WO2020168845A1

WO2020168845A1 - Method, system and device for optimizing transaction costs

Info

Publication number: WO2020168845A1
Application number: PCT/CN2020/070503
Authority: WO
Inventors: 李智
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-02-19
Filing date: 2020-01-06
Publication date: 2020-08-27
Also published as: CN110033372A; TW202032478A

Abstract

Provided are a method, system and device for optimizing transaction costs. The method comprises: determining a transaction price corresponding to a target trading volume; splitting an expected total transaction time limit corresponding to the target trading volume, and determining a plurality of expected transaction time periods; splitting the target trading volume, and determining a plurality of stage target trading volumes, wherein the stage target trading volumes correspond to the expected transaction time periods; and determining multiple batches of transaction parameters, according to which an actual transaction is performed for the target trading volumes, with the multiple batches of transaction parameters comprising trading prices of all transaction batches, a transaction time of each transaction batch and the trading volume of each transaction batch, wherein a determined transaction price is taken as a trading price; and the transaction batches corresponding to the multiple batches of transaction parameters correspond to the expected transaction time periods, the transaction time of the corresponding transaction batch is determined according to the expected transaction time period, and the trading volume of the corresponding transaction batch is determined according to the stage target trading volume corresponding to the expected transaction time period.

Description

Method, system and equipment for optimizing transaction cost

Technical field

This manual relates to the field of computer technology, in particular to a method, system and equipment for optimizing transaction costs.

Background technique

In the financial sector, foreign exchange exposure is simply the imbalance of foreign exchange payments for banks. Foreign exchange exposure mainly comes from the currency mismatch of assets, liabilities and capital, as well as foreign currency profits and foreign currency statement translation. When in a certain period of time, in the presence of foreign exchange exposure, exchange rate changes may bring losses to the bank's current income or economic value, thereby forming exchange rate risks.

In the prior art, in an application scenario where there is a large number of multi-national currency exchanges, in order to reduce the risk of foreign exchange exposure, foreign exchange transaction customers need to conduct foreign exchange lock-up business with banking institutions in advance. Foreign exchange lock is to lock the exchange rate. In banks, this business is called forward foreign exchange settlement and sale. In the case of frequent exchange rate fluctuations, the bank handles the operation of locking the exchange rate for the enterprise. On the day of foreign exchange settlement, the foreign exchange is not settled according to the exchange rate of the day, but according to the previously determined exchange rate. For example, in an application scenario, in order to hedge the risk of international business, a foreign exchange transaction customer needs to purchase a certain amount of foreign exchange at a certain price (locked exchange) with the bank one day in advance to prevent losses caused by foreign exchange fluctuations the next day.

However, although foreign exchange locking can reduce the risk of foreign exchange exposure to a certain extent; however, in the scenario of foreign exchange locking, if the short-term trading volume of foreign exchange customers is too large, the huge trading volume will have an impact on the market price, which will greatly Increase transaction costs for foreign exchange customers.

Summary of the invention

In view of this, the embodiments of this specification provide a method, system, equipment, and computer-readable medium for optimizing transaction costs, which are used to solve the problem of excessive short-term transaction volume in the prior art application scenario where transaction prices are locked in advance. This leads to the impact of market prices, thereby increasing transaction costs.

The embodiments of this specification adopt the following technical solutions:

The embodiments of this specification provide a method for optimizing transaction costs, including:

Determine the transaction price corresponding to the target volume;

Split the expected total trading time limit corresponding to the target trading volume, and determine multiple expected trading time periods;

Split the target transaction volume and determine the target transaction volume in multiple stages, wherein the target transaction volume in the stage corresponds to the expected transaction time period;

Determine the multi-batch transaction parameters on which the actual transaction is based on the target transaction volume, the multi-batch transaction parameters include the transaction price of all transaction batches, the transaction time of each transaction batch, and the transaction volume of each transaction batch ,among them:

Use the determined transaction price as the transaction price;

The transaction batches corresponding to the multi-batch transaction parameters correspond to the expected transaction time period, the transaction time of the corresponding transaction batch is determined according to the expected transaction time period, and the phase target corresponding to the expected transaction time period is determined The trading volume determines the trading volume of the corresponding trading batch.

Preferably, in an embodiment, splitting the expected total transaction time limit corresponding to the target transaction volume and determining multiple expected transaction time periods includes:

Predict the change in transaction frequency within the expected total transaction time limit in the current transaction scenario;

Split the expected total transaction time limit according to the transaction frequency change, and determine multiple expected transaction time periods.

Preferably, in one embodiment, the expected total transaction time limit corresponding to the target transaction volume is split, and multiple expected transaction time periods are determined, wherein:

Splitting the expected total transaction time limit corresponding to the target transaction volume according to a preset fixed time interval, and determining a plurality of expected transaction time periods.

Preferably, in an embodiment, splitting the target transaction volume and determining the target transaction volume in multiple stages includes:

Predict the changes in market trading volume within the expected total trading time limit under the current trading scenario;

Split the target transaction volume according to the change in the market transaction volume, and determine the target transaction volume in multiple stages.

Preferably, in an embodiment:

Predict the change in market volume within the expected total trading time limit under the current trading scenario, where the change in trading volume includes that the market phase transaction volume corresponding to each expected trading time period accounts for the expected total trading time limit The proportion of the corresponding total market volume;

The target transaction volume is split according to the changes in the market transaction volume, and multiple stages of target transaction volume are determined, wherein the proportion of the target transaction volume in the stage to the target transaction volume is the market corresponding to the corresponding expected transaction time period The proportion of the phased transaction volume to the total market volume corresponding to the expected total transaction time limit is the same.

Preferably, in an embodiment, the prediction of the market transaction volume change within the expected total transaction time limit under the current transaction scenario, wherein the prediction is made by using a machine learning model.

Preferably, in an embodiment, a machine learning model is used for prediction, wherein a time series prediction model is used for prediction.

Preferably, in an embodiment, a machine learning model is used for prediction, wherein the prediction is based on an elastic network.

Preferably, in an embodiment, the prediction is based on an elastic network, wherein the objective function is solved

min||y-Xβ|| ² +λ ₂ ||β|| ² +λ ₁ ||β|| ₁

Obtain the optimal solution of β, and calculate the value of the transaction volume y in the time period to be predicted according to the optimal solution of β, where:

y is the transaction volume within the time period to be predicted;

β is the optimal parameter to be solved;

λ ₁ is the penalty coefficient of L1 norm;

λ ₂ is the penalty coefficient of L2 norm;

X is a transaction feature item.

Preferably, in an embodiment:

Determine the transaction price corresponding to the target transaction volume, among which, execute the lock-in business and lock the purchase exchange rate.

This application also proposes a system for optimizing transaction costs, including:

Transaction price determination module, which is configured to determine the transaction price corresponding to the target transaction volume;

A trading period setting module, which is configured to split the expected total trading time limit corresponding to the target trading volume and determine multiple expected trading time periods;

The trading volume setting module is configured to split the target trading volume and determine the target trading volume in multiple stages, where the target trading volume in the stages corresponds to the expected trading time period;

The transaction parameter setting module is configured to determine the multi-batch trading parameters on which the actual transaction is based on the target transaction volume, and the multi-batch trading parameters include the transaction price of all transaction batches and the transaction time of each transaction batch And the transaction volume of each transaction batch, including:

Use the determined transaction price as the transaction price;

Preferably, in an embodiment:

The system also includes a trading volume prediction module configured to predict changes in market trading volume within the expected total trading time limit under the current trading scenario;

The trading volume setting module is configured to split the target trading volume according to changes in the market trading volume.

Preferably, in an embodiment:

The trading volume prediction module is configured to predict changes in the market trading volume, wherein the changes in the trading volume include that the market phase trading volume corresponding to each expected trading time period accounts for the total market trading volume corresponding to the expected total trading time limit Ratio of amount

The transaction volume setting module is configured to split the target transaction volume according to changes in the market transaction volume, wherein the proportion of the target transaction volume in the stage to the target transaction volume is the same as the market corresponding to the expected transaction time period The proportion of the phased transaction volume to the total market volume corresponding to the expected total transaction time limit is the same.

The embodiment of this specification also proposes a device for information processing on the user equipment side. The device includes a memory for storing computer program instructions and a processor for executing the program instructions. When the computer program instructions are When the processor executes, it triggers the device to execute the method described in the embodiment of this specification.

The above-mentioned at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: the method according to the present invention can avoid the impact of short-term large-scale transactions on market prices under the premise of pre-locking transaction prices, thereby effectively controlling transaction costs.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 is a flowchart of the method for running an application program in an embodiment of this specification;

FIG. 2 is a partial flowchart of the method for running an application program in an embodiment of the specification;

FIG. 3 is a flowchart of a method for operating an application program in an embodiment of this specification;

4 and 5 are the structural block diagrams of the system in the embodiment of this specification.

detailed description

In order to make the purpose, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

In the existing application scenarios, in order to hedge the risks of international business, foreign exchange customers need to purchase a certain amount of foreign exchange with the bank at a certain price (locked exchange) one day in advance to prevent losses caused by foreign exchange fluctuations the next day. However, in the lock-up scenario, if the short-term trading volume of foreign exchange customers is too large, the huge trading volume will have an impact on market prices, which will greatly increase the transaction costs of foreign exchange customers.

In response to the above problems, the embodiments of this specification propose technical solutions for optimizing transaction costs. In order to propose the technical solution of the embodiment of this specification, the inventor first made a detailed analysis of the application scenario of foreign exchange transactions in the prior art.

In actual application scenarios, the essence of the foreign exchange lock-in business is to lock the price of foreign exchange transactions in advance. Under the premise of foreign exchange lock-in, no matter how the market price fluctuates during foreign exchange transactions, the actual transaction price is still based on the previously locked foreign exchange transaction price. In order to control transaction costs, when performing a lock-up business, the pre-locked price is usually determined based on the prediction result of the average market price in the subsequent trading time range. Under the premise of foreign exchange lock, if there are a large number of transactions in the short term, then the transaction itself will impact the market price, causing the market price to deviate from the predicted price when the foreign exchange was locked. That is to say, when the market price is impacted, the foreign exchange transaction price locked by the foreign exchange lock business has been unable to achieve the transaction cost control effect expected at the time of the foreign exchange lock.

In view of the above problems, in order to control transaction costs, one of the most direct feasible methods is to make the transaction price fluctuate with market price fluctuations at any time, but this is equivalent to unable to lock foreign exchange. Therefore, in the embodiments of this specification, consider from another angle, try to avoid the impact of the transaction itself on the market price, and make the market price as close as possible to the predicted price when the exchange was locked, so as to optimize the transaction cost to the greatest extent.

Specifically, under the premise of foreign exchange lock, the fundamental reason for the impact of foreign exchange transactions on market prices is that the volume of foreign exchange transactions is too large, that is, relative to the current total market transaction volume, the transaction volume of foreign exchange transactions has reached A point that cannot be ignored. Therefore, in order to avoid an impact on the current market price, in the embodiments of this specification, a method of reducing transaction volume is adopted. However, the transaction volume of locked foreign exchange is determined by the needs of transaction customers, and it is impossible to directly reduce the transaction volume in order to control transaction costs. Therefore, in the embodiments of this specification, it is not to reduce the transaction volume required by the transaction client, but to split the transaction volume required by the transaction client into a plurality of relatively small transaction volumes, which are respectively performed at different transaction times. The node conducts transactions. In this way, for each transaction time node, it does not carry out the transaction of the transaction volume required by the transaction client, which is equivalent to the transaction volume of the transaction time node is reduced. In this way, at this transaction time node, the lock-in transaction cannot have an impact on the market price. In the end, when all transaction time nodes complete the transaction, the transaction of the transaction volume required by the transaction client is generally realized, and the lock transaction on each transaction time node does not have an impact on the market price, which is effective Optimize transaction costs.

Furthermore, in the above method flow, the cost of foreign exchange transactions under the premise of foreign exchange lock is effectively optimized. However, in actual application scenarios, the transaction scenario where the transaction price is locked in advance is not limited to foreign exchange transactions. In other trading scenarios, there are also situations where the transaction that locks the transaction price itself impacts the market price. Therefore, in the embodiment of this specification, other trading scenarios are expanded according to the foreign exchange trading application scenarios. Under the premise of pre-locking the trading price, the total trading volume of the locked trading price is split, and comparisons are made at different trading time nodes. Small transaction volume (relative to total transaction volume) transactions, so as to avoid impact on market prices under the premise of realizing total transaction volume, and ultimately achieve the optimization of transaction costs.

In the description of this specification, the technical solutions proposed in the embodiments of this specification are mainly for foreign exchange trading scenarios. However, it does not mean that the technical solutions in the embodiments of this specification can only be applied to foreign exchange trading scenarios. For different application scenarios, the technical solutions in the embodiments of this specification can be used not only to optimize the cost of foreign exchange transactions, but also to optimize the transaction costs of other asset objects such as stocks, futures, bonds, etc.

The following describes in detail the technical solutions provided by the embodiments of this specification in conjunction with the accompanying drawings. As shown in Fig. 1, in one embodiment, the method includes the following steps:

S110: Determine the transaction price corresponding to the target transaction volume;

S120: Split the expected total transaction time limit corresponding to the target transaction volume, and determine multiple expected transaction time periods;

S130: Split the target transaction volume and determine the target transaction volume in multiple stages, where the target transaction volume in the stage corresponds to the expected transaction time period determined in step S120;

S140. Determine multi-batch transaction parameters for the target transaction volume. The multi-batch transaction parameters include the transaction price of all transaction batches, the transaction time of each transaction batch, and the transaction volume of each transaction batch, where:

Use the determined transaction price as the transaction price in the multi-batch transaction parameters;

The transaction batch corresponding to the multi-batch transaction parameters corresponds to the expected transaction time period. The transaction time of the corresponding transaction batch is determined according to the expected transaction time period, and the corresponding transaction batch is determined according to the target transaction volume of the phase corresponding to the expected transaction time period Volume.

After multiple batches of transaction parameters are determined through the above process, transactions can be performed in actual transaction scenarios. Specifically, each transaction of a single transaction batch is performed on the actual time node corresponding to each transaction time included in the multiple transaction parameters, and the transaction volume is the transaction volume of the transaction batch in the multiple transaction parameters. In this way, after all the time nodes corresponding to the transaction time have passed, multiple batches of transactions for the target transaction volume (time-sharing and component transactions of multiple transaction time nodes) are realized. Since the transaction volume achieved by a single transaction time node is far less than the total target transaction volume, the impact of the transaction volume achieved by each transaction time node on the market price is effectively controlled. So as to finally realize the optimization of transaction cost.

Further, in an embodiment of this specification, the target trading volume may be the expected trading volume of a single trading client. In another embodiment of this specification, the target trading volume may also be the total expected trading volume of multiple different trading customers. According to the method of an embodiment of this specification, the total expected trading volume of multiple different trading customers can be taken as A whole is split and allocated to optimize the total transaction cost of multiple different transaction customers.

Further, for the application scenario of foreign exchange transactions, in an embodiment of this specification: in step S110, the transaction price corresponding to the target transaction volume is determined, wherein the foreign exchange lock service is performed to lock the purchase exchange rate; in step S140, the transaction price is locked The purchase exchange rate is used as the transaction price in the multi-batch transaction parameters. In this way, in the actual foreign exchange transaction scenario, foreign exchange purchase operations are carried out in time-sharing and multiple batches at the locked purchase exchange rate, and the impact of the foreign exchange purchase transaction itself on the market foreign exchange exchange rate can be controlled to the greatest extent, thereby ultimately optimizing foreign exchange transaction costs.

Further, in an embodiment of the present specification, in step S120, the expected total transaction time limit corresponding to the target transaction volume is split according to a preset fixed time interval, and multiple expected transaction time periods are determined.

For example, in an application scenario, the entire day of the current date is the expected total trading time limit (expected trading day, 0:00 to 12 pm), and the expected total trading time limit is divided into 24 at an interval of 1 hour Expected trading time period.

Further, in other embodiments of the present specification, in step S120, the expected total transaction time limit may also be divided according to other division rules to obtain the expected transaction time period.

Specifically, in an embodiment of the present specification, in step S120, the expected total transaction time limit is divided according to historical transaction records and/or predictions of actual market transaction conditions corresponding to the expected total transaction time limit. For example, the transaction frequency records in the historical transaction records are corresponding to the expected total transaction time limit. For time periods with relatively high transaction frequency, a relatively small time interval is used for division.

Specifically, in an embodiment of this specification, in step S120: predict the change in the transaction frequency within the expected total transaction time limit in the current transaction scenario; split the expected total transaction time limit according to the predicted transaction frequency change, and determine the amount Expected trading time period. For example, for a time period in which the transaction frequency is relatively high in the forecast result, a relatively small time interval is used in the division.

For example, in an application scenario, the entire day of the next day of the current date is the expected total transaction time limit (the expected transaction day, from midnight to midnight). According to the expected total transaction time limit, the transaction frequency is predicted. The predicted result is that the transaction frequency during working hours (from 9 a.m. to 5 p.m.) is twice that of the break time (from 0:00 to 9 a.m. and from 5 p.m. to 12 p.m.). Therefore, in the time range from 9 a.m. to 5 p.m., with 0.5 hour intervals, the expected total trading time limit is divided into 18 expected trading time periods. In the time range from 0:00 to 9: 00 and 5: 00 to 12: 00, the expected total trading time is divided into 15 expected trading time periods at 1 hour intervals. In total, the expected total trading time limit is divided into 33 expected trading time periods.

Further, in the embodiment of the present specification, when setting multi-batch transaction parameters, a variety of different types of transaction time can be selected. Specifically, in an embodiment of the present specification, the transaction time is a certain time range, for example, within 5 minutes from 10 am to 10:5 am. In an embodiment of this specification, the transaction time is a certain time node, for example, 10 o'clock in the morning.

Further, in the embodiment of this specification, in the process of determining the transaction time of each transaction batch according to the time range corresponding to the expected transaction time period, a variety of different determination strategies can also be selected.

Specifically, in an embodiment of this specification, the starting time of each expected transaction time period is selected as the transaction time, or a fixed period of time starting from the beginning time of each expected transaction time period is selected as the transaction time; for example, The expected total trading time limit is one working day (from midnight to 12 o'clock in the evening). The expected total trading time limit is divided at one-hour intervals, and each hour is regarded as the transaction time, or the first 5 minutes of each hour as the transaction time.

Specifically, in an embodiment of this specification, the middle moment of each expected transaction time period is selected as the transaction time, or a fixed period starting from the middle time of each expected transaction time period is selected as the transaction time; for example, the expected total The transaction time limit is one working day (0:00 to 12:00 pm), and the expected total transaction time limit is divided at one-hour intervals. The 30-minute time per hour is used as the transaction time, or the time range from 30 minutes to 35 minutes per hour As transaction time.

Further, in an embodiment of the present specification, in step S130, the target transaction volume is divided into equal parts, that is, the target transaction volume is evenly distributed to multiple expected transaction time periods. However, considering that in actual trading scenarios, the trading volume per unit time is constantly changing, within a certain time range, the market trading volume may be extremely small (or even 0). In this way, evenly distributing the transaction volume of each expected transaction time period may not avoid the impact on market prices.

Therefore, in an embodiment of this specification, the target transaction volume is split according to the market transaction volume changes in the actual transaction scenario, so that the split target transaction volume and the market transaction volume changes and fluctuations tend to be consistent, so as to maximize During the avoidance phase, the target volume has an impact on the market price.

Specifically, as shown in Fig. 2, in an embodiment of this specification, splitting the target volume to determine the target volume in multiple stages includes:

S210: Predict the changes in market volume within the expected total trading time limit under the current trading scenario;

S220: Split the target transaction volume according to the market transaction volume change, and determine the target transaction volume in multiple stages.

Further, in an actual transaction scenario, the calculation formula of the average price (VWAP) weighted according to the transaction volume is:

In formula 1: x _i (i=1, 2,...n) represents the i-th transaction volume; p _i (i=1, 2,...n) represents the i-th transaction price; w _i =x _i /(x ₁ +x ₂ +...x _n ) represents the weight of the i-th transaction price based on the volume.

In an embodiment of this specification, the goal of optimizing transaction costs is to make the final average transaction price as close as possible to the average transaction price of the entire market during the period.

Solving function

min|w ₁ ^(s) p ₁ +w ₂ ^(s) p ₂ +…w _n ^(s) p _n -(w ₁ ^(m) p ₁ +w ₂ ^(m) p ₂ +…w _n ^(m) p _n )| (2)

Let formula 2 satisfy:

In formulas 2-6, the superscript (s) represents transaction data, and the superscript (m) represents market data. V represents the day's trading target, that is, how much volume needs to be traded.

It can be obtained that the minimum value of the objective function (2) is zero. That is to say, if you can accurately predict the proportion of the market's trading volume in each time period to the day's trading volume, then split the orders according to this ratio, and time-share transactions. The final total average transaction price is equal to the average market transaction price.

Based on the above analysis, in an embodiment of this specification, the ratio of the market transaction volume in a specific time period to the total market transaction volume is used to describe the market transaction volume change. Specifically, in an embodiment of this specification:

Predict the change in market volume within the expected total trading time limit under the current trading scenario, where the change in volume includes the proportion of the market phase transaction volume corresponding to each expected trading time period to the total market volume corresponding to the expected total trading time limit ；

Split the target volume according to the changes in market volume, and determine the target volume in multiple stages. Among them, the ratio of the target volume to the target volume in the phase and the market phase volume corresponding to the corresponding expected transaction time period account for the expected total transaction time limit The corresponding proportion of the total market volume is the same.

For example, in an application scenario, suppose that in the forecast: the total trading volume of the day in the market is 100; the trading volumes corresponding to the 5 expected trading time periods are 10, 20, 30, 20, and 20, respectively.

If the target volume of the day is 10. Then finally the target trading volume is split into 5 orders, the trading volume is 1, 2, 3, 2, 2.

Further, in an embodiment of this specification, the market transaction volume change within the expected total transaction time limit under the current transaction scenario is predicted based on the historical transaction volume distribution.

Specifically, as shown in Figure 3, in an application scenario, it is expected to conduct a transaction of a target volume on a target trading day. The transaction process is as follows:

S310: Obtain historical transaction volume distribution before the start of the target trading day;

S320: Predict the trading volume of each time period of the target trading day according to the historical trading volume distribution;

S330: On the target trading day, before/at the trading time corresponding to the i-th time period, determine the expected phase transaction volume corresponding to the i-th time period according to the prediction result of step S320 (i is a non-zero natural number, and the starting value is 1);

S340: Perform a transaction at the transaction time corresponding to the multi-batch transaction parameter in the i-th time period, and complete the expected phase transaction volume determined in step S330;

S350: Judge whether the transaction on the day is over;

S360, if the transaction on the day is not over, set i=i+1, and return to step S330;

If the day's trading ends, the target volume has been achieved.

It should be noted that in the foregoing embodiment, it is equivalent to setting multiple batch transaction parameters while performing corresponding batch-wise time-sharing transactions in the actual transaction process. In other embodiments of this specification, it is also possible to set all the multi-batch transaction parameters at once before the transaction starts.

Further, in an embodiment of this specification, a machine learning model is used to predict changes in market volume. Specifically, in an embodiment of this specification, a time series prediction model is used for prediction. Specifically, in another embodiment of the present specification, prediction is made based on an elastic network (ElasticNet).

More specifically, in an embodiment of this specification, prediction is made based on an elastic network, where the objective function is solved

min||y-Xβ|| ² +λ ₂ ||β|| ² +λ ₁ ||β|| ₁ (7)

Obtain the optimal solution of β, and calculate the value of the transaction volume y in the time period to be predicted according to the optimal solution of β, in formula (7):

y is the transaction volume within the time period to be predicted;

β is the optimal parameter to be solved;

λ ₁ is the penalty coefficient of L1 norm;

λ ₂ is the penalty coefficient of L2 norm;

X is a transaction feature item.

Specifically, in an embodiment of the present specification, the transaction feature item X includes the transaction volume of the same time period of the past M trading days and the transaction volume of the past N time periods (similar to the concept of year-on-year and ring-on-quarter). The transaction characteristic item X is obtained by analyzing the historical transaction volume distribution.

It should be noted here that in the embodiments of this specification, the expected total transaction time limit splitting method and the target transaction volume splitting method can be combined arbitrarily according to specific application scenarios.

Specifically, in one embodiment, the expected total transaction time limit is split according to a preset fixed time interval (for example, an expected transaction time period per hour), and the target transaction volume is split by an even distribution method (for example, for daily The target trading volume is equally divided into 24 shares and allocated to 24 expected trading time periods).

Specifically, in one embodiment, the expected total transaction time limit is split according to the result of the transaction frequency prediction (for example, within the time range from 9 am to 5 pm, at 0.5 hour intervals, the expected total transaction time limit is divided into 18 One expected trading time period; within the time range of 0:00 to 9 am and 5 pm to 12 pm, the expected total trading time is divided into 15 expected trading time periods at 1 hour intervals). Split the target volume by means of equal distribution (for example, for the daily target volume, it is equally divided into 33 shares and allocated to 33 expected trading time periods).

Specifically, in an embodiment, the expected total transaction time limit is split according to a preset fixed time interval (for example, an expected transaction time period per hour); according to the market transaction volume of each expected transaction time period, the total market transaction The prediction result of the proportion of the volume is split into the target volume.

Specifically, in one embodiment, the expected total transaction time limit is split according to the result of the transaction frequency prediction (for example, within the time range from 9 am to 5 pm, at 0.5 hour intervals, the expected total transaction time limit is divided into 18 Expected trading time periods. In the time range from 0:00 to 9 AM and 5 PM to 12 PM, the expected total trading time is divided into 15 expected trading time periods at 1 hour intervals); according to each The predicted result of the proportion of the market transaction volume in the expected transaction period to the total market transaction volume splits the target transaction volume.

Further, in an embodiment of the present specification, the process of the method further includes determining whether the target transaction volume will have an impact on the market. When it is determined that the target volume will have an impact on the market, the subsequent operation of splitting the target volume is performed. Specifically, in an application scenario, the market tolerance threshold is determined based on historical transaction volume records and/or transaction volume prediction results. When the target transaction volume exceeds the market tolerance threshold, it is determined that the target transaction volume will have an impact on the market. Specifically, in an application scenario, the instantaneous transaction volume accounting for 3% of the total market pending order volume at the time will have an impact on the market price. Before splitting, compare the target transaction volume with the predicted market transaction volume to determine whether the split is needed.

Further, in an embodiment of the present specification, the process of the method further includes, after the target transaction volume is split, determining whether the split target transaction volume will have an impact on the market. When determining the stage target volume will have an impact on the market, further split the stage target volume.

Based on the method of the embodiment of this specification, the embodiment of this specification also proposes a system for optimizing transaction costs. Specifically, as shown in FIG. 4, in an embodiment of this specification, the system includes:

The transaction price determination module 410 is configured to determine the transaction price corresponding to the target transaction volume;

The trading time period setting module 420 is configured to split the expected total trading time limit corresponding to the target trading volume and determine multiple expected trading time periods;

The transaction volume setting module 430 is configured to split the target transaction volume and determine the target transaction volume in multiple stages, where the target transaction volume in the stage corresponds to the expected transaction time period;

Transaction parameter setting module 440, which is configured to determine multi-batch transaction parameters when performing multi-batch transactions for the target transaction volume. The multi-batch transaction parameters include transaction price, transaction time of each batch, and transaction volume of each batch , Among which, the transaction price locked by the transaction price lock module is the transaction price, the transaction time of each batch is determined according to the time range corresponding to the expected transaction time period, and the target transaction volume of each batch is determined according to the target transaction volume corresponding to the expected transaction time period. Volume.

Further, as shown in FIG. 5, in an embodiment of the present specification, the system further includes a trading volume prediction module 550. The trading volume prediction module 550 is configured to predict the market trading volume within the expected total trading time limit in the current trading scenario. Change; the trading volume setting module 430 is also configured to split the target trading volume according to the market trading volume changes.

Further, in an embodiment of the present specification, the trading volume prediction module 550 is configured to predict changes in market trading volume, where the changes in trading volume include the market corresponding to the market phase of each expected trading time period in the expected total trading time limit. The proportion of total trading volume; the trading volume setting module 430 is configured to split the target trading volume according to the changes in the market trading volume, where the ratio of the phase target trading volume to the target trading volume and the market phase trading volume corresponding to the corresponding expected trading time period The proportion of the total market volume corresponding to the expected total transaction time is the same.

Further, based on the method of the present invention, the present invention also proposes a device for information processing on the user equipment side. The device includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, When the computer program instructions are executed by the processor, the device is triggered to execute the method of the present invention.

In the 1990s, the improvement of a technology can be clearly distinguished between hardware improvements (for example, improvements in circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements in method flow). However, with the development of technology, the improvement of many methods and processes of today can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware entity modules. For example, a programmable logic device (Programmable Logic Device, PLD) (for example, a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. It is programmed by the designer to "integrate" a digital system on a PLD without requiring the chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly realized by using "logic compiler" software, which is similar to the software compiler used in program development and writing, but before compilation The original code must also be written in a specific programming language, which is called Hardware Description Language (HDL), and there is not only one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language) , AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description), etc., currently most commonly used It is VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be clear to those skilled in the art that just a little bit of logic programming of the method flow in the above-mentioned hardware description languages and programming into an integrated circuit can easily obtain the hardware circuit that implements the logic method flow.

The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as a part of the memory control logic. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for implementing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.

The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or implemented by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing this application, the functions of each unit can be implemented in the same one or more software and/or hardware.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

In a typical configuration, the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.

Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

It should also be noted that the terms "include", "include", or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or equipment including a series of elements not only includes those elements, but also includes Other elements that are not explicitly listed, or include elements inherent to this process, method, commodity, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, commodity, or equipment that includes the element.

This application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The above descriptions are only examples of this application and are not used to limit this application. For those skilled in the art, this application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the scope of the claims of this application.

Claims

A method for optimizing transaction costs, characterized in that it includes:

Determine the transaction price corresponding to the target volume;

Split the expected total trading time limit corresponding to the target trading volume, and determine multiple expected trading time periods;

Split the target transaction volume and determine the target transaction volume in multiple stages, wherein the target transaction volume in the stage corresponds to the expected transaction time period;

Determine the multi-batch transaction parameters on which the actual transaction is based on the target transaction volume, the multi-batch transaction parameters include the transaction price of all transaction batches, the transaction time of each transaction batch, and the transaction volume of each transaction batch ,among them:

Use the determined transaction price as the transaction price;

The transaction batches corresponding to the multi-batch transaction parameters correspond to the expected transaction time period, the transaction time of the corresponding transaction batch is determined according to the expected transaction time period, and the phase target corresponding to the expected transaction time period is determined The trading volume determines the trading volume of the corresponding trading batch.
The method according to claim 1, wherein splitting the expected total transaction time limit corresponding to the target transaction volume and determining multiple expected transaction time periods comprises:

Predict the change in transaction frequency within the expected total transaction time limit in the current transaction scenario;

Split the expected total transaction time limit according to the transaction frequency change, and determine multiple expected transaction time periods.
The method according to claim 1, wherein the expected total transaction time limit corresponding to the target transaction volume is split to determine multiple expected transaction time periods, wherein:

Splitting the expected total transaction time limit corresponding to the target transaction volume according to a preset fixed time interval, and determining a plurality of expected transaction time periods.
The method according to any one of claims 1 to 3, wherein splitting the target transaction volume and determining the target transaction volume in multiple stages comprises:

Predict the changes in market trading volume within the expected total trading time limit under the current trading scenario;

Split the target transaction volume according to the change in the market transaction volume, and determine the target transaction volume in multiple stages.
The method according to claim 4, characterized in that:

Predict the change in market volume within the expected total trading time limit under the current trading scenario, where the change in trading volume includes that the market phase transaction volume corresponding to each expected trading time period accounts for the expected total trading time limit The proportion of the corresponding total market volume;

The target transaction volume is split according to the changes in the market transaction volume, and multiple stages of target transaction volume are determined, wherein the proportion of the target transaction volume in the stage to the target transaction volume is the market corresponding to the corresponding expected transaction time period The proportion of the phased transaction volume to the total market volume corresponding to the expected total transaction time limit is the same.
The method according to claim 4 or 5, wherein the prediction of the market volume change within the expected total trading time limit in the current trading scenario, wherein a machine learning model is used for prediction.
The method according to claim 6, wherein the prediction is performed by using a machine learning model, wherein the prediction is performed by using a time series prediction model.
The method according to claim 6, wherein the prediction is performed using a machine learning model, wherein the prediction is performed based on an elastic network.
The method according to claim 8, wherein the prediction is based on an elastic network, wherein the objective function is solved

min||y-Xβ|| 2 +λ 2 ||β|| 2 +λ 1 ||β|| 1

Obtain the optimal solution of β, and calculate the value of the transaction volume y in the time period to be predicted according to the optimal solution of β, where:

y is the transaction volume within the time period to be predicted;

β is the optimal parameter to be solved;

λ 1 is the penalty coefficient of L1 norm;

λ 2 is the penalty coefficient of L2 norm;

X is a transaction feature item.
The method according to any one of claims 1-9, characterized in that:

Determine the transaction price corresponding to the target transaction volume, among which, execute the lock-in business and lock the purchase exchange rate.
A system for optimizing transaction costs is characterized in that it includes:

Transaction price determination module, which is configured to determine the transaction price corresponding to the target transaction volume;

A trading period setting module, which is configured to split the expected total trading time limit corresponding to the target trading volume and determine multiple expected trading time periods;

The trading volume setting module is configured to split the target trading volume and determine the target trading volume in multiple stages, where the target trading volume in the stages corresponds to the expected trading time period;

The transaction parameter setting module is configured to determine the multi-batch trading parameters on which the actual transaction is based on the target transaction volume, and the multi-batch trading parameters include the transaction price of all transaction batches and the transaction time of each transaction batch And the transaction volume of each transaction batch, including:

Use the determined transaction price as the transaction price;

The transaction batches corresponding to the multi-batch transaction parameters correspond to the expected transaction time period, the transaction time of the corresponding transaction batch is determined according to the expected transaction time period, and the phase target corresponding to the expected transaction time period is determined The trading volume determines the trading volume of the corresponding trading batch.
The system according to claim 11, wherein:

The system also includes a trading volume prediction module configured to predict the current trading scenario and the market trading volume change within the expected total trading time limit;

The trading volume setting module is configured to split the target trading volume according to changes in the market trading volume.
The system according to claim 11, wherein:

The trading volume prediction module is configured to predict changes in the market trading volume, wherein the changes in the trading volume include that the market phase trading volume corresponding to each expected trading time period accounts for the total market trading volume corresponding to the expected total trading time limit Ratio of amount

The transaction volume setting module is configured to split the target transaction volume according to changes in the market transaction volume, wherein the proportion of the target transaction volume in the stage to the target transaction volume is the same as the market corresponding to the expected transaction time period The proportion of the phased transaction volume to the total market volume corresponding to the expected total transaction time limit is the same.
A device for information processing on a user equipment side. The device includes a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, the The device executes the method of any one of claims 1 to 10.