CN113592563A - Fund combination optimization intelligent decision method based on AI algorithm - Google Patents
Fund combination optimization intelligent decision method based on AI algorithm Download PDFInfo
- Publication number
- CN113592563A CN113592563A CN202110965949.5A CN202110965949A CN113592563A CN 113592563 A CN113592563 A CN 113592563A CN 202110965949 A CN202110965949 A CN 202110965949A CN 113592563 A CN113592563 A CN 113592563A
- Authority
- CN
- China
- Prior art keywords
- market
- strategy
- fund
- combination
- investment
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 12
- 230000006872 improvement Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
本发明公开一种基于AI算法的基金组合最优化智能决策方法，包括步骤一、搜集市场特征参数；步骤二、利用人工智能模型寻找市场规律进行策略归类；步骤三、生成多维度、线性及非线性关系并计算排名；步骤四、使用DNC算法模型对规律驱动因素进行筛选；步骤五、建立模型，对市场环境进行判断及预测；步骤六、搜集基金净值数据并计算基金投资权重；本发明基于深度学习和人工智能，结合市场特征数据来计算各个策略在市场环境下的短期预期收益，利用算法来衡量投资策略的相对强弱与风险，策略精确性大大提高，通过前一层的输出来求解有约束的优化问题，可以计算得到每只策略相应的权重，基于DNC模型大大降低了计算量。
The invention discloses an intelligent decision-making method for fund portfolio optimization based on AI algorithm. Non-linear relationship and calculation of ranking; Step 4, use DNC algorithm model to screen the regular driving factors; Step 5, establish a model to judge and predict the market environment; Step 6, collect fund net value data and calculate fund investment weight; the present invention Based on deep learning and artificial intelligence, combined with market characteristic data to calculate the short-term expected returns of each strategy in the market environment, using algorithms to measure the relative strength and risk of investment strategies, the strategy accuracy is greatly improved, through the output of the previous layer to To solve the constrained optimization problem, the corresponding weight of each strategy can be calculated, and the calculation amount can be greatly reduced based on the DNC model.
Description
Technical Field
The invention relates to the technical field of fund combination optimization, in particular to a fund combination optimization intelligent decision method based on an AI algorithm.
Background
At present, the stock market of the financial market in China is in a shock state for a long time, stable income is difficult to obtain along with indexes, the organization degree and the quantitative trading ratio of the market are lower at present, the quantitative trading is a reliable means for obtaining the long-term stable income of the capital market in China, and the quantitative trading has the advantages of large market capacity, scattered risk, stable income and the like;
the method is characterized in that a mean variance method is adopted for processing the optimization problem of investment strategy weight, a trend following strategy is adopted, the predicted income is used for estimating the actual income, the accuracy is poor, the calculated amount is large, and time is consumed, so that the method for optimizing the fund combination based on the AI algorithm is provided for solving the problems in the prior art, the market condition is observed in real time, the strategy configuration weight is dynamically adjusted, and the fund is actively managed.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an AI algorithm-based fund combination optimization intelligent decision method, which is based on deep learning and artificial intelligence, calculates the short-term expected income of each strategy in the market environment by combining market characteristic data, measures the relative strength and risk of investment strategies by using an algorithm, greatly improves the strategy accuracy, solves the constrained optimization problem through the output of the previous layer, can calculate the corresponding weight of each strategy, greatly improves the accuracy of the traditional model based on a DNC model, and solves the problem that a large amount of calculation power is needed when LSTM processing path dependent data.
In order to realize the purpose of the invention, the invention is realized by the following technical scheme: a fund combination optimization intelligent decision method based on an AI algorithm comprises the following steps:
step one, collecting market characteristic parameters, reading market characteristic parameter data and inputting the market characteristic parameter data into a strategy combination module based on an AI algorithm;
step two, observing market conditions in real time, dynamically adjusting strategy configuration weights, searching for market rules, and classifying trading strategies;
step three, generating a multi-dimensional, linear and nonlinear relation, and calculating the ranking;
screening market characteristic parameters and strategy net worth data rule driving factors by using a DNC algorithm model comprising an input layer, a hidden layer and an output layer;
step five, establishing a model, judging and predicting the market environment, adopting a DNC algorithm model, simulating the performance of strategies in different market environments, and generating a strategy combination which can realize the investment target to the maximum extent, specifically
First step of
Inputting the volume price time sequence, the macroscopic economic index time sequence and a group of historical expression time sequence of investment strategies of a stock market, a bond market and a future market, predicting and outputting the expression of each strategy in the next time period, and calculating the mean square error of the predicted expression and the historical actual expression by a discount function;
second step of
Inputting the volume price time sequence and the macroscopic economic index time sequence of a stock market, a bond market and a future market, outputting the optimal strategy combination under the current market environment, giving a maximum withdrawal threshold value of an objective function and solving the investment combination with the maximum profit by a discount function, and giving a minimum profit threshold value of the objective function and solving the investment combination with the minimum withdrawal;
and step six, collecting fund net value data, reading the fund net value data, inputting the fund net value data into a fund analysis module, performing alpha ranking, calculating effective transaction interval area and calculating wind control quality three-dimensional grading ranking on each fund in the same group, and calculating fund investment weight by combining the strategy combination obtained in the step one to the step five.
The further improvement lies in that: the fund trading strategy in the second step comprises 23 strategy items such as stock market neutral basic surface multi-factor strategy, statistical arbitrage strategy and commodity future term structure trading.
The further improvement lies in that: in the step one, the strategy combination module firstly learns and quantifies the performance of the strategies in the strategy big database in the historical market environment, and then calculates by combining with the current market characteristic parameters; the strategy combination module is used for processing investment strategy weight optimization problems, short-term expected income of each strategy under the market environment is calculated through a differentiable computer (DNC) algorithm model and by combining with market characteristic data, constrained optimization problems are solved through the output of the previous layer, and corresponding weights of each strategy are calculated.
The further improvement lies in that: and in the sixth step, when the alpha ranking is executed, strategy grouping is firstly carried out on the sub-funds, then the alpha +0.4 multiplied by the Charpy ratio is executed according to 0.6 multiplied by the year, the income difference of the net value relative to the basic strategy of the group is calculated, and then the obtained data is subjected to in-group ranking.
The further improvement lies in that: when the effective trading interval area is calculated in the sixth step, the daily gain of the fund is firstly calculated to the daily fluctuation rate open-close/high-low of the market index where the fund is located, and then the third-order polynomial regression is calculated on the value: in the curve chart of the cubic polynomial, the curve y is more than 0, and the area of an interval formed by the x axis is the effective transaction interval area, and then the obtained data is subjected to intra-group ranking.
The further improvement lies in that: when the wind control quality is calculated in the sixth step, the daily gain of the fund is calculated for the daily fluctuation rate open-close/high-low of the market index, and then the third-order polynomial regression is calculated for the value: and y is ax ^3+ bx ^2+ cx + d, in the curve chart of the cubic polynomial, the area of an interval formed by the curve y < 0 and the x axis is the potential loss of the wind control quality, and then the obtained data are subjected to intra-group ranking.
The invention has the beneficial effects that: the method is based on deep learning and artificial intelligence algorithms, short-term expected income of each strategy in the market environment is calculated by combining market characteristic data, relative strength and risk of investment strategies are measured by using the algorithms, the strategy accuracy is greatly improved, the constrained optimization problem is solved through the output of the previous layer, corresponding weight of each strategy can be calculated, the problem of simulating actual data environment characteristics is solved based on a DNC model, the algorithms are separated from storage, and the operation speed is greatly increased.
Drawings
FIG. 1 is a diagram of a decision framework of the present invention.
FIG. 2 is a flow chart of a policy combining module according to the present invention.
Detailed Description
In order to further understand the present invention, the following detailed description will be made with reference to the following examples, which are only used for explaining the present invention and are not to be construed as limiting the scope of the present invention.
Example 1
According to fig. 1 and 2, the embodiment provides an intelligent decision method for fund combination optimization based on an AI algorithm, which includes the following steps:
the method comprises the steps of firstly, collecting market volume price characteristics, market macroscopic characteristics and market characteristic parameters of a market microstructure, reading market characteristic parameter data, inputting the market characteristic parameter data into a strategy combination module based on an AI algorithm, wherein the strategy combination module firstly learns and quantifies the performance of strategies in a strategy big database in a historical market environment, and then calculates by combining with the current market characteristic parameters;
the strategy combination module is used for processing the investment strategy weight optimization problem, calculating the short-term expected income of each strategy in the market environment by a differentiable computer in combination with market characteristic data, solving the constrained optimization problem by the output of the previous layer, and calculating to obtain the corresponding weight of each strategy;
step two, observing market conditions in real time, dynamically adjusting strategy configuration weight, searching market rules, and classifying fund trading strategies;
step three, generating a multi-dimensional, linear and nonlinear relation, and calculating the ranking;
screening market characteristic parameters and strategy net value data rule driving factors by using a DNC (differentiable computer) algorithm model comprising an input layer, a hidden layer and an output layer;
step five, establishing a model, judging and predicting the market environment, adopting DNC differentiable computer technology, simulating the performance of strategies in different market environments, and generating a strategy combination which can realize the investment target to the maximum extent, specifically
First step of
Inputting the volume price time sequence, the macroscopic economic index time sequence and a group of historical expression time sequence of investment strategies of a stock market, a bond market and a future market, predicting and outputting the expression of each strategy in the next time period, and calculating the mean square error of the predicted expression and the historical actual expression by a discount function;
second step of
Inputting the volume price time sequence and the macroscopic economic index time sequence of a stock market, a bond market and a future market, outputting the optimal strategy combination under the current market environment, giving a maximum withdrawal threshold value of an objective function and solving the investment combination with the maximum profit by a discount function, and giving a minimum profit threshold value of the objective function and solving the investment combination with the minimum withdrawal;
step six, collecting fund net value data, reading the fund net value data, inputting the fund net value data into a fund analysis module, and carrying out three-dimensional scoring ranking on each fund in the same group:
1) performing alpha ranking, namely performing strategy grouping on the sub-funds, then performing alpha +0.4 (adjustable weight) x sharp ratio according to 0.6 (adjustable weight) x annual execution, calculating the profit difference of the net value relative to the basic strategy of the group, and then performing intra-group ranking on the obtained data;
2) calculating the effective trading interval area, firstly calculating the daily gain of the fund to the daily fluctuation rate open-close/high-low of the market index, and then calculating the value to obtain a cubic polynomial regression: y ^ ax ^3+ bx ^2+ cx + d, in the curve chart of the cubic polynomial, the area of an interval formed by a curve y > 0 and an x axis is the area of an effective transaction interval, and then the obtained data is subjected to intra-group ranking;
3) calculating the wind control quality, namely firstly calculating the daily income of the fund to the daily fluctuation rate open-close/high-low of the market index, and then calculating a cubic polynomial regression for the value: in the curve graph of the cubic polynomial, the area of an interval formed by a curve y < 0 and an x axis is the potential loss of the wind control quality, and then the obtained data is subjected to intra-group ranking;
and calculating fund investment weight by combining the strategy combinations obtained in the first step to the fifth step, wherein the fund analysis module analyzes the strategy structure of each fund by comparing the hedge fund net value with the strategy net value in the quantitative strategy big database.
Example 2
According to fig. 1 and 2, the embodiment provides an intelligent decision method for fund combination optimization based on an AI algorithm, which includes the following steps:
the method comprises the steps of firstly, collecting market volume price characteristics, market macroscopic characteristics and market characteristic parameters of a market microstructure, reading market characteristic parameter data, inputting the market characteristic parameter data into a strategy combination module based on an AI algorithm, wherein the strategy combination module firstly learns and quantifies the performance of strategies in a strategy big database in a historical market environment, and then calculates by combining with the current market characteristic parameters;
the strategy combination module is used for processing the investment strategy weight optimization problem, calculating the short-term expected income of each strategy in the market environment by a differentiable computer in combination with market characteristic data, solving the constrained optimization problem by the output of the previous layer, and calculating to obtain the corresponding weight of each strategy;
step two, observing market conditions in real time, dynamically adjusting strategy configuration weight, searching market rules, and classifying fund trading strategies;
step three, generating a multi-dimensional, linear and nonlinear relation, and calculating the ranking;
screening market characteristic parameters and strategy net value data rule driving factors by using a DNC (differentiable computer) algorithm model comprising an input layer, a hidden layer and an output layer;
step five, establishing a model, judging and predicting the market environment, adopting DNC differentiable computer technology, simulating the performance of strategies in different market environments, and generating a strategy combination which can realize the investment target to the maximum extent, specifically
First step of
Inputting the volume price time sequence, the macroscopic economic index time sequence and a group of historical expression time sequence of investment strategies of a stock market, a bond market and a future market, predicting and outputting the expression of each strategy in the next time period, and calculating the mean square error of the predicted expression and the historical actual expression by a discount function;
second step of
Inputting the volume price time sequence and the macroscopic economic index time sequence of a stock market, a bond market and a future market, outputting the optimal strategy combination under the current market environment, giving a maximum withdrawal threshold value of an objective function and solving the investment combination with the maximum profit by a discount function, and giving a minimum profit threshold value of the objective function and solving the investment combination with the minimum withdrawal;
generating a combination of strategies that best achieves the investment objective, comprising the steps of:
firstly, setting an investment target;
secondly, reading market volume price characteristics, market macroscopic characteristics and market characteristics of a market microstructure, wherein the market volume price characteristics comprise index income, index income kurtosis, skewness, a kiney coefficient of the income rate of each stock, daily fluctuation rate of the volume of each stock, daily sharp of each stock and the daily activity degree of plates; market macro features include currency policy incentives; the market microstructure comprises total passive list quantity, total passive list removing/total passive list hanging and total active list quantity;
and thirdly, generating a strategy combination, and refining the strategy for three times.
Step six, collecting fund net value data, reading the fund net value data, inputting the fund net value data into a fund analysis module, and carrying out three-dimensional scoring ranking on each fund in the same group:
1) performing alpha ranking, namely performing strategy grouping on the sub-funds, then performing alpha +0.4 (adjustable weight) x sharp ratio according to 0.6 (adjustable weight) x annual execution, calculating the profit difference of the net value relative to the basic strategy of the group, and then performing intra-group ranking on the obtained data;
2) calculating the effective trading interval area, firstly calculating the daily gain of the fund to the daily fluctuation rate open-close/high-low of the market index, and then calculating the value to obtain a cubic polynomial regression: y ^ ax ^3+ bx ^2+ cx + d, in the curve chart of the cubic polynomial, the area of an interval formed by a curve y > 0 and an x axis is the area of an effective transaction interval, and then the obtained data is subjected to intra-group ranking;
3) calculating the wind control quality, namely firstly calculating the daily income of the fund to the daily fluctuation rate open-close/high-low of the market index, and then calculating a cubic polynomial regression for the value: in the curve graph of the cubic polynomial, the area of an interval formed by a curve y < 0 and an x axis is the potential loss of the wind control quality, and then the obtained data is subjected to intra-group ranking;
and calculating fund investment weight by combining the strategy combinations obtained in the first step to the fifth step, wherein the fund analysis module analyzes the strategy structure of each fund by comparing the hedge fund net value with the strategy net value in the quantitative strategy big database.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. An AI algorithm-based fund combination optimization intelligent decision method is characterized by comprising the following steps:
step one, collecting a market characteristic parameter time sequence, reading market characteristic parameter data and inputting the market characteristic parameter data into a strategy combination module based on an AI algorithm;
step two, observing market conditions in real time, dynamically adjusting strategy configuration weights, searching for market rules, and classifying trading strategies;
step three, generating a multi-dimensional, linear and nonlinear relation, and calculating the ranking;
screening market characteristic parameters and strategy net worth data rule driving factors by using a DNC algorithm model comprising an input layer, a hidden layer and an output layer;
step five, establishing a model, judging and predicting the market environment, adopting the technology, simulating the performance of the strategy in different market environments, and generating a strategy combination which can realize the investment target to the maximum extent, specifically
First step of
Inputting the volume price time sequence, the macroscopic economic index time sequence and a group of historical expression time sequence of investment strategies of a stock market, a bond market and a future market, predicting and outputting the expression of each strategy in the next time period, and calculating the mean square error of the predicted expression and the historical actual expression by a discount function;
second step of
Inputting the volume price time sequence and the macroscopic economic index time sequence of a stock market, a bond market and a future market, outputting the optimal strategy combination under the current market environment, giving a maximum withdrawal threshold value of an objective function and solving the investment combination with the maximum profit by a discount function, and giving a minimum profit threshold value of the objective function and solving the investment combination with the minimum withdrawal;
and step six, collecting fund net value data, reading the fund net value data, inputting the fund net value data into a fund analysis module, performing alpha ranking, calculating effective transaction interval area and calculating wind control quality three-dimensional grading ranking on each fund in the same group, and calculating fund investment weight by combining the strategy combination obtained in the step one to the step five.
2. The AI algorithm based fund combination optimization intelligent decision method of claim 1, wherein: the market characteristic parameters in the first step comprise a stock market, a bond market, a future market volume price time series, a market macroscopic economic index time series and an investment strategy historical expression time series.
3. The AI algorithm based fund combination optimization intelligent decision method of claim 1, wherein: in the step one, the strategy combination module firstly learns and quantifies the performance of the strategies in the strategy big database in the historical market environment, and then calculates by combining with the current market characteristic parameters; the strategy combination module is used for processing investment strategy weight optimization problems, calculating short-term expected income of each strategy in a market environment by combining DNC and market characteristic data, solving constrained optimization problems by the output of the previous layer, and calculating to obtain the corresponding weight of each strategy.
4. The AI algorithm based fund combination optimization intelligent decision method of claim 1, wherein: and in the sixth step, when the alpha ranking is executed, strategy grouping is firstly carried out on the sub-funds, then the alpha +0.4 multiplied by the Charpy ratio is executed according to 0.6 multiplied by the year, the income difference of the net value relative to the basic strategy of the group is calculated, and then the obtained data is subjected to in-group ranking.
5. The AI algorithm based fund combination optimization intelligent decision method of claim 1, wherein: when the effective trading interval area is calculated in the sixth step, the daily gain of the fund is firstly calculated to the daily fluctuation rate open-close/high-low of the market index where the fund is located, and then the third-order polynomial regression is calculated on the value: in the curve chart of the cubic polynomial, the curve y is more than 0, and the area of an interval formed by the x axis is the effective transaction interval area, and then the obtained data is subjected to intra-group ranking.
6. The AI algorithm based fund combination optimization intelligent decision method of claim 1, wherein: when the wind control quality is calculated in the sixth step, the daily gain of the fund is calculated for the daily fluctuation rate open-close/high-low of the market index, and then the third-order polynomial regression is calculated for the value: and y is ax ^3+ bx ^2+ cx + d, in the curve chart of the cubic polynomial, the area of an interval formed by the curve y < 0 and the x axis is the potential loss of the wind control quality, and then the obtained data are subjected to intra-group ranking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110965949.5A CN113592563A (en) | 2021-08-23 | 2021-08-23 | Fund combination optimization intelligent decision method based on AI algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110965949.5A CN113592563A (en) | 2021-08-23 | 2021-08-23 | Fund combination optimization intelligent decision method based on AI algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113592563A true CN113592563A (en) | 2021-11-02 |
Family
ID=78238995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110965949.5A Pending CN113592563A (en) | 2021-08-23 | 2021-08-23 | Fund combination optimization intelligent decision method based on AI algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592563A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066650A (en) * | 2021-11-19 | 2022-02-18 | 中信证券股份有限公司 | A data processing method and system |
| CN115525556A (en) * | 2022-09-29 | 2022-12-27 | 成都万创科技股份有限公司 | AI decision system testing method and system |
-
2021
- 2021-08-23 CN CN202110965949.5A patent/CN113592563A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066650A (en) * | 2021-11-19 | 2022-02-18 | 中信证券股份有限公司 | A data processing method and system |
| CN115525556A (en) * | 2022-09-29 | 2022-12-27 | 成都万创科技股份有限公司 | AI decision system testing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Enterprise credit risk evaluation based on neural network algorithm | |
| Li et al. | Risk prediction in financial management of listed companies based on optimized BP neural network under digital economy | |
| AU2021106580A4 (en) | Intelligent decision making method for fund portfolio optimization based on AI algorithm | |
| Hussain et al. | Regularized dynamic self-organized neural network inspired by the immune algorithm for financial time series prediction | |
| CN113592563A (en) | Fund combination optimization intelligent decision method based on AI algorithm | |
| Lauguico et al. | A fuzzy logic-based stock market trading algorithm using bollinger bands | |
| Li et al. | Financial risk prediction for listed companies using IPSO-BP neural network | |
| Deng et al. | A hybrid model of dynamic time wrapping and hidden Markov model for forecasting and trading in crude oil market | |
| Li et al. | A medium to long-term multi-influencing factor copper price prediction method based on CNN-LSTM | |
| TW201928844A (en) | Financial correlation prediction system and the method thereof | |
| Sun et al. | Identifying key factors of regional agricultural drought vulnerability using a panel data grey combined method | |
| CN110738565A (en) | Real estate finance artificial intelligence composite risk control model based on data collection | |
| CN118710388A (en) | Method, system and storage medium for constructing credit risk model based on rejection inference | |
| Li et al. | Forex prediction based on SVR optimized by artificial fish swarm algorithm | |
| CN117172381A (en) | Risk prediction method based on big data | |
| CN109711848A (en) | A kind of matching system and its construction method, matching process of financial transaction | |
| CN112418575A (en) | Futures initiative contract quantitative timing decision system based on cloud computing and artificial intelligence deep learning algorithm | |
| KR20240028036A (en) | Machine Learning-Based Cyanobacterial Bloom Prediction System and Method having Appropriate Training-validation Dataset Selecting Unit | |
| Uddin et al. | Comparison of some statistical forecasting techniques with GMDH predictor: A case study | |
| Saman | Scenarios of the romanian GDP evolution with neural models | |
| Anuradha | Stock trend prediction using news headlines | |
| Fu et al. | Prediction of financial economic time series based on group intelligence algorithm based on machine learning | |
| Liu et al. | Exchange rate forecasting method based on particle swarm optimization and probabilistic neural network model | |
| Liu et al. | Research on Renewal Prediction of Life Insurance Policy Based on Back Propagation (BP) Neural Network | |
| Zhang et al. | Analysis of CSI 300 stock index futures price trend based on ARIMA model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211102 |
|
| RJ01 | Rejection of invention patent application after publication |