CN115239104A - Algorithm transaction evaluation method, device, equipment and storage medium - Google Patents
Algorithm transaction evaluation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115239104A CN115239104A CN202210815055.2A CN202210815055A CN115239104A CN 115239104 A CN115239104 A CN 115239104A CN 202210815055 A CN202210815055 A CN 202210815055A CN 115239104 A CN115239104 A CN 115239104A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- scoring
- transaction
- details
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of securities trading, in particular to an algorithm trading evaluation method, a device, equipment and a storage medium, wherein the method comprises the following steps: obtaining the entrusting details and transaction details of the current entrusting of the algorithm to be evaluated; acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data; searching a corresponding scoring standard in a preset scoring template according to a received query instruction; and scoring the index values according to a scoring standard, and evaluating the algorithm to be evaluated based on the scoring result. According to the invention, the index values corresponding to different evaluation indexes are determined according to the entrustment details, the transaction details and the historical transaction data, then the corresponding scoring standards are searched in the preset scoring template, and the index values are scored according to the scoring standards, so that compared with the existing user self-evaluation, the evaluation accuracy can be improved.
Description
Technical Field
The invention relates to the technical field of securities trading, in particular to an algorithm trading evaluation method, device, equipment and storage medium.
Background
At present, in the process of stock exchange, an algorithm exchange mode is mostly adopted, namely, a computer program automatically sends out exchange instructions according to exchange time, exchange price, exchange requirements and the like required by a user to exchange.
The existing algorithm transaction executes related operations according to algorithm entrustment of a user, and a transaction result is displayed after the transaction is finished, but if the user wants to know the execution condition of the algorithm transaction, the user can only self-evaluate the result of the algorithm transaction, so that the evaluation process is complex, the accuracy is low, and further how to accurately evaluate the algorithm transaction is a problem to be solved urgently.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide an algorithm transaction evaluation method, device, equipment and storage medium, and aims to solve the technical problem that evaluation of algorithm transaction execution conditions is inaccurate in the prior art.
In order to achieve the above object, the present invention provides an algorithmic transaction evaluation method, comprising the steps of:
obtaining the entrusting details and the transaction details of the current entrusting of the algorithm to be evaluated;
acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data;
searching a corresponding scoring standard in a preset scoring template according to a received query instruction;
and scoring the index values according to the scoring standard, and evaluating the algorithm to be evaluated based on the scoring result.
Optionally, the step of searching for the corresponding scoring standard in the preset scoring template according to the received query instruction includes:
obtaining an evaluation index to be queried according to a received query instruction;
and searching a corresponding mapping relation table in a preset grading template according to the evaluation index to be inquired, and taking the mapping relation table as a grading standard.
Optionally, the step of scoring the index value according to the scoring criterion and evaluating the algorithm to be evaluated based on a scoring result includes:
determining a target numerical value interval to which the index numerical value belongs and an index score interval corresponding to the target numerical value interval according to the grading standard;
acquiring a numerical interval lower limit value and a numerical interval upper limit value corresponding to the target numerical interval;
acquiring a value interval lower limit value and a value interval upper limit value corresponding to the target value interval;
scoring the index value through a preset scoring formula according to the numerical interval lower limit value, the numerical interval upper limit value, the score interval lower limit value and the score interval upper limit value;
wherein, the preset scoring formula is as follows:
wherein S is a score result, X is the index value, and X is a+1 Is the upper limit value of the numerical range, X a Is the lower limit value of the numerical range, Y a+1 Is the upper limit value of the score interval, Y a Is the lower limit value of the score interval;
and evaluating the algorithm to be evaluated based on the grading result.
Optionally, before the step of obtaining the delegation details and the deal details of the current delegation of the algorithm to be evaluated, the method further includes:
when receiving an algorithm entrustment, extracting information of the algorithm entrustment;
judging whether the algorithm entrusts reach a preset order dismantling condition or not according to the extraction result;
and if so, performing order splitting on the algorithm entrusts to obtain a single splitting flow, and obtaining entrustment details and transaction details according to the single splitting flow.
Optionally, the step of extracting information from the algorithm delegation when the algorithm delegation is received includes:
when an algorithm commission is received, security codes and parameter configuration in the algorithm commission are extracted;
acquiring corresponding transaction data according to the security code;
and configuring the transaction data and the parameters as extraction results.
Optionally, before the step of obtaining the delegation details and the deal details of the current delegation of the algorithm to be evaluated, the method further includes:
obtaining an evaluation index and a reference standard interval corresponding to a target algorithm according to the received parameter recommendation instruction;
acquiring historical transaction details based on the evaluation indexes and the reference standard interval;
and acquiring recommended parameters according to the historical transaction details, and displaying the recommended parameters.
Optionally, after the step of obtaining historical transaction data within a preset time range and determining index values corresponding to different evaluation indexes according to the delegation details, the deal details and the historical transaction data, the method further includes:
if the query instruction is not found, acquiring an index subclass corresponding to the query instruction, and adding a relevant registration item in the index subclass;
and adding a mapping relation table in the initial scoring template according to the index subclass and the related registration items to obtain a preset scoring template.
In addition, in order to achieve the above object, the present invention further provides an algorithmic transaction evaluation device, including:
the detail obtaining module is used for obtaining the delegation detail and the deal detail of the current delegation of the algorithm to be evaluated;
the numerical value determining module is used for acquiring historical transaction data within a preset time range and determining index numerical values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data;
the standard searching module is used for searching a corresponding scoring standard in a preset scoring template according to the received query instruction;
and the algorithm evaluation module is used for scoring the index values according to the scoring standard and evaluating the algorithm to be evaluated based on the scoring result.
In addition, to achieve the above object, the present invention further provides an algorithmic transaction evaluation device, including: a memory, a processor and an algorithmic transaction evaluation program stored on the memory and executable on the processor, the algorithmic transaction evaluation program being configured to implement the steps of an algorithmic transaction evaluation method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium, on which an algorithmic transaction evaluation program is stored, and the algorithmic transaction evaluation program, when executed by a processor, implements the steps of the algorithmic transaction evaluation method as described above.
The invention obtains the entrusting details and the transaction details of the current entrusting of the algorithm to be evaluated; acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data; searching a corresponding scoring standard in a preset scoring template according to a received query instruction; and scoring the index values according to the scoring standard, and evaluating the algorithm to be evaluated based on the scoring result. According to the invention, the index values corresponding to different evaluation indexes are determined according to the entrustment details, the transaction details and the historical transaction data, then the corresponding scoring standards are searched in the preset scoring template, and the index values are scored according to the scoring standards, so that compared with the existing user self-evaluation, the evaluation accuracy can be improved.
Drawings
Fig. 1 is a schematic structural diagram of an algorithmic transaction evaluation device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of a first embodiment of an algorithmic transaction evaluation method of the present invention;
FIG. 3 is a schematic flow chart diagram of a second embodiment of an algorithmic transaction evaluation method of the present invention;
FIG. 4 is a schematic flow chart diagram of a third embodiment of an algorithmic transaction evaluation method of the present invention;
FIG. 5 is a schematic flow chart diagram illustrating a fourth embodiment of an algorithmic transaction evaluation method of the present invention;
fig. 6 is a block diagram showing the structure of the algorithmic transaction evaluating device according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an algorithmic transaction evaluation device of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the algorithmic transaction evaluation device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of an algorithmic transaction evaluation device and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an algorithmic transaction evaluation program.
In the algorithmic transaction evaluation device shown in fig. 1, the network interface 1004 is primarily used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the algorithmic transaction evaluation device of the present invention may be disposed in an algorithmic transaction evaluation device, and the algorithmic transaction evaluation device calls an algorithmic transaction evaluation program stored in the memory 1005 through the processor 1001 and executes an algorithmic transaction evaluation method provided by an embodiment of the present invention.
An embodiment of the present invention provides an algorithm transaction evaluation method, and referring to fig. 2, fig. 2 is a schematic flow diagram of a first embodiment of the algorithm transaction evaluation method according to the present invention.
In this embodiment, the algorithm transaction evaluation method includes the following steps:
step S10: and acquiring the commission details and the deal details of the current commission of the algorithm to be evaluated.
It should be noted that the method of the present embodiment may be applied in a scenario of evaluating an algorithm in a certificate transaction, or in other scenarios that require evaluation of an algorithm transaction. The execution main body of the embodiment can be an algorithm transaction evaluation device with data processing, network communication and program running functions, such as a computer, a mobile phone and the like, or other devices capable of realizing the same or similar functions. The present embodiment and the following embodiments are specifically described with the above arithmetic transaction evaluation device (hereinafter, simply referred to as a device).
It can be understood that the algorithm to be evaluated can be an algorithm designed according to various information such as a mathematical model, statistical data, market real-time information and the like, so that the equipment can automatically trade a target order according to the algorithm to be evaluated, and meanwhile, the equipment can quickly and effectively reduce the trading cost by running the algorithm to be evaluated, control the market impact cost, strive for the optimal bargain price and quantity, hide the trading intention and the like.
It should be understood that the current order may be an order issued by the user in accordance with the respective request for the order, the device automatically performing the associated transaction in accordance with the current order.
It is emphasized that the order details may be data related to each purchase and sale order recorded by the device, including customer code, asset account, security code, order quantity, etc., or other order details related to the transaction requirements; the details of the deal may be details of each transaction, including the time of the deal, the amount of the deal, the average price of the deal, the flow status, etc., or other details related to the success of the deal.
In a specific implementation, when a user wants to know the score of the algorithm to be evaluated, the device obtains the delegation details and the deal details of the current delegation of the algorithm to be evaluated.
Further, considering that different current orders correspond to different order details and transaction details, in order to accurately obtain the order details and the transaction details, before the step S10, the method further includes:
step S001: and when receiving the algorithm entrusts, extracting information of the algorithm entrusts.
It should be noted that the algorithm delegation may be created according to the requirement of the user when the user has a trading requirement, and the algorithm delegation may carry information required for algorithm trading, including an algorithm trading strategy, a client code, an asset account, a security code, a parameter configuration, and the like.
Further, in order to improve the extraction efficiency, when an algorithm commission is received, security codes and parameter configuration in the algorithm commission are extracted;
it should be noted that the security code refers to a code corresponding to a security that a user needs to buy or sell, each of the securities has a corresponding code, and if a user needs to buy or sell a certain security, the user needs to input the corresponding security code and store the security code in the algorithm commission.
It is understood that the above parameter configuration may be the configuration of the transaction requirements, and may include the transaction amount, the transaction price, the transaction duration, the transaction time interval, etc., or other configurations related to the transaction requirements, which may be determined by the user according to the actual situation.
It should be understood that, when the device extracts the security code and the parameter configuration, the security code and the parameter configuration are stored in a database, and the database may be disposed inside the device or in the cloud.
In a specific implementation, when receiving an algorithm commission proposed by a user, the device extracts security codes and parameter configuration carried in the algorithm commission, and stores the security codes and parameter configuration in a database.
Acquiring corresponding transaction data according to the security code;
the device may obtain, according to the security code in the algorithm request, a related market situation corresponding to the security code, where the related market situation may include information corresponding to the security code, such as a large-volume index, a volume of trades, a hand-off rate, a market profit rate, and a total amount.
It can be understood that the device may obtain corresponding transaction data according to the related market, where the transaction data may include data of a transaction time interval, a transaction duration, a transaction amount, a transaction price, and the like, and the transaction data may be set according to parameter configuration in the algorithm delegation, for example, if there is a related demand for the transaction price in the parameter configuration, the transaction data may include data of the transaction price.
In a specific implementation, the equipment acquires corresponding related quotations according to the security codes in the algorithm entrusts, acquires corresponding transaction data according to the related quotations, and configures the transaction data and the parameters as extraction results.
Step S002: and judging whether the algorithm entrustment reaches a preset order dismantling condition or not according to the extraction result.
It should be noted that the preset ticket splitting condition may be that the transaction price reaches the transaction price of the user in the parameter configuration, or a condition required by another user, and may be set according to the parameter configuration in the algorithm commission of the user, for example, if there is a related requirement for the transaction time in the parameter configuration, the preset ticket splitting condition may be that the transaction time is reached.
In a specific implementation, the device may determine whether the algorithm delegation reaches a preset order splitting condition according to an extraction result.
Step S003: if so, the order of the algorithm entrusts is disassembled to obtain an order disassembling flow, and entrustment details and transaction details are obtained according to the order disassembling flow.
It should be noted that the order splitting may be to split the transaction quantity in the algorithm delegation, and since the transaction quantity of the user may include related orders for different transactions, the orders need to be split according to different information.
It can be understood that the splitting flow water may be a related flow account after the order is split, the device may obtain the entrustment details from the database according to the splitting flow water, and obtain the transaction details from the transaction data, the splitting flow water may be stored in the database, and a flow meter for storing the splitting flow water may be set in the database.
In a specific implementation, if the entrustment of the judgment algorithm reaches a preset order splitting condition, the device splits the order to obtain a split order running water, stores the split order running water into a running water table, and obtains entrustment details and transaction details according to the split order running water.
Step S20: and acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data.
It should be noted that the preset time range may be set according to the transaction time in the algorithm delegation, or may be set by the user according to the circumstances, for example, if the transaction time is set to 10 hours, the preset time may be set to 10 hours, and the device may obtain the historical transaction data of the past 10 hours.
It is understood that the historical trading data may be related data of trading information after the algorithm is committed to execute, and may include security codes, trading time, latest price, number of deals, total amount of deals, and the like.
It should be understood that the above evaluation indexes may be statistical indexes for examining, evaluating, and comparing the effects of different algorithm entrusts, and the user may set different evaluation indexes according to the actual situation.
It should be emphasized that the above-mentioned index value may be result values corresponding to the above-mentioned different evaluation indexes, in this embodiment, the above-mentioned over standard TWAP is how much better the average price of the single bargain of the algorithm is than the standard TWAM, and the over standard TWAP can be divided into buying and selling, for example, the average price of buying and selling for a certain share of an algorithm is 16.40, and the average price of bargaining for the standard TWAP algorithm in the same time period is 16.45, then the above-mentioned over standard TWAP value is (16.45-16.40) × 10000=500;
the standard TWAP calculation mode is as follows: the total number of the finished transactions is n,
setting m historical transaction data in a preset time range,
then the
Over standard TWAP = (standard TWAP-parity x 10000,
in the above calculation mode, n isThe amount of the order of the transaction,
price of bargain i X number of bargain i The product of the transaction price of each order and the corresponding transaction amount is summed for the n orders,
number of bargaining i Summing the number of deals per single, m being the number of historical transactions,
closing price i And summing the closing price of each order in the m pieces of historical transaction data.
The above-mentioned exceeding standard VWAP is how much better the average price of the single transaction under the algorithm is than the standard VWAP, and the exceeding standard VWAP can be divided into buying price and selling price, for example, if the average price of the buying price of an algorithm for a certain share is 16.42, and the average price of the standard VWAP algorithm for the same time slot is 16.50, then the above-mentioned value of the exceeding standard VWAP is (16.50-16.42) × 10000=800;
the calculation mode exceeding the standard VWAP is as follows: the total number of n transactions is set up,
setting m historical transaction data in a preset time range,
then
Over standard VWAP = (parity-standard VWAP) × 10000,
in the above calculation mode, n is the amount of orders for the transaction,
price of transaction i X number of final deals i For n ordersThe products of the transaction price of each order and the corresponding transaction quantity are summed up after the orders are respectively processed,
number of deals i And summing up the transaction amount of each single, wherein m is the number of the historical transactions, the total transaction amount is the total transaction amount of the m historical transaction data, and the total transaction amount is the total transaction amount of the m historical transaction data.
The reporting-withdrawing ratio can be the proportion of the number of orders withdrawn by the algorithm operation entrustment to the total number of orders withdrawn by the entrustment, and the smaller the reporting-withdrawing ratio is, the higher the transaction rate of the orders withdrawn by the algorithm operation entrustment can be represented; the trade order may be divided into a master order and a child order, and one or more child orders may be contained within a master order.
The reporting and withdrawing ratio is calculated in the following mode: setting n sub-entrusts (eliminating the waste singular number),
in the above calculation method, n is the number of the sub-orders after the rejected orders are removed from the trade order, the removed sub-singular number is the number of all the removed sub-orders, and the partial removed sub-singular number is the number of the partial removed sub-orders.
The completion rate can be the proportion of the number of orders issued by the algorithm to the number of orders issued by the entrustment, and the higher the proportion is, the better the order issuing task of the entrustment can be executed by the algorithm; the completion rate may include a completion rate of the mother sheet, or may be a completion rate of the algorithm.
The calculation mode of the completion rate is as follows: the total number of the sub-entrusts is n,
the algorithm completion rate is calculated in the following way: the total number of the female bills is m,
in the above calculation mode, m is the number of the mother list, X i The completion rate of each master list is shown.
The instantaneous impact cost may be a cost that a large amount of securities need to be bought or sold quickly in a arbitrage transaction and cannot be bought according to a reserved price, for example, when an organization account for a group of stocks, it takes a long time to build a warehouse. If the warehouse is urgent, the stock price can be raised due to a large amount of purchase in a short time, and the warehouse building cost is higher than the expected cost; similarly, if it is urgent to cast a stock, which is equal to the stock price of oneself being compressed, the final selling price is lower than the original expected price, and the lower the impact cost, the better. The impact costs may include buy class impact costs, sell class impact costs, mother-to-bill impact costs, and algorithm impact costs.
The impact cost is calculated in the following mode:
for buy-class algorithms: the impact cost of each transaction sheet = (transaction price of the pen-latest price of the previous snapshot) x transaction amount of the pen;
for the sell class algorithm: impact cost of each transaction sheet = (latest price of previous snapshot-transaction price of the pen) x transaction amount of the pen;
for the master-slave impact:
in the above calculation mode, n is the number of the mother sheet and the child sheet;
for the algorithm impact cost:
in the above calculation mode, m is the number of the mother list, X i The cost is the single impact per letter.
The actual market participation rate can be the proportion of the volume of the primary order in the market deals from the first order entrusted to the last deal order;
the calculation method for the actual market participation rate is as follows:
actual market participation rate = total volume of stock solution/(Vol) end -Vol start )×100％，
Wherein Vol end Vol, market cumulative volume to end snapshots start The volume is accumulated for the market that started the snapshot.
In a specific implementation, the device acquires historical transaction data within a preset time range, and determines index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data.
Step S30: searching a corresponding scoring standard in a preset scoring template according to a received query instruction;
it should be noted that the query instruction may be an instruction issued by a user when the user wants to obtain a scoring result of the algorithm, and the query instruction may be a button clicked on a query interface by the user, or in another manner, which is not limited in this embodiment.
It can be understood that the device stores a preset scoring template, and because scoring modes of different algorithms are different, scoring standards of index values corresponding to different algorithms are stored in the preset scoring template, and the scoring standards can be scores corresponding to different index values, and the scores can be used for providing references for users.
In a specific implementation, when receiving a query instruction sent by a user, the device may search for a corresponding scoring standard in a preset scoring template.
Step S40: and scoring the index values according to the scoring standard, and evaluating the algorithm to be evaluated based on a scoring result.
In a specific implementation, when the device finds the scoring standard, the device may obtain a corresponding score according to the index value and in combination with the scoring standard, display a scoring result, and evaluate the algorithm according to the scoring result.
When receiving an algorithm commission proposed by a user, the equipment of the embodiment extracts security codes and parameter configuration carried in the algorithm commission and stores the security codes and parameter configuration into a database; acquiring corresponding related quotations according to the security codes in the algorithm entrusts, acquiring corresponding transaction data according to the related quotations, and configuring the transaction data and the parameters as extraction results; the equipment judges whether the algorithm entrusts to reach a preset order dismantling condition according to the extraction result; if the entrusting of the judgment algorithm reaches a preset order dismantling condition, the entrusting carries out order dismantling to obtain a dismantled single flow, the dismantled single flow is stored in a flow meter, and entrusting details and transaction details are obtained according to the dismantled single flow; when a user wants to know the score of the algorithm to be evaluated, the equipment acquires the delegation details and the transaction details of the current delegation of the algorithm to be evaluated; acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrustment details, the transaction details and the historical transaction data; when a query instruction sent by a user is received, a corresponding scoring standard can be searched in a preset scoring template; when the scoring standard is found, obtaining corresponding scoring according to the index value and the scoring standard, displaying a scoring result, and evaluating the algorithm according to the scoring result; according to the embodiment, the index values corresponding to different evaluation indexes are determined according to the entrustment details, the transaction details and the historical transaction data, the corresponding scoring standards are searched in the preset scoring template, and the index values are scored according to the scoring standards, so that compared with the existing user self-evaluation, the evaluation accuracy can be improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a transaction evaluation method according to a second embodiment of the algorithm of the present invention.
In order to obtain the scoring criteria, scoring directly according to the index value is generally adopted, but this method is inefficient and has insufficient accuracy, so as shown in fig. 3, in order to further improve the accuracy, based on the first embodiment, the step S30 includes:
step S31: obtaining an evaluation index to be queried according to a received query instruction;
it should be noted that the evaluation index to be queried may be an index corresponding to an algorithm that a user wants to query, for example, if the user wants to query the revocation ratio of the a algorithm, the query instruction may carry a code of an instruction related to the revocation ratio of the a algorithm, and the device may obtain a user requirement according to the query instruction.
In a specific implementation, the device may obtain an evaluation index that a user wants to query according to a received query instruction.
Step S32: and searching a corresponding mapping relation table in a preset grading template according to the evaluation index to be inquired, and taking the mapping relation table as a grading standard.
In this embodiment, the score template stores a mapping relationship table corresponding to different indexes, and the mapping relationship table is provided with corresponding relationships between different index intervals and different index score intervals, for example, the retraction ratio of the a algorithm is 25%, and the index score interval corresponding to the index value interval [20%, 30%) in the mapping relationship corresponding to the retraction ratio of the a algorithm may be [7, 8%).
In a specific implementation, the device searches a corresponding mapping relation table in a preset scoring template according to the evaluation index to be queried, and takes the mapping relation table as a scoring standard.
Further, the step S40 includes: determining a target numerical value interval to which the index numerical value belongs and an index score interval corresponding to the target numerical value interval according to the grading standard;
the target value interval is a value interval of the index value.
Acquiring a numerical interval lower limit value and a numerical interval upper limit value corresponding to the target numerical interval;
acquiring a score interval lower limit value and a score interval upper limit value corresponding to the target numerical value interval;
in general, the mapping relation table is composed of an index value interval and an index score interval, and for easy understanding, see table 1 below specifically
| Interval of index value | Interval of index score |
| (-∞，X 1 ) | Y 1 |
| [X 1 ，X 2 ) | [Y 1 ，Y 2 ) |
| …… | …… |
| [X n-1 ，X n ) | [Y n-1 ，Y n ) |
| [X n ，+∞) | Y n |
TABLE 1
In the above mapping relation table, X 1 ～X n Denotes n index value interval division points, Y 1 ～Y n And n index score interval division points are represented.
It is understood that, for example, if the index value interval is [20%, 30%), the target value interval may be [20%, 30%), the corresponding index score interval is [7, 8%), the lower limit value of the value interval is 20%, the upper limit value of the value interval is 30%, the upper limit value of the value interval is 8, and the lower limit value of the value interval is 7.
In a specific implementation, the device determines a target value interval to which the index value belongs and an index score interval according to the scoring standard, and acquires a corresponding value interval lower limit value, a corresponding value interval upper limit value, a corresponding score interval lower limit value and a corresponding score interval upper limit value.
Scoring the index value through a preset scoring formula according to the lower value interval limit value, the upper value interval limit value, the lower value interval limit value and the upper value interval limit value;
it should be noted that, the preset scoring formula is:
wherein S is a score result, X is the index value, and X is a+1 Is the upper limit value of the numerical range, X a Is the lower limit value of the numerical range, Y a+1 Is the upper limit value of the score interval, Y a The lower limit value of the score interval is set;
based on the example, the reporting-withdrawing ratio of the A algorithm is 25%, the index value interval is [20%, 30%), and the index score interval is [7, 8%), then
A score of 7.5 was obtained.
And evaluating the algorithm to be evaluated based on the grading result.
In specific implementation, the equipment scores the index value according to the numerical interval lower limit value, the numerical interval upper limit value, the score interval lower limit value and the score interval upper limit value through a preset scoring formula to obtain a scoring result, and evaluates the algorithm to be evaluated based on the scoring result.
In this embodiment, the device may obtain an evaluation index that a user wants to query according to a received query instruction; searching a corresponding mapping relation table in a preset grading template according to the evaluation index to be inquired, and taking the mapping relation table as a grading standard; determining a target numerical interval to which the index numerical value belongs and an index score interval according to the grading standard, and acquiring a corresponding numerical interval lower limit value, a corresponding numerical interval upper limit value, a corresponding score interval lower limit value and a corresponding score interval upper limit value; and scoring the index value through a preset scoring formula according to the obtained lower limit value of the value interval, the obtained upper limit value of the value interval, the obtained lower limit value of the score interval and the obtained upper limit value of the score interval, obtaining a scoring result, and evaluating the algorithm to be evaluated based on the scoring result. Because this embodiment grades through the mapping relation and the preset formula of grading that correspond in the preset template of grading to index value, compare in current user's self-evaluation, the assessment result is more accurate, and efficiency is higher.
Referring to fig. 4, fig. 4 is a flowchart illustrating a transaction evaluation method according to a third embodiment of the algorithm of the present invention.
As shown in fig. 4, considering that a part of users may use an algorithm commission for the first time, the parameter configuration of the algorithm commission is less understood, and in order to facilitate the users to better understand related information and improve user experience, before the step S10, the method further includes:
step S01: obtaining an evaluation index and a reference standard interval corresponding to a target algorithm according to the received parameter recommendation instruction;
it should be noted that the parameter recommendation instruction may be an instruction triggered by a user when parameter configuration needs to be recommended, the recommended parameter button may be displayed on the device, and when the user presses the recommended parameter button, the parameter recommendation instruction represents that the user needs the device to perform parameter recommendation.
It can be understood that the target algorithm may be an algorithm that a user needs to use, the evaluation index may be an index that the user needs to refer to, and the reference standard interval may be a scoring interval of the user for the target algorithm, for example, the user needs to obtain a relevant score of the algorithm a for the reporting-canceling ratio and obtain a reference standard interval of the user demand, the device may first obtain the user demand, the target algorithm is the algorithm a, the evaluation index is the reporting-canceling ratio, and the reference standard interval is [7,8 ], and then the device may know that the user demand is a parameter configuration that requires the reporting-canceling ratio score in the algorithm a to be [7, 8).
In a specific implementation, the device acquires an evaluation index and a reference standard interval corresponding to a target algorithm according to the received parameter recommendation instruction.
Step S02: acquiring historical transaction details based on the evaluation index and the reference standard interval;
in a specific implementation, the device searches for satisfactory historical transaction details in the database based on the evaluation index and the reference standard interval.
Step S03: and acquiring recommended parameters according to the historical transaction details, and displaying the recommended parameters.
The device in this embodiment obtains an evaluation index and a reference standard interval corresponding to a target algorithm according to a received parameter recommendation instruction, searches a historical transaction detail meeting requirements in a database based on the evaluation index and the reference standard interval, obtains parameter configuration in a historical algorithm commission from the historical transaction detail meeting requirements, and displays the parameter configuration as a recommendation parameter. And then, the user can conveniently carry out algorithm delegation according to the recommended parameters, and the user experience is improved.
Referring to fig. 5, fig. 5 is a flowchart illustrating a fourth embodiment of the algorithmic transaction evaluation method of the present invention.
Further, considering that there may not be an index value corresponding to the evaluation index required by the user in the preset scoring template, in order to meet the user requirement, as shown in fig. 5, after the step S20, the method further includes:
step S21: if the query instruction is not found, acquiring an index subclass corresponding to the query instruction, and adding a relevant registration item in the index subclass;
the index subclass may be an index value required by the user, and the related entry may be a database corresponding to the index subclass, which may store configuration information, status attributes, and various information data, or may include an evaluation index corresponding to the index value.
In a specific implementation, an index sub-class under a corresponding algorithm may be added to the device internal program according to a corresponding index value, and a corresponding entry may be added to the index sub-class.
Step S22: and adding a mapping relation table in the initial scoring template according to the index subclass and the related registration items to obtain a preset scoring template.
In a specific implementation, the device may generate a mapping relationship table corresponding to an evaluation index required by a user according to the index subclass and the related registration entry, and store the mapping relationship table into a preset scoring die.
In this embodiment, the device may add an index sub-class under a corresponding algorithm in the internal program of the device according to a corresponding index value, and add a corresponding registration entry in the index sub-class; and generating a mapping relation table corresponding to the evaluation index of the user requirement according to the index subclass and the related registration item, and storing the mapping relation table into a preset scoring mould, so that a preset scoring template in which the user requirement is stored is formed, and the user experience is improved.
In addition, an embodiment of the present invention further provides a storage medium, where an algorithmic transaction evaluation program is stored, and when being executed by a processor, the algorithmic transaction evaluation program implements the steps of the algorithmic transaction evaluation method described above.
In addition, referring to fig. 6, fig. 6 is a block diagram of a first embodiment of the algorithmic transaction evaluation device according to the present invention, and the embodiment of the present invention further provides an algorithmic transaction evaluation device, where the algorithmic transaction evaluation device includes:
the detail obtaining module 601 is used for obtaining the delegation detail and the transaction detail of the current delegation of the algorithm to be evaluated;
a value determining module 602, configured to obtain historical transaction data within a preset time range, and determine index values corresponding to different evaluation indexes according to the delegation details, the transaction details, and the historical transaction data;
a standard searching module 603, configured to search, according to the received query instruction, a corresponding scoring standard in a preset scoring template;
and the algorithm evaluation module 604 is configured to score the index value according to the scoring criteria, and evaluate the algorithm to be evaluated based on a scoring result.
In this embodiment, when receiving an algorithm commission proposed by a user, the device extracts security codes and parameter configuration carried in the algorithm commission, and stores the security codes and parameter configuration in a database; acquiring corresponding related quotations according to the security codes in the algorithm entrusts, acquiring corresponding transaction data according to the related quotations, and configuring the transaction data and the parameters as extraction results; the equipment judges whether the algorithm entrusts to reach a preset order dismantling condition according to the extraction result; if the entrusting of the judgment algorithm reaches a preset order dismantling condition, the entrusting carries out order dismantling to obtain a dismantled single flow, the dismantled single flow is stored in a flow meter, and entrusting details and transaction details are obtained according to the dismantled single flow; when a user wants to know the score of the algorithm to be evaluated, the equipment acquires the delegation details and the transaction details of the current delegation of the algorithm to be evaluated; acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrustment details, the transaction details and the historical transaction data; when a query instruction sent by a user is received, a corresponding scoring standard can be searched in a preset scoring template; when the scoring standard is found, obtaining corresponding scoring according to the index value and the scoring standard, displaying a scoring result, and evaluating the algorithm according to the scoring result; according to the invention, the index values corresponding to different evaluation indexes are determined according to the entrustment details, the transaction details and the historical transaction data, then the corresponding scoring standards are searched in the preset scoring template, and the index values are scored according to the scoring standards, so that compared with the conventional user self-evaluation, the evaluation accuracy can be improved.
Other embodiments or specific implementation manners of the algorithm transaction evaluation device of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. An algorithmic transaction evaluation method, the method comprising the steps of:
obtaining the entrusting details and the transaction details of the current entrusting of the algorithm to be evaluated;
acquiring historical transaction data within a preset time range, and determining index values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data;
searching a corresponding scoring standard in a preset scoring template according to a received query instruction;
and scoring the index values according to the scoring standard, and evaluating the algorithm to be evaluated based on a scoring result.
2. The algorithmic transaction evaluation method of claim 1, wherein said step of searching for a corresponding scoring criteria in a preset scoring template based on a received query comprises:
obtaining an evaluation index to be queried according to a received query instruction;
and searching a corresponding mapping relation table in a preset grading template according to the evaluation index to be inquired, and taking the mapping relation table as a grading standard.
3. The algorithmic transaction evaluation method according to claim 1, wherein the step of scoring the index value according to the scoring criteria and evaluating the algorithm to be evaluated based on the scoring result, comprises:
determining a target numerical value interval to which the index numerical value belongs and an index score interval corresponding to the target numerical value interval according to the grading standard;
acquiring a numerical interval lower limit value and a numerical interval upper limit value corresponding to the target numerical interval;
acquiring a score interval lower limit value and a score interval upper limit value corresponding to the target numerical value interval;
scoring the index value through a preset scoring formula according to the numerical interval lower limit value, the numerical interval upper limit value, the score interval lower limit value and the score interval upper limit value;
wherein, the preset scoring formula is as follows:
wherein S is a score result, X is the index value, X a+1 Is the upper limit value of the numerical range, X a Is the lower limit value of the numerical range, Y a+1 Is the upper limit value of the score interval, Y a Is the lower limit value of the score interval;
and evaluating the algorithm to be evaluated based on the grading result.
4. The algorithmic transaction evaluation method of any of claims 1 to 3, wherein the step of obtaining commitment details and deal details of a current commitment of an algorithm to be evaluated is preceded by the steps of:
when receiving an algorithm commission, extracting information of the algorithm commission;
judging whether the algorithm entrustment reaches a preset order dismantling condition or not according to an extraction result;
and if so, performing order splitting on the algorithm entrusts to obtain a single splitting flow, and obtaining entrustment details and transaction details according to the single splitting flow.
5. The algorithmic transaction evaluation method of claim 4, wherein the step of extracting information from the algorithm commitment upon receipt of the algorithm commitment comprises:
when an algorithm commission is received, security codes and parameter configuration in the algorithm commission are extracted;
acquiring corresponding transaction data according to the security code;
and configuring the transaction data and the parameters as extraction results.
6. The algorithmic transaction evaluation method of claim 5, wherein said step of obtaining commitment details and deal details for a current commitment of an algorithm to be evaluated is preceded by the steps of:
obtaining an evaluation index and a reference standard interval corresponding to a target algorithm according to the received parameter recommendation instruction;
acquiring historical transaction details based on the evaluation index and the reference standard interval;
and acquiring recommended parameters according to the historical transaction details, and displaying the recommended parameters.
7. The algorithmic transaction evaluation method according to claim 1, wherein after the step of obtaining historical transaction data within a preset time range and determining index values corresponding to different evaluation indexes according to the delegation details, the deal details, and the historical transaction data, the method further comprises:
if the query instruction is not found, acquiring an index subclass corresponding to the query instruction, and adding a relevant registration item in the index subclass;
and adding a mapping relation table in the initial scoring template according to the index subclass and the related registration items to obtain a preset scoring template.
8. An algorithmic transaction evaluation device, the device comprising:
the detail acquisition module is used for acquiring the consignment details and the transaction details of the current consignment of the algorithm to be evaluated;
the numerical value determining module is used for acquiring historical transaction data within a preset time range and determining index numerical values corresponding to different evaluation indexes according to the entrusting details, the transaction details and the historical transaction data;
the standard searching module is used for searching a corresponding scoring standard in a preset scoring template according to the received query instruction;
and the algorithm evaluation module is used for scoring the index values according to the scoring standard and evaluating the algorithm to be evaluated based on the scoring result.
9. An algorithmic transaction evaluation device, the device comprising: a memory, a processor and an algorithmic transaction evaluation program stored on the memory and executable on the processor, the algorithmic transaction evaluation program being configured to implement the steps of the algorithmic transaction evaluation method of any of claims 1 to 7.
10. A storage medium having stored thereon an algorithmic transaction evaluation program which, when executed by a processor, implements the steps of the algorithmic transaction evaluation method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210815055.2A CN115239104A (en) | 2022-07-12 | 2022-07-12 | Algorithm transaction evaluation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210815055.2A CN115239104A (en) | 2022-07-12 | 2022-07-12 | Algorithm transaction evaluation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115239104A true CN115239104A (en) | 2022-10-25 |
Family
ID=83673001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210815055.2A Pending CN115239104A (en) | 2022-07-12 | 2022-07-12 | Algorithm transaction evaluation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115239104A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777630A (en) * | 2023-08-16 | 2023-09-19 | 杭州星锐网讯科技有限公司 | Transaction splitting method and system based on federal learning |
-
2022
- 2022-07-12 CN CN202210815055.2A patent/CN115239104A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777630A (en) * | 2023-08-16 | 2023-09-19 | 杭州星锐网讯科技有限公司 | Transaction splitting method and system based on federal learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Winner determination for risk aversion buyers in multi-attribute reverse auction | |
| Fildes | Quantitative forecasting—the state of the art: econometric models | |
| Dean et al. | Scoring and profitability models for evaluating and selecting engineering projects | |
| JP2020523657A (en) | Method and system for evaluating vendors | |
| Fildes | Quantitative forecasting—The state of the art: Extrapolative models | |
| Wu et al. | Green supplier selection based on DEA model in interval-valued Pythagorean fuzzy environment | |
| CN102541899B (en) | Information identification method and equipment | |
| CN110689355A (en) | Client classification method, device, computer equipment and storage medium | |
| CN115239104A (en) | Algorithm transaction evaluation method, device, equipment and storage medium | |
| CN104156784A (en) | Bid evaluation method based on unascertained measurement comprehensive evaluation | |
| CN112053225A (en) | Loan overdue prediction method and device, electronic equipment and storage medium | |
| Coey et al. | Scalable optimal online auctions | |
| CN114186024A (en) | Recommendation method and device | |
| CN112396455A (en) | Pricing method, apparatus, device and medium for data assets | |
| CN115526479B (en) | Automatic part nesting method, device, equipment and storage medium | |
| CN110942405A (en) | Decoration project quotation system based on supplier material information | |
| CN116012086A (en) | Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium | |
| CN115982653A (en) | Abnormal account identification method and device, electronic equipment and readable storage medium | |
| CN115809891A (en) | Multi-product combined demand prediction method and device based on substitution and correlation effects | |
| CN115564276A (en) | Project statistics reserve management system, method and storage medium | |
| CN101763618A (en) | Financial investment decision information quality inspection method | |
| CN115293867A (en) | Financial reimbursement user portrait optimization method, device, equipment and storage medium | |
| CN110458302B (en) | Vehicle push repairing method and system based on user satisfaction | |
| CN114331188A (en) | Project value evaluation reference method and system based on big data | |
| Gnanasekaran et al. | An integrated model for supplier selection using fuzzy analytical hierarchy process: a steel plant case study |
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 |