CN116503174A - Financial data prediction system based on big data - Google Patents
Financial data prediction system based on big data Download PDFInfo
- Publication number
- CN116503174A CN116503174A CN202310753970.8A CN202310753970A CN116503174A CN 116503174 A CN116503174 A CN 116503174A CN 202310753970 A CN202310753970 A CN 202310753970A CN 116503174 A CN116503174 A CN 116503174A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- model
- module
- 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
- 238000010801 machine learning Methods 0.000 claims abstract description 28
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000010276 construction Methods 0.000 claims abstract description 14
- 238000004140 cleaning Methods 0.000 claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000012954 risk control Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A financial data prediction system based on big data comprises a data acquisition module, a data preprocessing module, a feature extraction module, a model construction module, a prediction output module and an investment suggestion module, wherein the data acquisition module acquires stock, foreign exchange and commodity data in a financial market, the data preprocessing module carries out cleaning, normalization and missing value filling operation on the acquired data, the feature extraction module carries out feature extraction on the preprocessed data, the model construction module establishes a financial data prediction model by utilizing a machine learning technology, the prediction output module applies the model to real-time data and outputs a prediction result, and the investment suggestion module provides investment suggestions for investors according to risk preference and investment target factors based on the prediction result. The invention has the beneficial effects that: the machine learning and deep learning technology is utilized to construct a high-efficiency accurate financial data prediction model, and comprehensive and accurate investment advice is provided for investors.
Description
Technical Field
The invention relates to data processing, in particular to a financial data prediction system based on big data.
Background
Big data finance is to collect data such as customer transaction information, network community communication behaviors, fund flow trend and the like through big data technology, and the big data finance is used for knowing the consumption habit of customers, so that different marketing and advertising are put on for different customers or credit conditions of the customers are analyzed. Since big data financial data is collected based on the customer's own behavior. Big data finance is objective and real, so marketing scheme and preference recommendation formulated by big data finance aiming at clients can be accurate. The big data has higher financial matching degree. Financial big data refers to information generated by financial institutions (banks, insurance, securities, etc.), manufacturers (information service providers, etc.), individual payment settlement, stock investment decisions, cost pricing, futures option transactions, bond investments, fund borrowing, currency issue, ticket posting and reimbursement, etc. business transactions and related actions. Financial big data is taken as a subset of big data, is the value which can be used as the asset by the best embodiment data, and can be understood as information reflecting the financial transaction behaviors of people contained in the big data. The financial big data contains a great number of characteristics such as multidimensional, completeness, timeliness and the like, and when people make a decision according to the financial big data, the big data must be screened, judged and predicted by means of artificial intelligent technologies such as machine learning, the Internet of things, block chains and the like.
For large financial data, we need to know the data value correctly, and usually consider that the data value is based on historical data accumulation to feed back objective transaction value, and it is the last development trend of things or the logical relationship of data reaction that is judged. Therefore, for the data in the financial industry, we generally divide the data into four major categories, namely strong financial attribute data, secondary financial attribute data, scene attribute data, analysis and statistical attribute data according to the importance degree of the data value.
The invention aims to provide a financial data prediction system based on big data.
Disclosure of Invention
In view of the foregoing, the present invention aims to provide a financial data prediction system based on big data.
The aim of the invention is realized by the following technical scheme:
a financial data prediction system based on big data comprises a data acquisition module, a data preprocessing module, a feature extraction module, a model construction module, a prediction output module and an investment suggestion module, wherein the data acquisition module acquires stock, foreign exchange and commodity data in a financial market, the data preprocessing module carries out cleaning, normalization and missing value filling operation on the acquired data, the feature extraction module carries out feature extraction on the preprocessed data, the model construction module establishes a financial data prediction model by utilizing machine learning and deep learning technologies, model training is carried out according to the extracted features to obtain an efficient and accurate prediction model, the prediction output module applies the model to real-time data, predicts important indexes in the financial market in real time and outputs a prediction result, and the investment suggestion module provides investment suggestions for investors according to risk preference and investment target factors based on the prediction result.
Preferably, the data collection module collects, collates and processes stock, foreign exchange, commodity data in the financial market, provides base data for subsequent data preprocessing and predictive model training, and obtains data from a plurality of sources, including financial exchanges, financial media, social media, web crawlers.
Preferably, the data acquisition module realizes the functions of data source selection, data acquisition, data storage and data updating, wherein the data source selection selects a proper data source according to the requirements and purposes of a system, and the data source comprises an official website, a financial news website and a social media platform of a financial exchange; the data acquisition, the web crawler technology is utilized to acquire data from a selected data source, a website is automatically accessed, webpage content is grabbed, the data is stored in a database, the quality and the integrity of the data need to be noted in the data acquisition process, and the accuracy of a subsequent prediction model is prevented from being reduced due to data missing or data error; the data storage is used for storing the acquired data into a database so as to facilitate the subsequent preprocessing and model training; the data updating is realized by a timing task and real-time streaming data mode because the data of the financial market changes rapidly and the data needs to be updated in time so as to ensure the accuracy of the prediction model.
Preferably, the data preprocessing module converts the data into a form suitable for processing by a machine learning algorithm through cleaning, integrating, converting and reducing and processing the original data, firstly cleaning the original data, removing invalid data, repeated data, abnormal values and noise to ensure the accuracy and consistency of the data, integrating the data from different data sources into a unified data set so as to facilitate subsequent processing and analysis, converting the original data into a form suitable for processing by the machine learning algorithm, converting text data into numerical data, carrying out data standardization and regularization, reducing the data dimension by using a data dimension reduction technology for high-dimensional data to improve the efficiency and accuracy of the machine learning algorithm, and carrying out filling processing by using a data interpolation method for the data with the missing value.
Preferably, the feature extraction module extracts representative features from the original data, provides important input variables for subsequent prediction model training and prediction, needs to consider the representativeness and the moderate quantity control of the features to improve the accuracy and generalization of the prediction model, picks out the features with important influences on the prediction target from the original data, preprocesses the original features to enable the data to have better interpretability and comparability, combines a plurality of features to construct new features, realizes the feature construction through a mathematical model and a machine learning model method, and needs to reduce the number of the features to a proper range through a feature dimension reduction method for the situation of more features so as to avoid dimension disaster problems, and needs to further screen and adjust the features after feature extraction and dimension reduction so as to ensure the accuracy and representativeness of the features.
Preferably, the model construction module is used for selecting a proper machine learning algorithm, constructing a prediction model, training and optimizing the model, selecting the proper machine learning algorithm according to the type and the data characteristics of the prediction problem before the model is constructed, training the model by using the existing data set after the model is constructed so as to learn model parameters, paying attention to fitting and under-fitting problems in the model training process, adopting an AIC/BIC method to adjust the model parameters, and having a model evaluation function, wherein model evaluation indexes comprise accuracy, recall rate and F1 value, evaluating the model by using an ROC curve, and further optimizing the model by using parameter adjustment and feature engineering technology to improve the prediction effect of the model.
Preferably, the prediction output module applies the prediction model after model training and optimization to new data, outputs a prediction result, visualizes and analyzes the prediction result, applies the trained model to the new data, generates the prediction result, outputs the generated prediction result to a designated position in batch and real time, comprises a database, a file and a message queue, simultaneously, needs to output the interpretability of the prediction result, namely, relates the prediction result to specific data characteristics, helps a user to better understand the prediction result, visualizes the prediction result, comprises a line graph, a histogram, a scatter graph and a thermodynamic diagram, so that the user can more intuitively understand the prediction result, and simultaneously, needs to analyze the prediction result in a common visualization mode, finds rules and abnormal points existing in the prediction result, helps the user to make more accurate decisions, updates and optimizes the prediction model according to the new data and user feedback, comprises parameter adjustment, characteristic engineering and a new algorithm introduction mode, and simultaneously, needs to test and evaluate the new model to ensure better prediction performance.
Preferably, the investment advice module provides personalized investment advice and decision support for the user according to the prediction result and the user demand, analyzes the prediction result generated by the prediction output module, finds out the development trend and the change rule of the market, so as to provide more accurate investment advice for the user, analyzes the investment demand and the preference of the user, knows the risk bearing capacity, the investment target and the time schedule factor of the user, generates personalized investment advice according to the prediction result and the user demand, and advice comprises advice in terms of investment direction, investment time, capital configuration and risk control, and provides prediction of return on investment for the user by analyzing the market trend and the risk factor, wherein the prediction of return on investment helps the user to better know the risk and return of investment so as to make a more intelligent investment decision.
The invention has the beneficial effects that:
(1) The data preprocessing module converts the original data into a form suitable for processing of a machine learning algorithm through cleaning, integrating, converting and reducing the dimension of the original data, converts the text data into numerical data, performs data standardization and regularization, reduces the data dimension of high-dimensional data by using a data dimension reduction technology so as to improve the efficiency and the accuracy of the machine learning algorithm, and performs filling processing on the data with a missing value by using a data interpolation method.
(2) The investment advice module provides personalized investment advice and decision support for the user according to the prediction result and the user demand, analyzes the prediction result generated by the prediction output module, finds out the development trend and the change rule of the market, so as to provide more accurate investment advice for the user, analyzes the investment demand and the preference of the user, knows the risk bearing capacity, the investment target and the time schedule factor of the user, generates personalized investment advice according to the prediction result and the user demand, advice comprises advice in terms of investment direction, investment time, capital configuration and risk control, and provides prediction of investment return for the user by analyzing the market trend and the risk factor, and the investment return prediction helps the user to better know the risk and the income of investment so as to make more intelligent investment decision.
(3) And predicting important indexes in the financial market in real time, outputting a prediction result, and providing investment advice for investors according to risk preference and investment target factors based on the prediction result by the investment advice module.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation on the invention, and other drawings can be obtained by one of ordinary skill in the art without undue effort from the following drawings.
Fig. 1 is a schematic diagram of the structure of the present invention.
Detailed Description
The invention will be further described with reference to the following examples.
A financial data prediction system based on big data comprises a data acquisition module, a data preprocessing module, a feature extraction module, a model construction module, a prediction output module and an investment suggestion module, wherein the data acquisition module acquires stock, foreign exchange and commodity data in a financial market, the data preprocessing module carries out cleaning, normalization and missing value filling operation on the acquired data, the feature extraction module carries out feature extraction on the preprocessed data, the model construction module establishes a financial data prediction model by utilizing machine learning and deep learning technologies, model training is carried out according to the extracted features to obtain an efficient and accurate prediction model, the prediction output module applies the model to real-time data, predicts important indexes in the financial market in real time and outputs a prediction result, and the investment suggestion module provides investment suggestions for investors according to risk preference and investment target factors based on the prediction result.
Preferably, the data collection module collects, collates and processes stock, foreign exchange, commodity data in the financial market, provides base data for subsequent data preprocessing and predictive model training, and obtains data from a plurality of sources, including financial exchanges, financial media, social media, web crawlers.
Preferably, the data acquisition module realizes the functions of data source selection, data acquisition, data storage and data updating, wherein the data source selection selects a proper data source according to the requirements and purposes of a system, and the data source comprises an official website, a financial news website and a social media platform of a financial exchange; the data acquisition, the web crawler technology is utilized to acquire data from a selected data source, a website is automatically accessed, webpage content is grabbed, the data is stored in a database, the quality and the integrity of the data need to be noted in the data acquisition process, and the accuracy of a subsequent prediction model is prevented from being reduced due to data missing or data error; the data storage is used for storing the acquired data into a database so as to facilitate the subsequent preprocessing and model training; the data updating is realized by a timing task and real-time streaming data mode because the data of the financial market changes rapidly and the data needs to be updated in time so as to ensure the accuracy of the prediction model.
Preferably, the data preprocessing module converts the data into a form suitable for processing by a machine learning algorithm through cleaning, integrating, converting and reducing and processing the original data, firstly cleaning the original data, removing invalid data, repeated data, abnormal values and noise to ensure the accuracy and consistency of the data, integrating the data from different data sources into a unified data set so as to facilitate subsequent processing and analysis, converting the original data into a form suitable for processing by the machine learning algorithm, converting text data into numerical data, carrying out data standardization and regularization, reducing the data dimension by using a data dimension reduction technology for high-dimensional data to improve the efficiency and accuracy of the machine learning algorithm, and carrying out filling processing by using a data interpolation method for the data with the missing value.
Preferably, the feature extraction module extracts representative features from the original data, provides important input variables for subsequent prediction model training and prediction, needs to consider the representativeness and the moderate quantity control of the features to improve the accuracy and generalization of the prediction model, picks out the features with important influences on the prediction target from the original data, preprocesses the original features to enable the data to have better interpretability and comparability, combines a plurality of features to construct new features, realizes the feature construction through a mathematical model and a machine learning model method, and needs to reduce the number of the features to a proper range through a feature dimension reduction method for the situation of more features so as to avoid dimension disaster problems, and needs to further screen and adjust the features after feature extraction and dimension reduction so as to ensure the accuracy and representativeness of the features.
Preferably, the model construction module is used for selecting a proper machine learning algorithm, constructing a prediction model, training and optimizing the model, selecting the proper machine learning algorithm according to the type and the data characteristics of the prediction problem before the model is constructed, training the model by using the existing data set after the model is constructed so as to learn model parameters, paying attention to fitting and under-fitting problems in the model training process, adopting an AIC/BIC method to adjust the model parameters, and having a model evaluation function, wherein model evaluation indexes comprise accuracy, recall rate and F1 value, evaluating the model by using an ROC curve, and further optimizing the model by using parameter adjustment and feature engineering technology to improve the prediction effect of the model.
Preferably, the prediction output module applies the prediction model after model training and optimization to new data, outputs a prediction result, visualizes and analyzes the prediction result, applies the trained model to the new data, generates the prediction result, outputs the generated prediction result to a designated position in batch and real time, comprises a database, a file and a message queue, simultaneously, needs to output the interpretability of the prediction result, namely, relates the prediction result to specific data characteristics, helps a user to better understand the prediction result, visualizes the prediction result, comprises a line graph, a histogram, a scatter graph and a thermodynamic diagram, so that the user can more intuitively understand the prediction result, and simultaneously, needs to analyze the prediction result in a common visualization mode, finds rules and abnormal points existing in the prediction result, helps the user to make more accurate decisions, updates and optimizes the prediction model according to the new data and user feedback, comprises parameter adjustment, characteristic engineering and a new algorithm introduction mode, and simultaneously, needs to test and evaluate the new model to ensure better prediction performance.
Preferably, the investment advice module provides personalized investment advice and decision support for the user according to the prediction result and the user demand, analyzes the prediction result generated by the prediction output module, finds out the development trend and the change rule of the market, so as to provide more accurate investment advice for the user, analyzes the investment demand and the preference of the user, knows the risk bearing capacity, the investment target and the time schedule factor of the user, generates personalized investment advice according to the prediction result and the user demand, and advice comprises advice in terms of investment direction, investment time, capital configuration and risk control, and provides prediction of return on investment for the user by analyzing the market trend and the risk factor, wherein the prediction of return on investment helps the user to better know the risk and return of investment so as to make a more intelligent investment decision.
The beneficial effects of this embodiment are: (1) The data preprocessing module converts the original data into a form suitable for processing of a machine learning algorithm through cleaning, integrating, converting and reducing the dimension of the original data, converts the text data into numerical data, performs data standardization and regularization, reduces the data dimension of high-dimensional data by using a data dimension reduction technology so as to improve the efficiency and the accuracy of the machine learning algorithm, and performs filling processing on the data with a missing value by using a data interpolation method. (2) The investment advice module provides personalized investment advice and decision support for the user according to the prediction result and the user demand, analyzes the prediction result generated by the prediction output module, finds out the development trend and the change rule of the market, so as to provide more accurate investment advice for the user, analyzes the investment demand and the preference of the user, knows the risk bearing capacity, the investment target and the time schedule factor of the user, generates personalized investment advice according to the prediction result and the user demand, advice comprises advice in terms of investment direction, investment time, capital configuration and risk control, and provides prediction of investment return for the user by analyzing the market trend and the risk factor, and the investment return prediction helps the user to better know the risk and the income of investment so as to make more intelligent investment decision. (3) And predicting important indexes in the financial market in real time, outputting a prediction result, and providing investment advice for investors according to risk preference and investment target factors based on the prediction result by the investment advice module.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications can be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. A financial data prediction system based on big data comprises a data acquisition module, a data preprocessing module, a feature extraction module, a model construction module, a prediction output module and an investment suggestion module, wherein the data acquisition module acquires stock, foreign exchange and commodity data in a financial market, the data preprocessing module carries out cleaning, normalization and missing value filling operation on the acquired data, the feature extraction module carries out feature extraction on the preprocessed data, the model construction module establishes a financial data prediction model by utilizing machine learning and deep learning technologies, model training is carried out according to the extracted features to obtain an efficient and accurate prediction model, the prediction output module applies the model to real-time data, predicts important indexes in the financial market in real time and outputs a prediction result, and the investment suggestion module provides investment suggestions for investors according to risk preference and investment target factors based on the prediction result.
2. The big data based financial data prediction system of claim 1, wherein the data collection module collects, sorts and processes stock, foreign exchange, commodity data in the financial market, provides base data for subsequent data preprocessing and predictive model training, and the module obtains data from a plurality of sources including financial exchanges, financial media, social media, web crawlers.
3. The financial data prediction system based on big data according to claim 1, wherein the data acquisition module realizes the functions of data source selection, data acquisition, data storage and data updating, wherein the data source selection selects proper data sources according to the requirements and purposes of the system, the data sources comprise official websites, financial news websites and social media platforms of financial exchanges, the data acquisition utilizes a web crawler technology to acquire data from the selected data sources, automatically accesses websites, grabs web page contents and stores the data in a database, and the quality and the integrity of the data need to be paid attention in the data acquisition process, so that the accuracy of a subsequent prediction model is prevented from being reduced due to data loss or data errors; the data storage is used for storing the acquired data into a database so as to facilitate the subsequent preprocessing and model training; the data updating is realized by a timing task and real-time streaming data mode because the data of the financial market changes rapidly and the data needs to be updated in time so as to ensure the accuracy of the prediction model.
4. The system of claim 1, wherein the data preprocessing module converts the data into a form suitable for machine learning algorithm processing by cleaning, integrating, converting, reducing and processing the raw data, firstly cleaning the raw data to remove invalid data, repeated data, abnormal values and noise to ensure the accuracy and consistency of the data, integrating the data from different data sources into a unified data set to facilitate subsequent processing and analysis, converting the raw data into a form suitable for machine learning algorithm processing, converting the text data into numerical data, performing data standardization and regularization, reducing the data dimension for high-dimensional data by using a data dimension reduction technology to improve the efficiency and accuracy of the machine learning algorithm, and performing filling processing for the data with missing values by using a data interpolation method.
5. The financial data prediction system based on big data according to claim 1, wherein the feature extraction module extracts representative features from the original data, provides important input variables for subsequent prediction model training and prediction, the feature extraction module needs to consider the representativeness and the moderate control of the number of the features to improve the accuracy and generalization of the prediction model, picks out the features with important influence on the prediction target from the original data, preprocesses the original features to enable the data to have better interpretability and comparability, combines a plurality of features to construct new features, realizes feature construction through a mathematical model and a machine learning model method, reduces the feature number to a proper range through a feature dimension reduction method for the condition of a large number of features to avoid dimension problems, and further screens and adjusts the features after feature extraction and dimension reduction to ensure the accuracy and representativeness of the features.
6. The financial data prediction system based on big data according to claim 1, wherein the model construction module is used for selecting a proper machine learning algorithm, constructing a prediction model, training and optimizing the model, selecting a proper machine learning algorithm according to the type and data characteristics of the prediction problem before the model is constructed, training the model by using the existing data set after the model is constructed, learning model parameters, paying attention to the over-fitting and under-fitting problem during the model training process, adopting an AIC/BIC method for adjustment, and having a model evaluation function, wherein the model evaluation index comprises an accuracy rate, a recall rate and an F1 value, evaluating the model by using an ROC curve, further optimizing the model, and improving the prediction effect of the model by using parameter adjustment and feature engineering technology.
7. The financial data prediction system based on big data according to claim 1, wherein the prediction output module applies the prediction model trained and optimized by the model to new data, outputs the prediction result, visualizes and analyzes the prediction result, applies the trained model to the new data to generate the prediction result, the prediction application is batched and real-time, outputs the generated prediction result to a designated position, including a database, a file and a message queue, and simultaneously, needs to output the interpretability of the prediction result, namely, relates the prediction result to specific data features, and helps a user to better understand the prediction result, the prediction output module visualizes the prediction result, including a line graph, a histogram, a scatter graph and a thermodynamic diagram, so that the user can more intuitively understand the prediction result, and a common visualization mode, and simultaneously, needs to analyze the prediction result, find rules and abnormal points existing in the prediction result, help the user make more accurate decisions, update and optimize the prediction model according to the new data and user feedback, including parameter adjustment, engineering characteristics, new algorithm introduction and new algorithm, and new model evaluation have better performance.
8. The financial data prediction system based on big data according to claim 1, wherein the investment advice module provides personalized investment advice and decision support for the user according to the prediction result and the user demand, the investment advice module analyzes the prediction result generated by the prediction output module to find out the development trend and the change rule of the market so as to provide more accurate investment advice for the user, analyzes the investment demand and preference of the user, knows the risk bearing capacity, the investment objective and the time schedule factor of the user, generates personalized investment advice according to the prediction result and the user demand, the advice comprises advice in terms of investment direction, investment time, capital configuration and risk control, and provides prediction of return on investment for the user by analyzing the market trend and the risk factor, and the return on investment prediction helps the user to better know the risk and the return of investment so as to make a more intelligent investment decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310753970.8A CN116503174A (en) | 2023-06-26 | 2023-06-26 | Financial data prediction system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310753970.8A CN116503174A (en) | 2023-06-26 | 2023-06-26 | Financial data prediction system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503174A true CN116503174A (en) | 2023-07-28 |
Family
ID=87325169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310753970.8A Pending CN116503174A (en) | 2023-06-26 | 2023-06-26 | Financial data prediction system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503174A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593101A (en) * | 2023-11-30 | 2024-02-23 | 北京聚汇融盛互联网科技有限公司 | Financial risk data processing and analyzing method and system based on multidimensional data |
| CN117688105A (en) * | 2024-02-04 | 2024-03-12 | 成都威世通智能科技有限公司 | High-reliability general artificial intelligence core software algorithm system |
| CN117952185A (en) * | 2024-03-15 | 2024-04-30 | 中国科学技术大学 | Financial field large model training method and system based on multidimensional data evaluation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059896A (en) * | 2019-05-15 | 2019-07-26 | 浙江科技学院 | A kind of Prediction of Stock Index method and system based on intensified learning |
| CN111291925A (en) * | 2020-01-18 | 2020-06-16 | 武汉盛信鸿通科技有限公司 | Financial market prediction and decision-making system and method based on artificial intelligence |
| CN114169998A (en) * | 2021-11-30 | 2022-03-11 | 湖南工商大学 | Financial big data analysis and mining algorithm |
| CN116109280A (en) * | 2023-03-11 | 2023-05-12 | 广东德澳智慧医疗科技有限公司 | Multifunctional financial monitoring and analyzing platform based on intelligent big data and algorithm |
-
2023
- 2023-06-26 CN CN202310753970.8A patent/CN116503174A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059896A (en) * | 2019-05-15 | 2019-07-26 | 浙江科技学院 | A kind of Prediction of Stock Index method and system based on intensified learning |
| CN111291925A (en) * | 2020-01-18 | 2020-06-16 | 武汉盛信鸿通科技有限公司 | Financial market prediction and decision-making system and method based on artificial intelligence |
| CN114169998A (en) * | 2021-11-30 | 2022-03-11 | 湖南工商大学 | Financial big data analysis and mining algorithm |
| CN116109280A (en) * | 2023-03-11 | 2023-05-12 | 广东德澳智慧医疗科技有限公司 | Multifunctional financial monitoring and analyzing platform based on intelligent big data and algorithm |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593101A (en) * | 2023-11-30 | 2024-02-23 | 北京聚汇融盛互联网科技有限公司 | Financial risk data processing and analyzing method and system based on multidimensional data |
| CN117593101B (en) * | 2023-11-30 | 2024-03-22 | 北京聚汇融盛互联网科技有限公司 | Financial risk data processing and analyzing method and system based on multidimensional data |
| CN117688105A (en) * | 2024-02-04 | 2024-03-12 | 成都威世通智能科技有限公司 | High-reliability general artificial intelligence core software algorithm system |
| CN117952185A (en) * | 2024-03-15 | 2024-04-30 | 中国科学技术大学 | Financial field large model training method and system based on multidimensional data evaluation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220343432A1 (en) | Machine learning architecture for risk modelling and analytics | |
| Nazário et al. | A literature review of technical analysis on stock markets | |
| Amani et al. | Data mining applications in accounting: A review of the literature and organizing framework | |
| CN116503174A (en) | Financial data prediction system based on big data | |
| Höglund | Tax payment default prediction using genetic algorithm-based variable selection | |
| US8930254B2 (en) | Financial methodology to valuate and predict the news impact of major events on financial instruments | |
| Tserng et al. | A grey system theory‐based default prediction model for construction firms | |
| CN110689437A (en) | Communication construction project financial risk prediction method based on random forest | |
| CN117455417B (en) | Automatic iterative optimization method and system for intelligent wind control approval strategy | |
| CN102496126A (en) | Custody asset transaction data monitoring equipment | |
| Liu et al. | News tone, investor sentiment, and liquidity premium | |
| Yang et al. | The extraction of early warning features for predicting financial distress based on XGBoost model and shap framework | |
| Arora et al. | Predicting distress: A post insolvency and bankruptcy code 2016 analysis | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
| US20230394582A1 (en) | User interface for guiding actions for desired impact | |
| Moubariki et al. | Enhancing cash management using machine learning | |
| Ardyanta et al. | A prediction of stock price movements using support vector machines in Indonesia | |
| Park et al. | A machine learning-based model for the asymmetric prediction of accounting and financial information | |
| CN115186101A (en) | Investment management back-end system, method, equipment and storage medium | |
| Gök et al. | Dating currency crisis and assessing the determinants based on meta fuzzy index functions | |
| Zhou et al. | Evolution of high-frequency systematic trading: a performance-driven gradient boosting model | |
| Liang | Informativeness of Flexibility in Cash Flows Classification Standards | |
| KR102614106B1 (en) | Apparatus for predicting fluctuation of stock price based on learning model | |
| KR102662354B1 (en) | Method and device for analyzing investment value based on deep learning | |
| CN118071513B (en) | Personalized bank asset management method and system based on artificial intelligence driving |
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: 20230728 |
|
| RJ01 | Rejection of invention patent application after publication |