CN115482106A - Financial product transaction data analysis method and device - Google Patents

Financial product transaction data analysis method and device Download PDF

Info

Publication number
CN115482106A
CN115482106A CN202211157000.3A CN202211157000A CN115482106A CN 115482106 A CN115482106 A CN 115482106A CN 202211157000 A CN202211157000 A CN 202211157000A CN 115482106 A CN115482106 A CN 115482106A
Authority
CN
China
Prior art keywords
transaction
data
specified
daily
time range
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211157000.3A
Other languages
Chinese (zh)
Inventor
李科强
刘涛
张瑾
谢灿
郭伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202211157000.3A priority Critical patent/CN115482106A/en
Publication of CN115482106A publication Critical patent/CN115482106A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention discloses a method and a device for analyzing transaction data of financial products, which relate to the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring daily transaction characteristic data of a specified financial product within a specified time range; determining a weight value of each transaction characteristic data according to a preset mapping relation between the transaction characteristic data and the weight value; normalizing the daily transaction characteristic data; constructing daily transaction feature vectors according to the daily transaction feature data after normalization processing and the weight value of each transaction feature data; generating transaction time sequence data in a specified time range according to the daily transaction feature vector; inputting transaction time sequence data into a transaction data analysis model, and determining a transaction characteristic vector of a specified financial product on a specified date; and performing inverse normalization processing on the transaction characteristic vector on the appointed date to obtain transaction characteristic data of the appointed financial product on the appointed date. The invention can improve the analysis accuracy of the financial product transaction data.

Description

Financial product transaction data analysis method and device
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a financial product transaction data analysis method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, with the development of internet technology, more and more customers are willing to buy financial products such as funds, stocks and the like through financial software, so that the transaction data analysis result of the financial software on the financial products such as the funds, the stocks and the like is a premise for the customers to consider whether to buy the financial products in the software. However, the change of the transaction data of the financial product is easily influenced by various factors, and the existing analysis method of the transaction data of the financial product has low analysis accuracy and cannot provide accurate reference for purchasing the financial product for customers due to the fact that the data characteristics of the financial product are not obvious and timeliness is low.
Disclosure of Invention
The embodiment of the invention provides an analysis method of financial product transaction data, which is used for improving the analysis accuracy of the financial product transaction data and comprises the following steps:
acquiring daily transaction characteristic data of a designated financing product in a designated time range;
determining daily: a weight value for each transaction characteristic data;
normalizing the daily transaction characteristic data;
constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data;
generating transaction time sequence data in a specified time range according to daily transaction feature vectors;
inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the specified date to obtain the transaction characteristic data of the specified financing product on the specified date.
The embodiment of the invention also provides an analysis device for the transaction data of the financial product, which is used for improving the analysis accuracy of the transaction data of the financial product and comprises the following components:
the data acquisition module is used for acquiring daily transaction characteristic data of a specified financial product within a specified time range;
the weight determining module is used for determining the daily: a weight value for each transaction characteristic data;
the first processing module is used for carrying out normalization processing on daily transaction characteristic data;
the second processing module is used for constructing daily transaction feature vectors according to the daily transaction feature data after normalization processing and the weight value of each transaction feature data;
the third processing module is used for generating transaction time sequence data in a specified time range according to the daily transaction characteristic vector;
the vector determination module is used for inputting transaction time sequence data in a specified time range into a pre-trained transaction data analysis model and determining transaction characteristic vectors of specified financial products on specified dates; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
and the fourth processing module is used for performing inverse normalization processing on the transaction characteristic vectors of the specified financing products on the specified dates to obtain the transaction characteristic data of the specified financing products on the specified dates.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the analysis method of the financial product transaction data when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for analyzing transaction data of a financial product is implemented.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method for analyzing transaction data of a financial product.
In the embodiment of the invention, daily transaction characteristic data of a specified financial product in a specified time range is obtained; determining daily: a weight value for each transaction characteristic data; carrying out normalization processing on daily transaction characteristic data; constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data; generating transaction time sequence data in a specified time range according to daily transaction feature vectors; inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range; and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the specified date to obtain the transaction characteristic data of the specified financing product on the specified date. Compared with the existing technical scheme for analyzing the transaction data of the financial product, the daily transaction characteristic vector is constructed through daily transaction characteristic data in a specified time range and the weight value of each transaction characteristic data, the transaction time sequence data in the specified time range generated according to the daily transaction characteristic vector is used as the input of a neural network model, the analysis accuracy of the transaction data of the financial product can be improved, and accurate purchasing reference of the financial product is provided for clients.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart of a method for analyzing transaction data of financial products in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a method for training a transactional data analysis model provided in an embodiment of the invention;
FIG. 3 is a schematic diagram of an apparatus for analyzing transaction data of financial products according to an embodiment of the present invention;
FIG. 4 is a schematic view of another financial product transaction data analysis device provided in an embodiment of the present invention;
fig. 5 is a schematic diagram of a computer device provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
Research shows that with the development of internet technology, more and more customers are willing to buy financial products such as funds, stocks and the like through financial software, so that the analysis result of the transaction data of the financial software on the financial products such as the funds, the stocks and the like is a premise for the customers to consider whether to buy the financial products in the software. However, the change of the transaction data of the financial product is easily influenced by various factors, and the conventional analysis method for the transaction data of the financial product has low analysis accuracy due to the fact that the data characteristics of the financial product are not obvious and the timeliness is low, so that accurate reference for purchasing the financial product cannot be provided for a client.
Aiming at the research, the embodiment of the invention provides an analysis scheme of the financial product transaction data, which can improve the analysis accuracy of the financial product transaction data.
As shown in fig. 1, a flowchart of a method for analyzing transaction data of a financial product according to an embodiment of the present invention may include the following steps:
step 101, acquiring daily transaction characteristic data of a specified financial product within a specified time range;
step 102, determining daily: a weight value for each transaction characteristic data;
103, normalizing the daily transaction characteristic data;
104, constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data;
105, generating transaction time sequence data in a specified time range according to daily transaction feature vectors;
step 106, inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
and step 107, performing inverse normalization processing on the transaction characteristic vectors of the specified financing products on the specified dates to obtain the transaction characteristic data of the specified financing products on the specified dates.
In the embodiment of the invention, daily transaction characteristic data of a specified financial product in a specified time range is obtained; determining daily: a weight value for each transaction characteristic data; carrying out normalization processing on daily transaction characteristic data; constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data; generating transaction time sequence data in a specified time range according to daily transaction feature vectors; inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range; and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the specified date to obtain the transaction characteristic data of the specified financing product on the specified date. Compared with the existing technical scheme for analyzing the transaction data of the financial product, the daily transaction characteristic vector is constructed through daily transaction characteristic data in a specified time range and the weight value of each transaction characteristic data, the transaction time sequence data in the specified time range generated according to the daily transaction characteristic vector is used as the input of a neural network model, the analysis accuracy of the transaction data of the financial product can be improved, and accurate purchasing reference of the financial product is provided for clients.
In the step 101, when analyzing the transaction data of the designated financial product, a designated time range may be set, and daily transaction characteristic data of the designated financial product in the designated time range may be acquired.
In an embodiment of the present invention, the daily transaction characteristic data may include at least one of the following: opening price, closing price, highest price, lowest price, transaction amount.
The specified time range may be a specific time period, for example: from 1 day in 6 months to 30 days in 6 months, the daily transaction characteristic data from 1 day in 6 months to 30 days in 6 months can be acquired; the specified time range may be a time period, for example, the time period is 100 days, and the transaction characteristic data of the current date and 99 days before the current date may be acquired with the current date as an expiration date.
In step 102, a weight value of each daily transaction feature data is determined according to a preset mapping relationship between the transaction feature data and the weight value.
In specific implementation, because the transaction characteristic data of the same type have different degrees of influence on the analysis result of the transaction data of the financial product if the corresponding values are different, different weights can be set for different transaction characteristic data in order to eliminate the influence of different values of the transaction characteristic data of the same type on the analysis result as much as possible. For example, when the daily maximum price is greater than 20, the corresponding weight value may be set to 1; when the daily maximum price is within the range of 10-20, the corresponding weight value is 5; when the daily maximum price is less than 10, the corresponding weight value is 4, and the like.
In step 103, the daily transaction feature data is normalized.
In specific implementation, in order to improve the analysis efficiency of the transaction data of the financial product, each transaction characteristic data can be normalized according to the maximum value and the minimum value of the daily transaction characteristic data.
In step 104, a daily transaction feature vector is constructed according to the daily transaction feature data after the normalization process and the weight value of each transaction feature data.
In step 105, in order to improve the analysis accuracy of the financial product transaction data, transaction time series data in a specified time range needs to be generated according to daily transaction feature vectors.
In particular implementations, the transaction timing data may include: the data dimension, the number of sequences and the data length are both 1, and the data length is determined according to the number of dates contained in the specified time range. For example, if the specified time range is 5 days, the data length is 5.
In step 106, the transaction timing data is input into a pre-trained transaction data analysis model, and the transaction feature vector of the specified financial product on the specified date is determined.
The transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range.
The specified date may be the next day of the current date, and it is understood that the transaction feature vector of the next day of the current date is determined from the transaction sequence data of consecutive days preceding the current date (including the current date).
In the embodiment of the present invention, as shown in fig. 2, the transaction data analysis model may be trained according to the following method:
step 201, acquiring historical transaction data of a plurality of financial products;
step 202, aiming at the historical transaction data of each financial product, the following operations are executed: according to historical transaction time information, dividing historical transaction data, and determining daily historical transaction characteristic data within each specified time range; determining daily in each designated time range according to a preset mapping relation between the transaction characteristic data and the weight value: a weight value for each historical transaction characteristic data; normalizing the daily historical transaction characteristic data within each specified time range; according to the daily historical trading feature data in each specified time range after normalization processing and the weight value of each historical trading feature data, daily historical trading feature vectors in each specified time range are constructed; generating historical trading time sequence data of each appointed time range according to the daily historical trading feature vector in each appointed time range;
step 203, the following of a plurality of financial products: taking historical transaction time sequence data of each appointed time range as sample data, and constructing a training set and a test set;
step 204, training the neural network model by using a training set to obtain a transaction data analysis model;
step 205, the transaction data analysis model is tested by using the test set.
In specific implementation, historical transaction data of a plurality of financial products is acquired, wherein each historical transaction data may include: trade date, opening price, closing price, highest price on the same day, lowest price on the same day, trade volume, financing product code and the like.
In specific implementation, aiming at the historical transaction data of each financial product, the following operations are executed: according to the transaction date (namely historical transaction time information) in each historical transaction data, the historical transaction data is divided, and the daily historical transaction characteristic data in each specified time range is determined. For example, historical transaction data can be sorted according to the time sequence of transaction dates, a sliding window is set according to a specified time range, and then daily historical transaction characteristic data in a first specified time range are sequentially obtained from the sorted historical transaction data according to the sliding window; moving the sliding window backwards for one day to obtain daily historical transaction characteristic data within a second specified time range; and by analogy, moving the sliding window backwards one day each time to obtain daily historical transaction characteristic data in the next specified time range.
After obtaining the daily historical transaction characteristics data in each specified time range, the weight value of each historical transaction characteristics data is determined. For example, the weight value of each historical transaction characteristic data every day in each 100 days is determined according to the preset mapping relation between the transaction characteristic data and the weight value.
In order to improve the analysis efficiency of the financial product, normalization processing needs to be carried out on daily historical transaction characteristic data within each specified time range; then, according to the daily historical transaction characteristic data in each specified time range after normalization processing and the weight value of each historical transaction characteristic data, a daily historical transaction characteristic vector in each specified time range is constructed; and generating historical trading time sequence data of each appointed time range according to the daily historical trading feature vector in each appointed time range.
In specific implementation, after the historical transaction data of each financial product is processed through the steps, historical transaction time sequence data of each financial product in each appointed time range is obtained and used as sample data, and a training set and a test set are constructed according to a preset proportion (such as 3. Training the neural network model by using a training set to obtain a transaction data analysis model; and testing the transaction data analysis model by using the test set. For example, inputting historical transaction time sequence data of each designated time range, outputting historical transaction time sequence data of the next designated time range, wherein the last transaction feature vector in the historical transaction time sequence data of the next designated time range is the predicted transaction feature vector of the next day; and testing the transaction data analysis model according to the predicted transaction characteristic vector of the next day and the real transaction characteristic vector corresponding to the date.
The neural network model in the embodiment of the invention is a circulating neural network model based on a long-term and short-term memory network (LSTM) and can learn the long-term dependence relationship, so that the accuracy of an analysis result can be improved by analyzing the transaction data of a financial product by using the LSTM circulating neural network model.
In the step 107, the transaction feature vector of the specified financial product on the specified date is subjected to inverse normalization processing, so as to obtain the transaction feature data of the specified financial product on the specified date.
In the embodiment of the invention, the transaction characteristic data of the designated financial product in continuous multiple days can be analyzed simultaneously, and the method can be realized by the following steps:
when the transaction characteristic data of a specified financial product on multiple continuous days needs to be analyzed, repeating the following steps until the transaction characteristic data of multiple continuous days is obtained:
removing the transaction characteristic vector of the first day in the transaction time sequence data of the specified time range, taking the determined transaction characteristic vector of the specified financial product on the specified date as the transaction characteristic vector of the last day in the transaction time sequence data of the specified time range, and generating updated transaction time sequence data;
inputting the updated transaction time sequence data into a transaction data analysis model trained in advance, and determining a new transaction characteristic vector of a specified financial product on a specified date;
and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the new specified date to obtain the transaction characteristic data of the specified financing product on the new specified date.
In specific implementation, when transaction characteristic data of a designated financial product on multiple continuous days are analyzed, the transaction characteristic data on the first day needs to be analyzed, then the transaction characteristic data on the first day is added into transaction time sequence data, the transaction characteristic data on the next day is determined, and the like is carried out until the transaction characteristic data on multiple continuous days are obtained.
In this way, the transaction characteristic vector of the first day in the transaction time series data of the specified time range is removed, the determined transaction characteristic vector of the specified financial product on the specified date is used as the transaction characteristic vector of the last day in the transaction time series data of the specified time range, and updated transaction time series data are generated; and determining the new transaction characteristic vector of the specified date of the specified financial product according to the updated transaction time sequence data, so that the accuracy of the analysis result of the transaction data of the financial product can be improved.
In the embodiment of the invention, the transaction characteristic data of continuous multiple days can be displayed in a line chart form, so that a concise, clear and clear transaction data analysis result is provided for a client.
In the technical scheme of the invention, the data acquisition, storage, use, processing and the like all conform to relevant regulations of national laws and regulations.
The embodiment of the invention also provides a device for analyzing the transaction data of the financial product, which is described in the following embodiment. Because the principle of solving the problems of the device is similar to the analysis method of the financial product transaction data, the implementation of the device can refer to the implementation of the analysis method of the financial product transaction data, and repeated parts are not repeated.
As shown in fig. 3, a schematic diagram of an apparatus for analyzing transaction data of financial products according to an embodiment of the present invention may include:
the data acquisition module 301 is used for acquiring daily transaction characteristic data of a specified financial product within a specified time range;
a weight determining module 302, configured to determine, according to a preset mapping relationship between the transaction feature data and the weight value, that: a weight value for each transaction characteristic data;
the first processing module 303 is configured to perform normalization processing on daily transaction characteristic data;
the second processing module 304 is configured to construct a daily transaction feature vector according to the daily transaction feature data after the normalization processing and the weight value of each transaction feature data;
a third processing module 305, configured to generate transaction timing sequence data in a specified time range according to the daily transaction feature vector;
the vector determination module 306 is used for inputting transaction time sequence data in a specified time range into a pre-trained transaction data analysis model and determining transaction characteristic vectors of specified financial products on specified dates; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
the fourth processing module 307 is configured to perform inverse normalization processing on the transaction feature vector of the specified financial product on the specified date to obtain transaction feature data of the specified financial product on the specified date.
In this embodiment of the present invention, as shown in fig. 4, the model training module 401 may further be included, configured to, when the vector determination module inputs transaction timing data in a specified time range into a transaction data analysis model trained in advance, determine that a transaction feature vector of a specified financial product is ahead of a transaction feature vector of a specified date:
acquiring historical transaction data of a plurality of financial products;
for the historical transaction data of each financial product, performing the following operations: according to historical transaction time information, dividing historical transaction data, and determining daily historical transaction characteristic data within each specified time range; determining daily in each specified time range according to a preset mapping relation between the transaction characteristic data and the weight value: a weight value for each historical transaction characteristic data; normalizing the daily historical transaction characteristic data within each specified time range; according to the daily historical trading feature data in each specified time range after normalization processing and the weight value of each historical trading feature data, daily historical trading feature vectors in each specified time range are constructed; generating historical trading time sequence data of each appointed time range according to the daily historical trading feature vector of each appointed time range;
combining: taking historical transaction time sequence data of each appointed time range as sample data, and constructing a training set and a test set;
training the neural network model by using a training set to obtain a transaction data analysis model;
and testing the transaction data analysis model by using the test set.
In the embodiment of the present invention, the method may further include:
when the transaction characteristic data of a designated financial product on multiple continuous days needs to be analyzed, repeating the following steps until the transaction characteristic data of multiple continuous days is obtained:
the third processing module is also used for removing the transaction characteristic vector on the first day in the transaction time sequence data in the specified time range, taking the determined transaction characteristic vector of the specified financial product on the specified date as the transaction characteristic vector on the last day of the transaction time sequence data in the specified time range, and generating updated transaction time sequence data;
the vector determination module is also used for inputting the updated transaction time sequence data into a transaction data analysis model trained in advance and determining a new transaction characteristic vector of the appointed financial product on an appointed date;
and the fourth processing module is also used for carrying out reverse normalization processing on the transaction characteristic vectors of the specified financial products on the new specified dates to obtain the transaction characteristic data of the specified financial products on the new specified dates.
In an embodiment of the present invention, the transaction characteristic data of consecutive days may be displayed in the form of a line graph.
An embodiment of the present invention further provides a computer device, as shown in fig. 5, which is a schematic diagram of the computer device in the embodiment of the present invention, where the computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and capable of being executed on the processor 520, and when the processor 520 executes the computer program 530, the method for analyzing the financial product transaction data is implemented.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the method for analyzing the transaction data of the financial product is realized.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method for analyzing transaction data of a financial product.
In the embodiment of the invention, daily transaction characteristic data of a specified financial product in a specified time range is obtained; determining daily: a weight value for each transaction characteristic data; carrying out normalization processing on daily transaction characteristic data; constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data; generating transaction time sequence data in a specified time range according to daily transaction feature vectors; inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range; and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the specified date to obtain the transaction characteristic data of the specified financing product on the specified date. Compared with the existing technical scheme for analyzing the transaction data of the financial product, the daily transaction characteristic vector is constructed by daily transaction characteristic data in a specified time range and the weight value of each transaction characteristic data, the transaction time sequence data in the specified time range generated according to the daily transaction characteristic vector is used as the input of a neural network model, the analysis accuracy of the transaction data of the financial product can be improved, and the accurate purchase reference of the financial product is provided for a client.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (11)

1. A method for analyzing financial product transaction data, comprising:
acquiring daily transaction characteristic data of a designated financing product in a designated time range;
determining daily: a weight value for each transaction characteristic data;
carrying out normalization processing on daily transaction characteristic data;
constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data;
generating transaction time sequence data in a specified time range according to daily transaction feature vectors;
inputting transaction time sequence data in a specified time range into a transaction data analysis model trained in advance, and determining a transaction characteristic vector of a specified financial product on a specified date; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
and performing inverse normalization processing on the transaction characteristic vector of the specified financing product on the specified date to obtain the transaction characteristic data of the specified financing product on the specified date.
2. The method of claim 1, wherein inputting transaction timing data for a specified time range into a pre-trained transaction data analysis model to determine that a specified financial product precedes a transaction feature vector for a specified date, further comprises:
acquiring historical transaction data of a plurality of financial products;
aiming at the historical transaction data of each financial product, the following operations are carried out: according to historical transaction time information, dividing historical transaction data, and determining daily historical transaction characteristic data within each specified time range; determining daily in each designated time range according to a preset mapping relation between the transaction characteristic data and the weight value: a weight value for each historical transaction characteristic data; normalizing the daily historical transaction characteristic data within each specified time range; according to the daily historical trading feature data in each specified time range after normalization processing and the weight value of each historical trading feature data, daily historical trading feature vectors in each specified time range are constructed; generating historical trading time sequence data of each appointed time range according to the daily historical trading feature vector in each appointed time range;
combining: taking historical transaction time sequence data in each appointed time range as sample data, and constructing a training set and a test set;
training the neural network model by using a training set to obtain a transaction data analysis model;
and testing the transaction data analysis model by using the test set.
3. The method of claim 1, further comprising:
when the transaction characteristic data of a designated financial product on multiple continuous days needs to be analyzed, repeating the following steps until the transaction characteristic data of multiple continuous days is obtained:
removing the transaction characteristic vector of the first day in the transaction time sequence data of the specified time range, taking the determined transaction characteristic vector of the specified financial product on the specified date as the transaction characteristic vector of the last day in the transaction time sequence data of the specified time range, and generating updated transaction time sequence data;
inputting the updated transaction time sequence data into a transaction data analysis model trained in advance, and determining a new transaction characteristic vector of a specified financial product on a specified date;
and performing inverse normalization processing on the transaction characteristic vector of the specified financial product on the new specified date to obtain the transaction characteristic data of the specified financial product on the new specified date.
4. The method of claim 3, wherein the transaction characteristic data for a plurality of consecutive days is presented in the form of a line graph.
5. An apparatus for analyzing transaction data of financial products, comprising:
the data acquisition module is used for acquiring daily transaction characteristic data of a specified financial product within a specified time range;
the weight determining module is used for determining the daily: a weight value for each transaction characteristic data;
the first processing module is used for carrying out normalization processing on daily transaction characteristic data;
the second processing module is used for constructing daily transaction characteristic vectors according to the daily transaction characteristic data after normalization processing and the weight value of each transaction characteristic data;
the third processing module is used for generating transaction time sequence data in a specified time range according to the daily transaction characteristic vector;
the vector determination module is used for inputting transaction time sequence data in a specified time range into a pre-trained transaction data analysis model and determining transaction characteristic vectors of specified financial products on specified dates; the transaction data analysis model is obtained by training a neural network model according to historical transaction time sequence data of a plurality of financial products in each appointed time range;
and the fourth processing module is used for performing inverse normalization processing on the transaction characteristic vectors of the specified financing products on the specified dates to obtain the transaction characteristic data of the specified financing products on the specified dates.
6. The apparatus of claim 5, further comprising a model training module for, when the vector determination module inputs the transaction timing data for a specified time range into the pre-trained transaction data analysis model, determining that the transaction feature vector for a specified financial product is prior to the specified date:
acquiring historical transaction data of a plurality of financial products;
for the historical transaction data of each financial product, performing the following operations: according to historical transaction time information, dividing historical transaction data, and determining daily historical transaction characteristic data within each specified time range; determining daily in each specified time range according to a preset mapping relation between the transaction characteristic data and the weight value: a weight value for each historical transaction characteristic data; normalizing the daily historical transaction characteristic data within each specified time range; according to the daily historical transaction characteristic data in each specified time range after normalization processing and the weight value of each historical transaction characteristic data, daily historical transaction characteristic vectors in each specified time range are constructed; generating historical trading time sequence data of each appointed time range according to the daily historical trading feature vector in each appointed time range;
combining: taking historical transaction time sequence data in each appointed time range as sample data, and constructing a training set and a test set;
training the neural network model by using a training set to obtain a transaction data analysis model;
and testing the transaction data analysis model by using the test set.
7. The apparatus of claim 5, further comprising:
when the transaction characteristic data of a specified financial product on multiple continuous days needs to be analyzed, repeating the following steps until the transaction characteristic data of multiple continuous days is obtained:
the third processing module is also used for removing the transaction characteristic vector on the first day in the transaction time sequence data in the specified time range, taking the determined transaction characteristic vector of the specified financial product on the specified date as the transaction characteristic vector on the last day of the transaction time sequence data in the specified time range, and generating updated transaction time sequence data;
the vector determination module is also used for inputting the updated transaction time sequence data into a transaction data analysis model trained in advance and determining a new transaction characteristic vector of the appointed financial product on an appointed date;
and the fourth processing module is also used for carrying out reverse normalization processing on the transaction characteristic vectors of the specified financial products on the new specified dates to obtain the transaction characteristic data of the specified financial products on the new specified dates.
8. The apparatus of claim 7, wherein the transaction characteristic data for a plurality of consecutive days is presented in the form of a line graph.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 4.
CN202211157000.3A 2022-09-22 2022-09-22 Financial product transaction data analysis method and device Pending CN115482106A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211157000.3A CN115482106A (en) 2022-09-22 2022-09-22 Financial product transaction data analysis method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211157000.3A CN115482106A (en) 2022-09-22 2022-09-22 Financial product transaction data analysis method and device

Publications (1)

Publication Number Publication Date
CN115482106A true CN115482106A (en) 2022-12-16

Family

ID=84394869

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211157000.3A Pending CN115482106A (en) 2022-09-22 2022-09-22 Financial product transaction data analysis method and device

Country Status (1)

Country Link
CN (1) CN115482106A (en)

Similar Documents

Publication Publication Date Title
Golightly et al. Bayesian sequential inference for nonlinear multivariate diffusions
US11915104B2 (en) Normalizing text attributes for machine learning models
CN106650992A (en) Quantitative investment strategy generating method and apparatus
KR20170079161A (en) Target information prediction system using big data and machine learning and method thereof
CN112884569A (en) Credit assessment model training method, device and equipment
CN114581249B (en) Financial product recommendation method and system based on investment risk bearing capacity assessment
CN115730947A (en) Bank customer loss prediction method and device
CN111445025B (en) Method and device for determining hyper-parameters of business model
CN111091466A (en) Method and device for generating asset investment suggestion information and readable storage medium
Vitt et al. The impact of patent activities on stock dynamics in the high-tech sector
CN115482106A (en) Financial product transaction data analysis method and device
CN112200488B (en) Risk identification model training method and device for business object
CN114297052A (en) Test data generation method and device
CN113971495A (en) Daytime batch processing method and device
CN113657656A (en) Loan data analysis and prediction method and device
CN113449923A (en) Multi-model object market quotation prediction method and device
CN112257215A (en) Maximum likelihood estimation solving method and system for product life distribution parameters
CN115375487A (en) Recommendation processing method and device for fund products
Espinosa et al. Leverage Effect on Financial Series using a Bayesian TAR Model
Patnaik et al. Selection problems for application of probit. tobit. logit and maximum likelihood estimation: A methodological issue
CN115631050A (en) Financial product recommendation method and device
CN117078423A (en) Quantitative transaction strategy testing method and device
CN115760373A (en) Method and device for establishing enterprise credit wind control model
CN118246810A (en) Software class discipline competition performance evaluation method and system based on improved dynamic Bayesian network
CN116955623A (en) Related problem recommendation method, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination