CN113327164A - Risk control method and device for futures trading and computer equipment - Google Patents

Risk control method and device for futures trading and computer equipment Download PDF

Info

Publication number
CN113327164A
CN113327164A CN202110554331.XA CN202110554331A CN113327164A CN 113327164 A CN113327164 A CN 113327164A CN 202110554331 A CN202110554331 A CN 202110554331A CN 113327164 A CN113327164 A CN 113327164A
Authority
CN
China
Prior art keywords
risk
trading
futures
data
target
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
CN202110554331.XA
Other languages
Chinese (zh)
Inventor
罗益旺
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.)
Shenzhen Aotongping Technology Co ltd
Original Assignee
Shenzhen Aotongping Technology Co 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 Shenzhen Aotongping Technology Co ltd filed Critical Shenzhen Aotongping Technology Co ltd
Priority to CN202110554331.XA priority Critical patent/CN113327164A/en
Publication of CN113327164A publication Critical patent/CN113327164A/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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Abstract

The embodiment of the invention discloses a risk control method for futures trading, which comprises the steps of determining a target futures trading order needing to be analyzed, and acquiring corresponding historical futures trading data, account historical trading data and futures market data; acquiring network data related to the target futures product through a web crawler and extracting key data; calculating historical trading risk factors, account trading risk factors, market trading risk factors and risk control coefficients, calculating corresponding target risk coefficients, acquiring corresponding risk factors, generating and outputting a risk control report corresponding to the target futures trading order. The embodiment of the invention also provides a risk control device for futures trading and computer equipment. By adopting the embodiment of the invention, the risk of futures trading can be effectively controlled, and the risk of futures trading is reduced.

Description

Risk control method and device for futures trading and computer equipment
Technical Field
The invention relates to the technical field of computers and financial technologies, in particular to a risk control method and device for futures trading and computer equipment.
Background
Since futures trading is a contract trading for forward delivered commodities that is done openly, a large amount of market supply and demand information is concentrated in this market, and different people, from different locations, understand different kinds of information and generate different opinions on forward prices through open bidding forms. The futures trading process is actually a comprehensive reflection of the expectations of supply and demand parties for supply and demand relationship changes and price trends at some future time. The price information has the characteristics of continuity, openness and predictability, and is beneficial to increasing market transparency and improving resource allocation efficiency.
Different people know and market knows from different angles and based on different information, and the understanding of the futures information is different, so that different opinions also exist on the forward price, and under the condition that investment decisions are made and trades are conducted when the futures market fluctuates, irrational decisions or trades exist with greater risks, and the futures can be irretrievable with carelessness.
Disclosure of Invention
In view of the above, it is necessary to provide a risk control method, an apparatus and a computer device for futures trading, which can perform risk control on futures trading and reduce the trading risk of futures trading. .
In a first aspect of the present invention, there is provided a risk control method for futures trading, comprising:
determining a target futures trading order needing to be analyzed, wherein the target futures trading order comprises a target account and a target futures product;
obtaining historical futures trading data corresponding to the target futures products, historical account trading data of a target account and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the market futures data through a preset risk factor calculation model;
calculating a risk control coefficient based on the key data through a preset risk control model;
calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, and acquiring a risk factor corresponding to the target risk coefficient;
and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors.
Optionally, the step of calculating a historical trading risk factor based on the futures historical trading data further includes:
dividing historical transaction data of futures into transaction subdata under multiple transaction dimensions according to a preset data grouping rule, wherein the transaction subdata under the multiple transaction dimensions have data overlapping;
for each transaction dimension:
calculating the risk factor under the transaction dimension according to a pre-constructed risk factor calculation model under the transaction dimension,
calculating an overlap coefficient under the transaction dimension according to a preset overlap coefficient calculation formula according to the data proportion of the overlapped data under the transaction dimension, the transaction dimension data with the overlapped data and the total number of the transaction dimensions;
according to the risk factor and the overlapping coefficient under each transaction dimension, calculating a historical transaction risk factor X according to the following calculation formula1：
Figure BDA0003076483340000021
Wherein k isiAs overlap factor of trading dimension, fiI is the risk factor for the trading dimension, i is the trading dimension.
Optionally, the step of calculating an account transaction risk factor based on the account historical transaction data further includes:
screening out transaction sub-data related to account risk preference from account historical transaction data, and calculating the screened transaction sub-data to obtain a first account risk sub-factor;
screening out transaction sub-data related to the account income preference from the historical transaction data of the account, and calculating the screened transaction sub-data to obtain a second account risk sub-factor;
and taking the first account risk sub-factor and the second account risk sub-factor as the account transaction risk factors.
Optionally, the step of extracting the key data in the network data further includes:
determining at least one keyword corresponding to the target futures product, and screening at least one piece of key data from the network data according to the determined at least one keyword;
through the preset risk control model, the step of calculating the risk control coefficient based on the key data further comprises the following steps:
for each piece of key data, obtaining a classification label corresponding to the key data according to a preset classification model, and calculating a control coefficient of the key data by calculating the product of label values of all classification labels of the key data according to the corresponding relation between the preset classification label and the label value;
determining a first control coefficient by calculating a ratio of a first absolute value of the sum of all positive risk coefficients to a second absolute value of the sum of all negative risk coefficients; determining the larger value of the first absolute value and the second absolute value as a second control coefficient;
and taking the first control coefficient and the second control coefficient as risk control coefficients corresponding to key data.
Optionally, the step of calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient further includes:
calculating a first risk coefficient according to the historical trading risk factor and the market trading risk factor;
calculating a first risk coefficient and a risk control coefficient, and calculating a second risk coefficient;
and calculating a corrected target risk coefficient according to a preset correction function, the account transaction risk factor and the second risk coefficient, wherein the value range of the target risk coefficient is [ -1,1 ].
Optionally, the step of calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient further includes:
determining a migration coefficient under each trading dimension according to the market risk trading factor, and calculating the migration amount according to the weighted sum of the risk factor and the migration coefficient under each trading dimension; calculating a first risk coefficient according to the historical transaction risk factor, the market transaction risk factor, the preset weighted sum of the weighted coefficient quality inspection and the sum of the calculated offset;
calculating the product of the first risk coefficient and the first control coefficient, and dividing the calculated product by the second control coefficient to determine a second risk coefficient;
calculating the product of the second risk coefficient and the first account risk sub-factor, subtracting the second account risk sub-factor and determining a third risk coefficient;
determining a reference value according to the first account risk sub-factor and the second account risk sub-factor, wherein the reference value is used for representing the preference degree of the user corresponding to the target account for the futures risk;
and calculating the target risk coefficient according to the third risk coefficient and the determined reference value by the following calculation formula:
Figure BDA0003076483340000031
wherein Y3 is a third risk coefficient, Q is a reference value, Fr is a target risk coefficient, and the value range of the target risk coefficient is [ -1,1 ].
Optionally, the step of obtaining the risk factor corresponding to the target risk factor further includes:
and in the calculation process of the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient and the target risk factor, extracting data meeting a preset rule according to the calculation process to serve as the risk factor.
Optionally, the step of generating a risk control report corresponding to the target futures trading order based on the futures historical trading data, the account historical trading data, the futures market data, and the key data according to the target risk coefficient and the corresponding risk factor further includes:
determining at least one risk report node according to whether the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient and the target risk factor respectively meet a preset coefficient threshold value set and whether the target risk factor exceeds a first risk threshold value;
acquiring a sub-report template corresponding to at least one risk report node, and generating a corresponding node sub-report according to a target risk coefficient calculation process and used data;
and generating the risk control report according to the target risk coefficient and the node sub-report corresponding to the at least one risk report node.
In a second aspect of the present invention, there is provided a risk control device for futures trading, comprising:
the system comprises an order acquisition module, a target futures trading module and a target futures trading module, wherein the order acquisition module is used for determining a target futures trading order needing to be analyzed, and the target futures trading order comprises a target account and a target futures product;
a data acquisition module, configured to acquire futures historical trading data corresponding to the target futures product, account historical trading data of a target account, and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
the first risk factor calculation module is used for calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the market futures data through a preset risk factor calculation model;
the second risk coefficient calculation module is used for calculating a risk control coefficient based on the key data through a preset risk control model;
a target risk coefficient calculation module, configured to calculate a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor, and the risk control coefficient, and obtain a risk factor corresponding to the target risk coefficient;
and the report generation module is used for generating and outputting a risk control report corresponding to the target futures trading order based on the futures historical trading data, the account historical trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factor.
In a third aspect of the invention, there is provided a computer apparatus comprising a memory and a processor, the memory having executable code which when run on the processor performs the method of:
determining a target futures trading order needing to be analyzed, wherein the target futures trading order comprises a target account and a target futures product;
obtaining historical futures trading data corresponding to the target futures products, historical account trading data of a target account and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the market futures data through a preset risk factor calculation model;
calculating a risk control coefficient based on the key data through a preset risk control model;
calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, and acquiring a risk factor corresponding to the target risk coefficient;
and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors.
The embodiment of the invention has the following beneficial effects:
after the risk control method and device for futures trading and the computer equipment are adopted, under the condition that risk assessment is needed to be carried out on futures trading orders, target futures trading orders needing to be analyzed are determined, wherein the target futures trading orders comprise target accounts and target futures products; then obtaining historical futures trading data corresponding to the target futures products, historical account trading data of the target account and futures market data; acquiring network data related to target futures products through a web crawler, and extracting key data related to target futures trading orders in the network data; after the data acquisition is finished, calculating historical trading risk factors based on the futures historical trading data through a preset risk factor calculation model, calculating account trading risk factors based on the account historical trading data, and calculating market trading risk factors based on the futures market data; calculating a risk control coefficient based on the key data through a preset risk control model; then, according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, calculating a target risk factor corresponding to the target futures trading order, and acquiring a risk factor corresponding to the target risk factor; and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors. That is, for futures trading, before trading or during the continuous holding process of trading, risk situations that may exist in futures trading are evaluated through historical trading data of futures products, futures market data and key data extracted from the network and having an influence on futures, risk preferences of users are evaluated according to the history of accounts currently trading, target risk coefficients for futures products and users are comprehensively evaluated, and risk control reports of risk points included in the analysis process are used for enabling users to not only accurately know the risk situations of current futures trading and specific situations that may cause risks, so as to help users to make decisions on futures trading better, and further reduce the risk of futures trading.
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 other drawings can be obtained by those skilled in the art without creative efforts.
Wherein:
fig. 1 is a schematic flow chart illustrating a risk control method for futures trading in one embodiment;
FIG. 2 is a flow diagram illustrating the process of calculating the historical risk trading factor X1 in one embodiment;
FIG. 3 is a schematic flow chart showing the calculation process of the target risk factor Fr in one embodiment;
fig. 4 is a schematic structural diagram of a risk control device for futures trading in one embodiment;
fig. 5 is a schematic structural diagram of a computer device for executing the risk control method of futures trading in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this embodiment, in order to evaluate and control the risk of futures trading, a risk control method for futures trading is provided to prompt the risk of futures trading and reduce the trading risk of futures trading. In this embodiment, the risk control method for futures trading may be executed by a computer device, for example, a computer device corresponding to a futures trading platform, the computer device may be a system server corresponding to the futures trading platform, or a user terminal (for example, a smart phone or a personal computer) corresponding to a user using the futures trading platform may be used. This embodiment is not limited.
When a user performs futures trading on a futures trading platform or a futures trading counter, risk prediction and reminding are required to be performed on corresponding futures trading before or after the trading. For example, in the case that the user performs futures trading on futures trading software on a mobile phone, or in the case that the user performs futures trading on futures trading software and the futures trading software or on a futures trading counter, after the user selects corresponding futures to be traded and before the user confirms the trading, or after the user performs futures trading, the risk control method for futures trading provided by the embodiment of the present invention is executed to remind the user of possible trading risk in the corresponding futures trading place, so as to determine whether to continue the corresponding futures trading or whether to continue to hold the corresponding futures trading. In another embodiment, during the transaction period of the futures transaction, after a time node required by the user, for example, one month after the futures transaction, the risk control method for futures transaction provided by the embodiment of the present invention may be automatically or actively initiated to perform risk judgment on whether there is any futures transaction to be held continuously, so as to provide decision judgment for the user to perform transaction.
Specifically, referring to fig. 1, the risk control method for futures trading includes steps S101 to S107.
The steps of the risk control method for futures trading described above are described in detail below with reference to fig. 1.
Step S101: determining a target futures trading order needing to be analyzed, wherein the target futures trading order comprises a target account and a target futures product.
Under the condition of risk control analysis of futures trading, acquiring a corresponding target futures trading order needing to be analyzed, wherein the order is a to-be-traded futures trading order or a traded futures order, and performing risk analysis and user reminding on the futures trading order. In the current step, the determined target futures trading order includes account information corresponding to the order (target account corresponding to the current user) and a futures product object (target futures product) for trading. For example, in one target futures trading order 000000001, the target account is "zhangsan" and the target futures product is "futures pingguo". Further, in this embodiment, the target futures trading order further includes other information, such as trading amount, trading time, and the like.
Step S102: obtaining historical futures trading data corresponding to the target futures products, historical account trading data of the target account and futures market data.
After determining the target futures trading order, data related to the target futures trading order (hereinafter, collectively referred to as trading-related data, in this embodiment, the trading-related data includes futures historical trading data, account historical trading data, and key data acquired in step S104 after futures market data) may be acquired according to the corresponding target account and the target futures product, and the acquired trading-related data is used for risk analysis and control.
The futures historical trading data is all historical trading records corresponding to the target futures product, which are searched in the futures trading data according to the target futures product, wherein the trading prices and price fluctuation data of the target futures product are also included, and the attention degree of each investor received by the target futures product before and the price fluctuation situation corresponding to the attention degree can be known according to the futures historical trading data, so that the price fluctuation trend possibly existing after the target futures product can be estimated.
The historical transaction data of the account refers to the transaction data of the target account which currently conducts futures transaction and purchases target futures products and other futures products before, and whether the target account has abundant futures investment experience can be known, so that whether a user corresponding to the target account has certain risk awareness can be judged. For example, users who have a blank futures investment experience have a low risk carrying capacity, and users who have a large amount of futures investment experience and a large investment amount in their accounts have a high risk carrying capacity.
The futures market data refers to all possible data of the whole futures market, because the price fluctuation of one futures is influenced not only by the target futures product, but also by the whole market, and in case of market fan, the trading risk of all futures increases, in this embodiment, the futures market data may include all data of the whole futures market (which may improve the accuracy of risk analysis), may include only the whole trend data of the futures market (which may reduce the data analysis amount), or in order to balance the accuracy and the calculation amount, the futures market data may include the whole trend data of the futures market and data corresponding to the related futures product of the industry or related industry where the target futures product is located.
Step S103: and calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the futures market data through a preset risk factor calculation model.
In step S102, after the data related to the target futures trading order is acquired, the risk calculation based on the futures market can be performed accordingly.
Specifically, in order to more accurately analyze the risk, in this embodiment, there is a need to analyze and calculate the possible risk in multiple dimensions and multiple directions, for example, in this step, corresponding risk factors need to be calculated respectively for the historical futures trading data, the historical account trading data, and the market futures data, so as to ensure the risk assessment in multiple directions and reduce the risk of final futures trading.
In specific implementation, through a preset risk factor calculation model, historical trading risk factors are calculated based on the historical futures trading data, account trading risk factors are calculated based on the historical account trading data, and market trading risk factors are calculated based on the market futures data. It should be noted that the risk factor calculation models corresponding to the calculation of the 3 transaction risk factors may be the same model (for example, a neural network model), or may be 3 different models respectively constructed according to data characteristics, which is not limited in this embodiment as long as the purpose of calculating the risk factors can be achieved.
Specifically, the step S103 further includes: and calculating and analyzing historical futures trading data based on a preset historical risk factor calculation model to obtain corresponding historical trading risk factors so as to evaluate whether trading risk exists in the aspect of the historical trading data of the futures in a target futures trading order.
In specific implementation, the historical transaction data of futures needs to be grouped at first to obtain transaction sub-data under multiple transaction dimensions; it should be noted that the packet here is different from a general data packet, and the general packet is a packet in which data is divided into a plurality of parts and there is no intersection between the data; in this embodiment, since there are also associations between multiple trading dimensions, when data grouping is performed, the related futures history trading data in each trading dimension is selected from the futures history trading data. Then, the data under each transaction dimension are respectively input into the risk factor calculation model under each transaction dimension to obtain the risk factor under each transaction dimension. Moreover, considering that data under multiple transaction dimensions overlap, the result is prevented from being biased by multi-layer evaluation of the data, so that an overlap coefficient under each transaction dimension needs to be output, and then a final historical risk factor corresponding to the historical futures transaction data is calculated according to a preset calculation rule through the overlap coefficient and the risk factor under each transaction dimension.
For example, the multiple trading dimensions include 4 trading dimensions, namely, a futures price fluctuation dimension a, a price change trend dimension B, a futures trading activity dimension C, and a profit case dimension D (the actual trading dimensions may be less than or equal to 4 or more than 4, and only at least 2 trading dimensions are defined herein, so as to facilitate comprehensive evaluation from at least 2 trading dimensions).
After obtaining the historical futures trading data, screening and preprocessing the data to obtain the trading sub-data under the 4 trading dimensions, wherein the data under the 4 trading dimensions are overlapped, and the corresponding overlapping coefficient can be calculated according to the overlapping condition.
Specifically, the overlap coefficient in each trading dimension is calculated according to the data proportion of the overlap data in the trading dimension and how many trading dimensions the overlap data appears in. For example, 20% of data in the trading dimension a is also included in the trading dimension B, and 5% of data is included in the trading dimension C as well as the trading dimension B, so that the overlap coefficient in the trading dimension a is calculated as follows:
the overlap factor is (0.15 × 2+0.05 × 3)/4, where 0.15 and 0.05 are data ratios of the overlap factor in the trading dimension a, 2 and 3 are the number of overlapping data appearing in the trading dimensions, and 4 is the total number of trading dimensions. That is, in a certain trading dimension, the calculation formula of the overlap coefficient k corresponding to the trading dimension is as follows:
Figure BDA0003076483340000091
where N is the total number of transaction dimensions, i characterizes each overlapping datum, MiIs the degree of overlap of the overlapping data, wherein MiIdentifying overlapping data occurrences under multiple transaction dimensionsThe number of overlapping transaction dimensions, p, in the transaction subdata of (1)iThe data volume of all the transaction sub-data under the transaction dimension is the ratio of the overlapping data.
Further, in each transaction dimension, a risk factor calculation model in the transaction dimension is constructed, and the model may be a neural network model (CNN model) to obtain a dimension risk factor in each transaction dimension.
Then, the risk factor in each transaction dimension, and the overlap coefficient, need to be obtained as historical transaction risk factors. Wherein, the calculation of the historical risk trading factor X1 may be:
Figure BDA0003076483340000092
wherein k isiAs overlap factor of trading dimension, fiAnd i is a risk factor of the trading dimension, namely A, B, C and D.
In another embodiment, the historical risk trading factor X1 may be calculated by a neural network model, that is, taking the risk factor in each trading dimension and the overlap coefficient as inputs, and obtaining the output as the historical risk trading factor. Referring specifically to fig. 2, a calculation process and a calculation model for calculating historical risk trading factors from multiple trading dimensions is shown in fig. 2.
Further, the step S103 further includes: and calculating and analyzing historical account transaction data of the target account based on a preset account risk factor calculation model to obtain a corresponding account transaction risk factor so as to evaluate whether the target futures transaction order has transaction risk from the aspect of the account corresponding to the order.
As previously described, the account historical transaction data may indicate a user's preference for risk and an acceptance level for the current account. In this step, the historical transaction data of the account needs to be analyzed and calculated to know the risk acceptance condition and benefit preference condition of the user corresponding to the target account, so as to decide the risk strategy of the subsequent futures transaction.
In this embodiment, the account transaction risk factors include a plurality of account risk factors, with risk being assessed from a plurality of dimensions. Specifically, the calculation of the account transaction risk factor may be considered from multiple dimensions, such as risk acceptance, transaction activity, and revenue preference. In this embodiment, the account trading risk factor represents a risk that is not a direct risk existing in the target futures trading order, represents a risk preference and a risk acceptance condition of a user corresponding to the target account, and can adjust a final risk control policy differently from person to person, instead of outputting the same risk control report for all users.
In particular embodiments, the account transaction risk factors include two sets of account risk sub-factors, one set being a first account risk sub-factor characterizing risk acceptance and preference, and the other set being a second account risk sub-factor characterizing revenue preference. It should be noted that the first account risk sub-factor is obtained by screening (to obtain data related to risk) and preprocessing the historical account transaction data, and then calculating according to a preset calculation model (for example, a neural network model) to obtain a risk factor; the second account risk sub-factor may be obtained by performing calculation according to a preset calculation model (e.g., a neural network model) after screening (obtaining data related to the profit) and preprocessing the historical account transaction data.
Further, the step S103 further includes: and calculating and analyzing the futures market data based on a preset market risk factor calculation model to obtain a corresponding market trading risk factor so as to evaluate whether a target futures trading order has trading risk in terms of market trading.
Futures market data is used to represent risk situations that exist across the futures market as a whole, e.g., a futures market fan overall, or a futures market ramp-up overall; that is, the overall situation of the future market also has a certain influence on the future price trend of the target future products, and therefore, in addition to the risk that the target future products may have themselves, the risk that the market may have as a whole needs to be considered.
Specifically, the futures market data mainly considers the market activity, the overall price trend, and the like to give market risk trading factors based on the futures market data, wherein the specific calculation may be calculated through a neural network model. The neural network model can be compatible with various different data inputs, and in the current step, the diversity of futures market data can be well compatible, so that the risk of the overall futures market on the target futures product can be evaluated.
Compared with the situation that the data are directly and completely divided into a plurality of groups, the integrity of the data in each transaction dimension and the degree of correlation between the data in each transaction dimension can be reserved, so that the complete risk assessment in each transaction dimension can be reserved, and the accuracy of the risk assessment is improved.
Step S104: and acquiring network data related to the target futures product through a web crawler, and extracting key data related to the target futures trading order in the network data.
The risk situations that may exist in the futures market, the historical trading data and the account situation are fully considered in steps S102 and S103, but this is only the risk analysis based on the data of the futures market, and does not consider other factors that may affect the futures price in the future. In this step, it is also necessary to consider whether there are other factors that may affect the price of the target futures product according to international situation, national conditions, market conditions, consumer reactions, enterprise conditions, and the like.
Specifically, in the specific risk analysis, network data related to the target futures product, for example, network data such as news, may be acquired through the web crawler tool; and feature extraction is performed on the network data to obtain key data that may affect the price of the target futures product. For example, drought and flood can raise the price of related agricultural products, and changes in important enterprises in the industry can affect corresponding price changes. In this step, data related to the target futures product and the overall futures market needs to be screened and extracted from the large amount of network data as key data to serve as one of the bases for the risk analysis of the risk that may exist in the target futures product.
In specific implementation, network data is screened through preset keywords; the preset keywords are keywords which are related to target futures products, industries, key enterprises and the like and may affect the futures market or the price of the futures, and key data which may affect the target futures products and the overall futures market can be screened from a large amount of network data through the keywords to be further analyzed in detail. Specifically, for each piece of network data, the similarity corresponding to the preset keyword is calculated, and the piece of network data is used as the key data when the similarity is greater than a preset similarity threshold. It should be noted that, in this step, the similarity depends on the number of keywords where different keywords appear and the frequency of appearance of a single keyword, and whether the keywords are core keywords or other keywords needs to be considered, the core keywords and other keywords are provided with different weight coefficients, and the contribution to the similarity is also different. That is, in the present embodiment, the aforementioned similarity is calculated from the weight coefficient corresponding to the hierarchy (core layer, other layers, etc.) of the appearing keywords, and the number of times the keywords appear, and the number of keywords that appear.
Step S105: and calculating a risk control coefficient based on the key data through a preset risk control model.
The key data is data that may affect the price of the target futures product or the overall futures market, and in this step, all the key data need to be integrated to calculate corresponding risk control coefficients, and the risk control coefficients are used to represent possible risk conditions in all the key data.
In a specific embodiment, for each piece of key data, the risk coefficient of each piece of key data is calculated according to a preset classification model, and then the risk control coefficient corresponding to the key data is calculated according to the risk coefficients of all pieces of key data.
According to a preset classification model, calculating a risk coefficient (the risk coefficient is a coefficient between-1 and 1) of the key data as follows:
inputting the key data into a preset classification model, and acquiring a corresponding classification label, wherein the classification label comprises one of a forward action, a reverse action and a non-directional action; one of enterprise data, industry data, market data; degree of action labels (expressed as a number between 0 and 1), and so forth. And then calculating corresponding risk coefficients based on a preset risk coefficient calculation formula according to the label values corresponding to the classification labels.
The label values corresponding to the forward action, the reverse action and the non-directional action are 1, -1 and +/-0.1, the label values corresponding to the enterprise data, the industry data and the market data are 0.1, 1 and 0.5, and when the risk coefficient c of the key data is calculated, the calculation can be performed according to the product of all the classification labels corresponding to the key data and the preset risk constant is multiplied (or other calculation modes can be performed, for example, calculation is performed according to a neural network model).
And calculating the risk control coefficients corresponding to the key data according to the risk coefficients c corresponding to all the key data, wherein in the specific calculation, the absolute value of the sum of the values taking positive numbers in all the risk coefficients and the absolute value of the sum of the values taking negative numbers in all the risk coefficients are respectively calculated, and then the ratio of the absolute values and the absolute value is calculated as the benefit risk ratio, so that the ratio (first control coefficient) between the benefit availability and the risk possibility is represented, and the larger the ratio is, the smaller the risk is, and vice versa, the smaller the ratio is, the larger the risk is. And, the larger of the 2 absolute values is taken as a risk basis value (second control coefficient), which represents the contribution value of the key data to the risk assessment, and the larger the risk basis value is, the greater the corresponding accuracy of the risk assessment is. And further, taking the income risk ratio and the risk basic value as risk control coefficients corresponding to the key data.
It should be noted that, the steps S102 to S103 and the steps S104 to S105 are not related to each other, and the steps S102 to S103 may be executed first and then the steps S104 to S105 may be executed, the steps S104 to S105 may be executed first and then the steps S102 to S103 may be executed, or the steps S102 to S103 and S104 to S105 may be executed simultaneously; steps S102-S103 and steps S104-S105 are performed after step S101 and before step S106.
After the risk factors (historical trading risk factors, account trading risk factors and market trading risk factors) corresponding to the target futures trading order are obtained in the previous steps and the risk control coefficients corresponding to the key data of the target futures product are obtained, the final risk control coefficients can be calculated, so that the final risk analysis and control of futures trading can be obtained.
Step S106: and calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, and acquiring a risk factor corresponding to the target risk coefficient.
The historical trading risk factor and the market trading risk factor characterize the risk condition that the target futures product may have, and the risk control coefficient is a coefficient corresponding to a factor that the future market may be affected by.
In a particular embodiment, the initial risk factor (factor 1+ historical trading risk factor + factor 2+ market trading risk factor) risk control factor. Further, in order to consider the preferences of the income and the risk of the target account, the initial risk coefficient is processed, specifically, the initial risk coefficient is normalized according to the account transaction risk factor to obtain the target risk coefficient with the value between-1 and 1.
In other embodiments, historical transaction risk factors, account transaction risk factors, market transaction risk factors and the risk control coefficients can be input into a preset neural network model, and the output result with the value between-1 and 1 is obtained and used as the target risk coefficient. Specifically, referring to fig. 3, in the neural network model, the historical transaction risk factor and the account transaction risk factor are input into a first-layer neural network submodel, then a first risk coefficient and a risk control coefficient output from the first neural network submodel are input into a second-layer neural network submodel, and then a second risk coefficient output from the second-layer neural network submodel and the account transaction risk factor are input into a third-layer neural network submodel, so as to obtain an output target risk factor.
Specifically, the first risk coefficient Y1 is calculated as follows:
Y1＝α1·X1+α3·X3+X13
where α 1 and α 3 are weighting coefficients (i.e., the aforementioned coefficient 1 and the aforementioned technique 2), α 1+ α 3 is 1, X1 is a historical risk trading factor, and X3 is a market risk trading factor. Further, in this embodiment, X13 is an offset based on the historical risk trading factor and the market risk trading factor.
Specifically, the offset X13 is calculated based on the correlation between the futures market data and the futures historical trading data. Specifically, risk factor f under each trading dimension in the process of calculating the historical risk trading factor through the market risk trading factoriIs processed to obtain a corresponding offset X13. For example, in 4 trading dimensions, namely, a futures price fluctuation dimension a, a price change trend dimension B, a futures trading activity dimension C and an income situation dimension D, the higher the value of X3, the higher the risk, the higher the possibility of fluctuation of the futures price and the activity, and therefore, the offset coefficient θ corresponding to each trading dimension needs to be calculated according to the market risk trading factor X3iThe offset X13 is then calculated according to the following equation:
X13＝∑iθifi。
the second risk coefficient Y2 is then calculated by the following calculation:
Figure BDA0003076483340000131
wherein the content of the first and second substances,
Figure BDA0003076483340000132
for the first control factor comprised by the risk control factor X4,
Figure BDA0003076483340000133
β is a constant coefficient, which is a second control coefficient included in the risk control coefficient X4.
Before calculating the target risk coefficient Fr, a third risk coefficient Y3 also needs to be calculated:
Figure BDA0003076483340000134
wherein the content of the first and second substances,
Figure BDA0003076483340000135
for the first account risk sub-factor contained by the account transaction risk factor X2,
Figure BDA0003076483340000136
before the second account risk sub-factor included in the account transaction risk factor X2 is obtained and the target risk factor Fr is obtained, in order to facilitate the risk factor corresponding to each futures transaction, normalization processing needs to be performed according to the account transaction risk factor X2, that is, according to the account transaction risk factor X2
Figure BDA0003076483340000137
A first account risk sub-factor,
Figure BDA0003076483340000138
Determining a reference value Q corresponding to a condition of relatively balanced risk and income by using the second account risk sub-factor, and then carrying out normalization processing on a third risk coefficient Y3 according to the reference value Q:
Figure BDA0003076483340000139
therefore, the value range of the obtained Fr is between-1 and 1, and the possible risk of the futures exchange can be well quantified.
The target risk factor represents the amount of risk that the target futures trading order may present. However, this data can only represent the magnitude of one risk, and it may be difficult for the user to decide if only the target risk factor is given, so in this embodiment, not only the target risk factor but also a corresponding report needs to be given. Specifically, in this step, in the calculation process of the above steps S102 to S106, not only the corresponding risk coefficient needs to be calculated, but also a forward factor and a backward factor having a larger target risk coefficient need to be obtained as risk factors, where the risk factors include screened partial data of the futures historical trading data, the account historical trading data, the futures market data, and the key data.
Specifically, in the process of calculating the historical risk transaction factors, whether the risk factors are extracted or not is determined according to whether the risk factors under each transaction dimension meet a preset value interval or not, that is, under the condition that the risk factors calculated under each transaction dimension are too high or too low, corresponding data are extracted as the risk factors, so that the corresponding revenue data and risk data are notified to the user in the generation stage of the risk control report.
And in the process of calculating the account risk transaction factor, determining whether to extract the risk factor according to whether the first account risk sub-factor and the second account risk sub-factor meet a preset value interval.
In the subsequent calculation processes of market risk trading, risk control coefficients and the like, whether corresponding data are extracted as risk factors is determined according to whether each intermediate data and the final data meet a preset value interval, and corresponding data with obviously improved or reduced risk are given as the basis of a subsequent risk control report.
Step S107: and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors.
In order to enable the user to comprehensively know the possible risk and the risk size of the current target futures trading order, in this embodiment, according to the target risk coefficient generated in the previous step, the extracted risk factor, all the calculation process data in the previous step, and the original futures historical trading data, the account historical trading data, the futures market data, and the key data initially acquired, a corresponding risk control report is generated according to a preset risk control report template, and is output to the user corresponding to the target account, so that the user can know the specific risk possibly existing in the current futures trading and give an investment decision whether to trade or whether to continue holding, thereby reducing the uncontrollable risk in the futures trading.
In a specific implementation, in order to show the risk or the profit possibility existing in the target futures trading order in a targeted manner, in the calculation process of the above steps S101 to S106, at least one risk reporting node needs to be determined according to whether the historical trading risk factor, the account trading risk factor, the market trading risk factor, the risk control coefficient and the target risk factor respectively satisfy a preset coefficient threshold value set, and whether the target risk factor exceeds the first risk threshold value. Wherein, each coefficient or factor is correspondingly provided with a corresponding coefficient threshold value so as to form a coefficient threshold value group as a whole. And the determined at least one risk reporting node is characterized by a node which has obvious gain or reduction effect on the risk in the calculation process, and the node is an analysis module corresponding to the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient and the target risk coefficient. In this embodiment, in order to fully display the data that needs to be noticed in each coefficient or factor, a corresponding sub-report template is correspondingly set for each analysis module, so that the data corresponding to the corresponding coefficient and the risk factor extracted in the factor calculation process can be fully displayed in the final control report.
Then, for the sub-report template corresponding to each analysis module, the corresponding sub-report template needs to be filled according to the aforementioned calculation process, all the used related data, and the previously extracted related risk factors, so as to generate a corresponding node sub-report, where the node sub-report includes the related data with a higher or lower value of the corresponding coefficient or factor and the data analysis content, so that the user can completely know the feedback of the calculation process of the risk coefficient.
Further, after the node sub-report of the at least one risk report node is generated, the risk control report needs to be further filled based on all the data and the calculation result according to the template of the risk control report, so as to generate a corresponding risk control report. In this embodiment, the report generation is a process of analyzing data according to a preset analysis logic, and a corresponding report template needs to be constructed in advance according to various situations.
Further, in order to improve the risk control effect of futures trading, when the target risk coefficient exceeds a preset second risk threshold, the corresponding target futures trading order may be forcibly closed or ended in advance, that is, when the target risk coefficient exceeds the preset second risk threshold, a preset risk control command is generated and executed to close or release the target futures trading order, so as to avoid trading or continuously holding the ultrahigh-risk futures trading order.
In another embodiment, there is provided a risk control device for futures trading, specifically referring to fig. 4, the device includes:
an order obtaining module 201, configured to determine a target futures trading order that needs to be analyzed, where the target futures trading order includes a target account and a target futures product;
a data obtaining module 202, configured to obtain futures historical trading data corresponding to the target futures product, account historical trading data of a target account, and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
the first risk factor calculation module 203 is configured to calculate a historical trading risk factor based on the futures historical trading data, calculate an account trading risk factor based on the account historical trading data, and calculate a market trading risk factor based on the futures market data through a preset risk factor calculation model;
a second risk coefficient calculation module 204, configured to calculate a risk control coefficient based on the key data through a preset risk control model;
a target risk coefficient calculation module 205, configured to calculate a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor, and the risk control coefficient, and obtain a risk factor corresponding to the target risk coefficient;
and a report generating module 206, configured to generate and output a risk control report corresponding to the target futures trading order based on the futures historical trading data, the account historical trading data, the futures market data, and the key data according to the target risk coefficient and the corresponding risk factor.
Optionally, in other embodiments, the first risk factor calculating module 203 is further configured to divide the futures historical transaction data into transaction sub-data in multiple transaction dimensions according to a preset data grouping rule, where the transaction sub-data in the multiple transaction dimensions have data overlapping; for each transaction dimension: calculating a risk factor under the transaction dimension according to a pre-constructed risk factor calculation model under the transaction dimension, and calculating an overlap coefficient under the transaction dimension according to a preset overlap coefficient calculation formula according to the data proportion of overlapped data under the transaction dimension, transaction dimension data with overlapped data and the total number of the transaction dimensions; according to the risk factor and the overlapping coefficient under each transaction dimension, calculating a historical transaction risk factor X according to the following calculation formula1：
Figure BDA0003076483340000161
Wherein k isiAs overlap factor of trading dimension, fiI is the risk factor for the trading dimension, i is the trading dimension.
Optionally, in other embodiments, the first risk factor calculation module 203 is further configured to filter out transaction sub-data related to account risk preference from the account historical transaction data, calculate the filtered transaction sub-data, and obtain a first account risk sub-factor; screening out transaction subdata related to the account income preference from the historical transaction data of the account, and calculating the screened transaction subdata to obtain a second account risk sub-factor; and taking the first account risk sub-factor and the second account risk sub-factor as the account transaction risk factors.
Optionally, in other embodiments, the data obtaining module 202 is further configured to determine at least one keyword corresponding to the target futures product, and screen out at least one piece of key data from the network data according to the determined at least one keyword;
the second risk coefficient calculation module 204 is further configured to, for each piece of key data, obtain a classification label corresponding to the key data according to a preset classification model, and calculate a control coefficient of the key data by calculating a product of label values of all classification labels of the key data according to a correspondence between preset classification labels and label values; determining a first control coefficient by calculating a ratio of a first absolute value of the sum of all positive risk coefficients to a second absolute value of the sum of all negative risk coefficients; determining the larger value of the first absolute value and the second absolute value as a second control coefficient; and taking the first control coefficient and the second control coefficient as risk control coefficients corresponding to key data.
Optionally, in other embodiments, the target risk coefficient calculation module 205 is further configured to calculate a first risk coefficient according to the historical trading risk factor and the market trading risk factor; calculating a first risk coefficient and a risk control coefficient, and calculating a second risk coefficient; and calculating a corrected target risk coefficient according to a preset correction function, the account transaction risk factor and the second risk coefficient, wherein the value range of the target risk coefficient is [ -1,1 ].
Optionally, in other embodiments, the target risk coefficient calculation module 205 is further configured to determine an offset coefficient in each trading dimension according to the market risk trading factor, and calculate an offset amount according to a weighted sum of the risk factor and the offset coefficient in each trading dimension; calculating a first risk coefficient according to the historical transaction risk factor, the market transaction risk factor, the weighted sum of the preset weighting coefficient quality inspection and the sum of the calculated offset; calculating the product of the first risk coefficient and the first control coefficient, and dividing the calculated product by the second control coefficient to determine a second risk coefficient; calculating the product of the second risk coefficient and the first account risk sub-factor, subtracting the second account risk sub-factor and determining a third risk coefficient; determining a reference value according to the first account risk sub-factor and the second account risk sub-factor, wherein the reference value is used for representing the preference degree of the user corresponding to the target account for the futures risk; and calculating the target risk coefficient according to the third risk coefficient and the determined reference value by the following calculation formula:
Figure BDA0003076483340000171
wherein Y3 is a third risk coefficient, Q is a reference value, Fr is a target risk coefficient, and the value range of the target risk coefficient is [ -1,1 ].
Optionally, in other embodiments, the target risk coefficient calculation module 205 is further configured to extract data meeting a preset rule as a risk factor according to a calculation process in the calculation process of the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient, and the target risk coefficient.
Optionally, in other embodiments, the report generating module 206 is further configured to determine at least one risk reporting node according to whether the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient, and the target risk factor respectively satisfy a preset set of coefficient thresholds, and whether the target risk factor exceeds a first risk threshold; acquiring a sub-report template corresponding to at least one risk report node, and generating a corresponding node sub-report according to a target risk coefficient calculation process and used data; and generating the risk control report according to the target risk coefficient and the node sub-report corresponding to the at least one risk report node.
Fig. 5 shows an internal structural diagram of a computer device for implementing the risk control method for futures trading in one embodiment. The computer device may specifically be a terminal, and may also be a server. As shown in fig. 5, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program which, when executed by a processor, causes the processor to carry out the above-mentioned method. The internal memory may also have stored therein a computer program which, when executed by the processor, causes the processor to perform the method described above. Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
After the risk control method and device for futures trading and the computer equipment are adopted, under the condition that risk assessment is needed to be carried out on futures trading orders, target futures trading orders needing to be analyzed are determined, wherein the target futures trading orders comprise target accounts and target futures products; then obtaining historical futures trading data corresponding to the target futures products, historical account trading data of the target account and futures market data; acquiring network data related to target futures products through a web crawler, and extracting key data related to target futures trading orders in the network data; after the data acquisition is finished, calculating historical trading risk factors based on the futures historical trading data through a preset risk factor calculation model, calculating account trading risk factors based on the account historical trading data, and calculating market trading risk factors based on the futures market data; calculating a risk control coefficient based on the key data through a preset risk control model; then, according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, calculating a target risk factor corresponding to the target futures trading order, and acquiring a risk factor corresponding to the target risk factor; and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors. That is, for futures trading, before trading or during the continuous holding process of trading, risk situations that may exist in futures trading are evaluated through historical trading data of futures products, futures market data and key data extracted from the network and having an influence on futures, risk preferences of users are evaluated according to the history of accounts currently trading, target risk coefficients for futures products and users are comprehensively evaluated, and risk control reports of risk points included in the analysis process are used for enabling users to not only accurately know the risk situations of current futures trading and specific situations that may cause risks, so as to help users to make decisions on futures trading better, and further reduce the risk of futures trading.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims. Please enter the implementation content part.

Claims (10)

1. A risk control method for futures trading is characterized by comprising
Determining a target futures trading order needing to be analyzed, wherein the target futures trading order comprises a target account and a target futures product;
obtaining historical futures trading data corresponding to the target futures products, historical account trading data of a target account and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the market futures data through a preset risk factor calculation model;
calculating a risk control coefficient based on the key data through a preset risk control model;
calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient, and acquiring a risk factor corresponding to the target risk coefficient;
and generating and outputting a risk control report corresponding to the target futures trading order based on the historical futures trading data, the historical account trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factors.
2. The risk control method of futures trading of claim 1, wherein the step of calculating historical trading risk factors based on futures historical trading data further comprises:
dividing historical transaction data of futures into transaction subdata under multiple transaction dimensions according to a preset data grouping rule, wherein the transaction subdata under the multiple transaction dimensions have data overlapping;
for each transaction dimension:
calculating the risk factor under the transaction dimension according to a pre-constructed risk factor calculation model under the transaction dimension,
calculating an overlapping coefficient under the transaction dimension according to a preset overlapping coefficient calculation formula and the data proportion of the overlapped data under the transaction dimension, the transaction dimension data of the data overlapping and the total number of the transaction dimensions;
based on the risk factor and overlap factor for each trading dimension, as followsCalculating historical transaction risk factor X by using calculation formula1：
Figure FDA0003076483330000011
Wherein k isiAs overlap factor of trading dimension, fiI is the risk factor for the trading dimension, i is the trading dimension.
3. The risk control method of futures trading according to claim 2, wherein the step of calculating an account trading risk factor based on account historical trading data further comprises:
screening out transaction subdata related to account risk preference from account historical transaction data, and calculating the screened transaction subdata to obtain a first account risk sub-factor;
screening out transaction subdata related to the account income preference from the historical transaction data of the account, and calculating the screened transaction subdata to obtain a second account risk sub-factor;
and taking the first account risk sub-factor and the second account risk sub-factor as the account transaction risk factors.
4. The risk control method of futures trading according to claim 3, wherein the step of extracting key data in the network data further comprises:
determining at least one keyword corresponding to the target futures product, and screening at least one piece of key data from the network data according to the determined at least one keyword;
through the preset risk control model, the step of calculating the risk control coefficient based on the key data further comprises the following steps:
for each piece of key data, obtaining a classification label corresponding to the key data according to a preset classification model, and calculating a control coefficient of the key data by calculating the product of label values of all classification labels of the key data according to the corresponding relation between the preset classification label and the label value;
determining a first control coefficient by calculating a ratio of a first absolute value of the sum of all positive risk coefficients to a second absolute value of the sum of all negative risk coefficients; determining the larger value of the first absolute value and the second absolute value as a second control coefficient;
and taking the first control coefficient and the second control coefficient as risk control coefficients corresponding to key data.
5. The risk control method for futures trading according to claim 4, wherein the step of calculating a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor and the risk control coefficient further comprises:
calculating a first risk coefficient according to the historical trading risk factor and the market trading risk factor;
calculating a first risk coefficient and a risk control coefficient, and calculating a second risk coefficient;
and calculating a corrected target risk coefficient according to a preset correction function, the account transaction risk factor and the second risk coefficient, wherein the value range of the target risk coefficient is [ -1,1 ].
6. The risk control method for futures trading according to claim 5, wherein the step of calculating a target risk factor corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor, and the risk control coefficient further comprises:
determining a migration coefficient under each trading dimension according to the market risk trading factor, and calculating the migration amount according to the weighted sum of the risk factor and the migration coefficient under each trading dimension; calculating a first risk coefficient according to the historical transaction risk factor, the market transaction risk factor, the weighted sum of the preset weighting coefficient quality inspection and the sum of the calculated offset;
calculating the product of the first risk coefficient and the first control coefficient, and dividing the calculated product by the second control coefficient to determine a second risk coefficient;
calculating the product of the second risk coefficient and the first account risk sub-factor, subtracting the second account risk sub-factor and determining a third risk coefficient;
determining a reference value according to the first account risk sub-factor and the second account risk sub-factor, wherein the reference value is used for representing the preference degree of the user corresponding to the target account for the futures risk;
and calculating the target risk coefficient according to the third risk coefficient and the determined reference value by the following calculation formula:
Figure FDA0003076483330000031
wherein Y3 is a third risk coefficient, Q is a reference value, Fr is a target risk coefficient, and the value range of the target risk coefficient is [ -1,1 ].
7. The risk control method of futures trading according to claim 1, wherein the step of obtaining the risk factor corresponding to the target risk factor further comprises:
and in the calculation process of the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient and the target risk factor, extracting data meeting a preset rule according to the calculation process to serve as the risk factor.
8. The method for risk control of futures trading according to claim 7, wherein the step of generating a risk control report corresponding to the target futures trading order based on the futures historical trading data, account historical trading data, futures market data, and key data according to the target risk coefficient and corresponding risk factor further comprises:
determining at least one risk report node according to whether the historical transaction risk factor, the account transaction risk factor, the market transaction risk factor, the risk control coefficient and the target risk factor respectively meet a preset coefficient threshold value set and whether the target risk factor exceeds a first risk threshold value;
acquiring a sub-report template corresponding to at least one risk report node, and generating a corresponding node sub-report according to a target risk coefficient calculation process and used data;
and generating the risk control report according to the target risk coefficient and the node sub-report corresponding to the at least one risk report node.
9. A risk control device for futures trading, comprising:
the system comprises an order acquisition module, a target futures trading module and a target futures trading module, wherein the order acquisition module is used for determining a target futures trading order needing to be analyzed, and the target futures trading order comprises a target account and a target futures product;
a data acquisition module, configured to acquire futures historical trading data corresponding to the target futures product, account historical trading data of a target account, and futures market data; acquiring network data related to the target futures product through a web crawler, and extracting key data related to a target futures trading order in the network data;
the first risk factor calculation module is used for calculating historical trading risk factors based on the historical futures trading data, calculating account trading risk factors based on the historical account trading data and calculating market trading risk factors based on the market futures data through a preset risk factor calculation model;
the second risk coefficient calculation module is used for calculating a risk control coefficient based on the key data through a preset risk control model;
a target risk coefficient calculation module, configured to calculate a target risk coefficient corresponding to the target futures trading order according to the historical trading risk factor, the account trading risk factor, the market trading risk factor, and the risk control coefficient, and obtain a risk factor corresponding to the target risk coefficient;
and the report generation module is used for generating and outputting a risk control report corresponding to the target futures trading order based on the futures historical trading data, the account historical trading data, the futures market data and the key data according to the target risk coefficient and the corresponding risk factor.
10. A computer device, characterized in that the computer device comprises a memory and a processor, the memory having executable code which when run on the processor implements the risk control method of futures trading according to any of claims 1 to 8.
CN202110554331.XA 2021-05-20 2021-05-20 Risk control method and device for futures trading and computer equipment Pending CN113327164A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110554331.XA CN113327164A (en) 2021-05-20 2021-05-20 Risk control method and device for futures trading and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110554331.XA CN113327164A (en) 2021-05-20 2021-05-20 Risk control method and device for futures trading and computer equipment

Publications (1)

Publication Number Publication Date
CN113327164A true CN113327164A (en) 2021-08-31

Family

ID=77416078

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110554331.XA Pending CN113327164A (en) 2021-05-20 2021-05-20 Risk control method and device for futures trading and computer equipment

Country Status (1)

Country Link
CN (1) CN113327164A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113989043A (en) * 2021-10-28 2022-01-28 支付宝(杭州)信息技术有限公司 Event risk identification method, device and equipment
CN116342268A (en) * 2023-01-04 2023-06-27 上甲数据服务(厦门)有限公司 Futures data analysis method and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107977787A (en) * 2017-11-30 2018-05-01 上海龙弈信息科技有限公司 A kind of transaction risk control processing system and method
CN110047001A (en) * 2019-03-28 2019-07-23 莆田学院 A kind of futures data artificial intelligence analysis method and system
CN110533536A (en) * 2019-08-30 2019-12-03 中国工商银行股份有限公司 Transaction risk appraisal procedure, device and computer system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107977787A (en) * 2017-11-30 2018-05-01 上海龙弈信息科技有限公司 A kind of transaction risk control processing system and method
CN110047001A (en) * 2019-03-28 2019-07-23 莆田学院 A kind of futures data artificial intelligence analysis method and system
CN110533536A (en) * 2019-08-30 2019-12-03 中国工商银行股份有限公司 Transaction risk appraisal procedure, device and computer system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113989043A (en) * 2021-10-28 2022-01-28 支付宝(杭州)信息技术有限公司 Event risk identification method, device and equipment
CN116342268A (en) * 2023-01-04 2023-06-27 上甲数据服务(厦门)有限公司 Futures data analysis method and system

Similar Documents

Publication Publication Date Title
US20220327135A1 (en) Advanced Secure Intelligent Networked Systems
US10861028B2 (en) Detecting and reducing bias (including discrimination) in an automated decision making process
US8812384B2 (en) Systems and methods for underlying asset risk monitoring for investment securities
de Andrés-Sánchez et al. Using fuzzy random variables in life annuities pricing
CN113327164A (en) Risk control method and device for futures trading and computer equipment
US10325235B2 (en) Method and system for analyzing and optimizing distribution of work from a plurality of queues
CN111738762A (en) Method, device, equipment and storage medium for determining recovery price of poor assets
Chen et al. A study on operational risk and credit portfolio risk estimation using data analytics
Zhang et al. An attention‐based Logistic‐CNN‐BiLSTM hybrid neural network for credit risk prediction of listed real estate enterprises
US11416935B2 (en) System, method, and device for autonomous fund management by computer-based algorithms
CN111950860A (en) Method and device for monitoring enterprise public opinion risk index
CN116361542A (en) Product recommendation method, device, computer equipment and storage medium
CN115239491A (en) Futures trading method and computer equipment
US20200410613A1 (en) Real estate bubble prediction based on big data
Kovalova et al. Innovate forms of project financing under the conditions of globalization
CN113421014A (en) Target enterprise determination method, device, equipment and storage medium
Metaxoglou et al. Forecasting stock returns using option-implied state prices
Liutvinavičius et al. Behavioural economics approach: Using investors sentiment indicator for financial markets forecasting
CN110135995A (en) Financing evaluation processing method, device, computer equipment and storage medium
Zarrin Nal et al. Providing an Optimal Model in Modeling the Dependence Structure of the Elements of Financial Systems Using an Approach Based on Vine-Copula Functions.(Case Study: Market and Industry Indices at Tehran Stock Exchange)
CN117522502A (en) Resource recommendation method, device, computer equipment and medium for meta space business hall
Santos et al. Subjective Probability Density Functions from FX Option Prices: Predictive Power and Performance on a Carry Trade Strategy
Sastry et al. Pricing Options Considering Bankruptcy of Underlying Issuer
Licari Analytical Solutions for Multi-Period Credit Portfolio Modelling
CN116644237A (en) Investment configuration recommendation method, device, equipment and medium based on artificial intelligence

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: 20210831

RJ01 Rejection of invention patent application after publication