methods and articles of manufacture for assessing trustworthiness of electronic tax return data | |
| US11354755B2 (en) | Methods systems and articles of manufacture for using a predictive model to determine tax topics which are relevant to a taxpayer in preparing an electronic tax return | |
| Hashim et al. | Expected-loss-based accounting for impairment of financial instruments: The FASB and IASB proposals 2009–2016 | |
| US11257161B2 (en) | Methods and systems for predicting market behavior based on news and sentiment analysis | |
| CN109859052B (en) | Intelligent recommendation method and device for investment strategy, storage medium and server | |
| US10255641B1 (en) | Predictive model based identification of potential errors in electronic tax return | |
| AU2021206811A1 (en) | Methods, systems and computer program products for collecting tax data | |
| Fitzpatrick et al. | How can lenders prosper? Comparing machine learning approaches to identify profitable peer-to-peer loan investments | |
| Ma et al. | A credit risk assessment model of borrowers in P2P lending based on BP neural network | |
| Petrides et al. | Cost-sensitive learning for profit-driven credit scoring | |
| CN113742492A (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
| EP4044094A1 (en) | System and method for determining and managing reputation of entities and industries through use of media data | |
| Hakala | Robo-advisors as a form of artificial intelligence in private customers’ investment advisory services | |
| El Qadi et al. | Feature contribution alignment with expert knowledge for artificial intelligence credit scoring | |
| US20180260903A1 (en) | Computerized machine learning based recommendations | |
| Prorokowski | Validation of the backtesting process under the targeted review of internal models: practical recommendations for probability of default models | |
| Orthaus et al. | Revisiting Constituents’ Reflections on the Incorporation of Day-one Losses into IFRS 9 | |
| CN116645217A (en) | Method and device for determining fund fixed casting strategy | |
| Mihov et al. | Towards Augmented Financial Intelligence | |
| Dellaportas et al. | Modelling volatility asymmetries: a Bayesian analysis of a class of tree structured multivariate GARCH models | |
| Huang et al. | Machine learning and its potential applications in the independent evaluation unit of the green climate fund: A scoping study | |
| Niyazli | Artificial intelligence in Behavioral Finance | |
| US20230394582A1 (en) | User interface for guiding actions for desired impact | |
| Guo et al. | A predictive indicator using lender composition for loan evaluation in P2P lending |
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 |