CN116611570A

CN116611570A - Stock quantitative transaction optimization method based on big data

Info

Publication number: CN116611570A
Application number: CN202310603885.3A
Authority: CN
Inventors: 王国良; 郭广兴
Original assignee: Liaoning Shihua University
Current assignee: Liaoning Shihua University
Priority date: 2023-05-26
Filing date: 2023-05-26
Publication date: 2023-08-18

Abstract

The application relates to the field of financial stock trading, in particular to a stock quantitative trading optimization method based on big data. The method comprises the following steps: constructing a stock quantitative transaction model; inputting a fixed amount to a stock quantization transaction model; determining a backtracking period of a target stock, performing simulation on a stock quantitative transaction model with a fixed quantity input, determining a variable relation between a selling coefficient and a buying coefficient and account balance in the backtracking period, and drawing a scatter diagram; determining a sell coefficient and a buy coefficient based on the scatter plot; drawing a ladder diagram on the stock trend diagram to obtain a composite diagram; determining a real-time holding quantity and an upper limit holding quantity; and determining the stock trading date and the stock trading operation according to the composite graph. The application solves the stock quantitative transaction model by establishing the stock quantitative transaction model and adopting a big data technology and computer simulation, and performs data visualization processing on the result, thereby finally providing an investment strategy for a target investor to obtain remarkable benefits.

Description

Stock quantitative transaction optimization method based on big data

Technical Field

The application relates to the field of financial stock trading, in particular to a stock quantitative trading optimization method based on big data.

Background

Because these target investors are relatively less rich, lack of professional investment knowledge and experience, difficulty in successfully resolving emotional disturbances and other reasons, many investment failures are caused, and finally, huge economic losses are suffered. Therefore, how to get higher returns to investors in a limited investment scope becomes a problem to be studied urgently.

Disclosure of Invention

The application provides a stock quantized transaction optimization method based on big data, which can solve the problem that a target investor fails to invest due to limited investment amount and lack of expert knowledge.

The technical scheme of the application is a stock quantization transaction optimization method based on big data, comprising the following steps:

s1: constructing a stock quantization transaction model about account balances, stock transaction prices, sales coefficients and buy coefficients;

acquiring a fixed quantity comprising an account balance of a target investor, a target stock to be invested by the target investor and a stock trading price corresponding to the target stock, and inputting the fixed quantity into the stock quantization trading model;

s2: determining a backtracking period of a target stock, performing simulation on a stock quantitative transaction model with a fixed quantity input based on big data, correspondingly determining variable relations between a sales coefficient and a buying coefficient and account balances in the backtracking period, and drawing a scatter diagram corresponding to the variable relations based on the variable relations;

determining a sell coefficient and a buy coefficient corresponding to the target investor based on the scatter plot;

s3: acquiring a stock trend chart of target stocks extending from the beginning of a backtracking period;

drawing a ladder diagram on the stock trend diagram according to the time sequence according to the stock trading price according to the time sequence change and the selling coefficient and buying coefficient corresponding to the target investor, and obtaining a composite diagram comprising the stock trend diagram and the ladder diagram;

s4: determining a real-time holding quantity and an upper limit holding quantity of a target investor about a target stock;

according to the composite graph and based on the real-time hold quantity and the upper limit hold quantity, a stock exchange date of the target investor and a selling/buying stock exchange operation corresponding to the stock exchange date are determined.

Optionally, the step S1 includes:

s11: establishing a stock quantitative trading model about account balances, stock trading prices, stock trading unit numbers, and selling and buying coefficients by taking maximization of the account balances as an objective function and taking stock trading prices, selling coefficients and buying coefficients as constraint conditions;

the objective function in the stock quantized transaction model is as follows:

wherein J (t) represents the final account balance of the target investor after the stock market has been drawn up on day t, t=1, 2, …, N, within the investment period N days;

l represents the number of stock exchange units per stock exchange; a represents a sales coefficient; b represents a buying coefficient;

p (t) represents the stock exchange price of the target investor in the exchange time of the t day in the investment period N days;

c (t) represents the stock exchange price of the last successful exchange of the target investor in the previous t days in the investment period N days;

d (t) represents that the target stock held by the target investor corresponds to the stock exchange price per purchase during the investment period;

h (t) represents the ratio of the holding quantity of the target investor after the stock market receives the plate in the investment period N days and L;

and, constraints in the stock quantization trading model are as follows:

P(t)∈[P _min (t),P _max (t)]；

1<a<∞；

0<b<1；

wherein P is _min (t) and P _max (t) represents the lowest real-time price and the highest real-time price of the target stock on day t;

s12: the method comprises the steps of obtaining a fixed quantity comprising an account balance of a target investor, a target stock to be invested by the target investor, a stock trading unit quantity and a stock trading price corresponding to the target stock, and inputting the fixed quantity into the stock quantitative trading model.

Optionally, the step S2 includes:

s21: determining an investment request date of a target investor, and correspondingly determining a backtracking period according to the investment request date;

s22: determining a plurality of coverage periods with preset interval duration at intervals calculated from the beginning of the retrospective period;

s23: based on big data, carrying out simulation on a stock quantitative transaction model with fixed quantity input, and correspondingly determining a selling coefficient and a variable relation between a buying coefficient and net income in a coverage period;

the net benefit is the difference between the account balance during the coverage period and the account balance at the beginning of the coverage period;

s24: drawing a scatter diagram corresponding to the coverage period according to the variable relation;

s25: performing surface fitting on the scatter diagram, and determining selling coefficients and buying coefficients corresponding to the coverage period according to the surface fitting diagram obtained after the surface fitting;

s26: repeating the steps S23-S25 until obtaining selling coefficients and buying coefficients corresponding to a plurality of coverage periods;

s27: based on the sales coefficients and the buying coefficients corresponding to the coverage periods, the sales coefficients and the buying coefficients corresponding to the target investors are obtained.

Optionally, the step S24 includes:

s241: taking a preset value interval as a value basis, and taking values for the selling coefficient and the buying coefficient to obtain a plurality of coordinate values related to the selling coefficient and a plurality of coordinate values related to the buying coefficient;

s242: determining a plurality of coordinate points taking (the coordinate value of the selling coefficient, the coordinate value of the buying coefficient and the net benefit) as a coordinate form according to the variable relation between the selling coefficient and the buying coefficient and the net benefit and according to the coordinate value of the selling coefficient and the coordinate value of the buying coefficient;

s243: and drawing a scatter diagram corresponding to the coverage period according to the plurality of coordinate points.

Optionally, the step S25 includes:

s251: performing surface fitting on the scatter diagram corresponding to the coverage period to obtain a surface fitting diagram corresponding to the coverage period;

s252: determining vertex coordinates of the surface fitting graph corresponding to the coverage period;

s253: from the vertex coordinates, the sell and buy coefficients corresponding to the coverage period are determined.

Optionally, the step S27 includes:

s271: averaging the plurality of sales coefficients and the plurality of buying coefficients to obtain a first comprehensive transaction coefficient expressed by (sales coefficient, buying coefficient);

s272: determining a second comprehensive transaction coefficient which has the highest occurrence frequency and is expressed by (selling coefficient, buying coefficient) according to the occurrence frequencies of the plurality of selling coefficients and the plurality of buying coefficients;

s273: determining the selling coefficient corresponding to the biggest benefit (selling coefficient, buying coefficient) from the selling coefficients and the buying coefficients, and determining the selling coefficient corresponding to the biggest benefit (selling coefficient, buying coefficient) as a third comprehensive transaction coefficient;

s274: and averaging the first comprehensive transaction coefficient, the second comprehensive transaction coefficient and the third comprehensive transaction coefficient to obtain the selling coefficient and the buying coefficient corresponding to the target investor.

Optionally, the step S3 includes:

s31: acquiring a stock trend chart of target stocks extending from the beginning of a backtracking period;

s32: drawing two extension lines which are arranged in parallel and correspondingly represent the multiplication result between the stock trading price and the selling coefficient and the multiplication price between the stock trading price and the buying coefficient on the stock trend chart according to the time sequence;

s33: when any extension line intersects with the stock trend line, updating the two extension lines according to the stock trading price of the intersection point;

s34: and performing the steps S32-S33 according to the time sequence iteration to obtain a composite graph which extends to the back of the backtracking period and comprises a stock trend graph and a ladder graph.

Optionally, the step S4 includes:

s41: according to the composite graph, confirming the intersection points of the stock trend graph and the ladder graph after the backtracking period according to the time sequence;

s42: confirming a stock trading date according to the intersection point, and determining a tendency trading operation of selling/buying corresponding to the stock trading date;

s43: determining a stock exchange unit number and an upper limit holding number of the target investor with respect to the target stock, and a real-time holding number corresponding to a stock exchange date;

s44: when the real-time holding quantity is 0, determining that the stock trading operation is to buy the target stock of the stock trading unit quantity;

s45: determining that the stock trading operation is a target stock selling a stock trading unit number when the tendency trading operation corresponding to the stock trading date is selling and the real-time holding number is not 0;

s46: when the tendency trading operation corresponding to the stock trading date is buying, and the real-time holding quantity is greater than 0 and the difference between the real-time holding quantity and the upper limit holding quantity is greater than or equal to the stock trading unit quantity, determining that the stock trading operation is buying the target stock of the stock trading unit quantity.

The beneficial effects are that:

the application establishes a stock quantitative transaction model by applying a stock quantitative transaction theory, solves the stock quantitative transaction model by adopting a big data technology and computer simulation, and performs data visualization processing on the result, thereby finally providing an investment strategy for a target investor to obtain remarkable benefits.

The traditional stock investment method relies on subjective judgment of people, and the problems of low accuracy, slow decision-making speed, easy risk influence and the like often exist in stock selection and investment strategy establishment. In contrast, the quantitative trading theory builds a mathematical model based on a large amount of stock history data, automatically trades by using a computer program, identifies and utilizes rules and trends in the market by statistical analysis, and formulates different investment strategies, thereby realizing stable return on investment and improving investment efficiency and precision. Meanwhile, the data visualization technology can intuitively display the data analysis result, and the understanding of investors on market trend and individual presentation is enhanced.

Specifically, the improvement effect of the present application is as follows:

(1) The stock quantitative trading model provided by the application can customize a dedicated investment strategy for a target investor, is simple to operate, and can provide accurate stock trading opportunity for the target investor only by knowing the stock and investment principal of the target investor for investment;

(2) The application provides a novel solving mode when solving the stock quantitative transaction model, and the optimal value can be obtained only by computer simulation and big data technology, and the traditional optimizing methods such as numerical calculation are not needed, so that the method is simple, quick and widely applicable to various optimizing problems;

in summary, the stock quantitative transaction method based on the big data technology can be combined with the data visualization technology to perform case analysis and optimization so as to further improve the investment benefit, thereby solving the problem that a target investor fails to invest due to limited investment amount and lack of professional knowledge.

Drawings

In order to more clearly illustrate the technical solution of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a flow chart of a stock quantized transaction optimization method based on big data in an embodiment of the application;

FIG. 2 is a schematic diagram of a ladder diagram drawing unit according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a ladder diagram of an embodiment of the present application;

FIG. 4 is a diagram of a simulated trend of stock exchanges plotted with optimal trading coefficients in an embodiment of the present application;

FIG. 5 is a logic diagram of a stock quantization transaction model according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The embodiments described in the examples below do not represent all embodiments consistent with the application. Merely exemplary of systems and methods consistent with aspects of the application as set forth in the claims.

The application provides a stock quantized transaction optimization method based on big data, as shown in fig. 1, fig. 1 is a flow diagram of the stock quantized transaction optimization method based on big data in the embodiment of the application, and the method comprises the following steps:

the account balance of the target investor, the target stock to be invested by the target investor and the fixed quantity of the stock trading price corresponding to the target stock are acquired, and the fixed quantity is input into the stock quantization trading model.

Wherein, step S1 includes:

the objective function in the stock quantized transaction model is as follows:

h (r) represents the ratio of the holding quantity of the target investor after the stock market receives the plate in the investment period N days and the t day to L;

and, constraints in the stock quantization trading model are as follows:

P(t)∈[P _min (r),P _max (t)]；

1<a<∞；

0<b<1；

Specifically, the stock quantization trading optimization method in the embodiment of the application can help a target investor to customize an investment strategy to assist the target investor in a method for reducing investment errors from the source.

Assume the conditions:

taking the stock of an industrial and commercial bank as an example, before specific transaction rules are given, in order to further clearly describe the method provided by the embodiment of the application, the following assumption conditions need to be set:

(1) The time period for which the investor's return is maximized is a fixed period (i.e., the number of days on which the investment return maximization transaction occurs), and the investor can only hold a limited number of stocks during that fixed period.

(2) When the stock price meets the trade condition, the number of stocks traded by the investor each time is a fixed legal constant.

(3) The investor's account funds only consider the income and expenditure costs generated when trading stocks, do not consider the transaction costs at the time of stock trading, etc., and the investor's account initial amount is sufficient to buy a limited number of stocks.

From the above, the above-mentioned related assumption conditions are not out of generality.

(II) symbolic representation:

to specifically quantify each transaction and establish a corresponding investment return function, based on the above assumptions, a relevant specific variable symbol definition needs to be given.

The method comprises the following steps:

the natural number N represents the concrete investment timeliness;

l represents the number of units of a specific stock exchange per time;

δL represents the number of stocks held at most during the period N days of the investment trade, where δ is a natural number given greater than 0;

P(t)∈R _>0 t=1, 2, …, N, represents the stock price in the trade time of the t-th day in the investment period N-th day, satisfying P (t) ∈ [ P ] _min (t),P _max (t)]Wherein P is _min (t) and P _max (t) minimum and maximum prices among stock prices on the t-th day;

m (t), t=1, 2, …, N, representing the number of shares held after the stock market receives the disc on day t in the investment period, where M (1) =l represents the number of stocks initially held by the investor;

c (t), t=1, 2, …, N, represents the price of the last successful transaction within the first t days of the investment period, wherein C (1) =p (1) represents that the investor first transaction occurred on the first day;

J(t)∈R _>0 t=1, 2, …, N, represents the account balance of the investor after the t-th share is received during the investment period, the initial balance of the investor account is ω, wherein the account balance J (1) =ω -C @ after the 1-th share is received1)L；

D∈R ^δ The price of each purchase corresponding to the stock held by the investor in the investment period is shown, and the initial value is set as follows: d (1) =c (1), D (2) = … =d (δ) =0

h (t) ∈ {0,1, …, δ } represents a ratio of the amount of holding the warehouse after closing the warehouse at the t-th day of the investment period to L, where h (1) =1;

m (t) =h (t), while D (1) >0, D (2) >0, …, D [ h (t) ] >0, d= [ h (t) +1] = … =d (δ) =0 when h (t) ∈ {0,1, …, δ };

when h (t) =0, D (1) = … D (δ) =0.

(III) model application scene:

based on the above-described correlation assumptions and correlation definition variables, specific stock exchange rules are as follows:

(1) Case one: when the current price of the stock satisfies the sell condition:

if the current price of the stock meets the sell condition, i.e

P(t)≥aD[h(t-1)]∩h(t-1)≥1；

t＝2,3,…,N；

Where a ε [1, +% represents the sales coefficient, and a-time the price of the current stock rises to the price corresponding to Dh (t-1) ].

Accordingly, the trade price when selling stocks at this time is as follows:

C(t)＝aD[h(t-1)]；

accordingly, the purchase price of the stock sold at this time is emptied in D according to the previous definition, i.e

D[h(t-1)]＝0；

The number of stocks held by the investor at this time is as follows:

M(t)＝M(t-1)-L；

the account balance of the investor at this time is as follows:

J(T)＝J(t-1)+aD[h(t-1)]L；

h(t)＝h(t-1)-1；

t＝t+1。

(2) And a second case: when the current price of the stock satisfies the purchase condition:

if the current price of the stock meets the purchase condition, i.e

P(t)≤bC[h(t-1)]∩h(t-1)≤δ-1；

t＝2,3,…,N；

Where b E (0, 1) represents the buying coefficient, i.e. the current stock price drops b times the last trade price.

Accordingly, the trade price for buying stock at this time is as follows:

C(t)＝bC(t-1)；

accordingly, the number of stocks held by the investor at this time is as follows:

M(t)＝M(t-1)+L；

accordingly, the purchase price of the stock purchased at this time is stored in D, i.e

h(t)＝h(t-1)+1；

D[h(t)]＝C(t)；

Accordingly, the account balance of the investor at this time is as follows:

J(T)＝J(t-1)-bC(t-1)L；

t＝t+1。

(3) And a third case: when the current price of the stock satisfies the purchase condition:

if the current stock price does not meet the two conditions, the investor executes holding action to wait for the next change of the stock price, and the holding coefficient is 1, namely

h(t)＝h(t-1)；

C(t)＝C(t-1)；

t＝t+1；

Until the stock price meets one of the two conditions.

From the above, when the value of a is smaller, that is, the expected selling price is lower, the stock exchange unit number is higher; when the value of a is large, the selling price is expected to be high, and the number of stock exchange units is small.

When the value of b is large, i.e., the expected purchase price is high, the stock exchange unit number is high; when the value of b is smaller, the price of buying is expected to be lower, and the number of units of stock exchange is smaller.

based on the scatter plot, a sell coefficient and a buy coefficient corresponding to the target investor are determined.

Wherein, step S2 includes:

s21: the investment request date of the target investor is determined, and the retrospective period is correspondingly determined according to the investment request date.

Specifically, taking the stock exchange history data of 250 trade days of the commercial bank as an example, an example will be described with respect to step S2 and the subsequent steps.

Assuming that the investor makes an investment request at the 100 th trading day, 100 trading days are traced forward.

Wherein, the 100 th transaction date is the investment request date;

150 trading days after the 100 th trading day are investment periods;

the first 100 trade days are retrospective periods.

S22: and determining a coverage period with a preset interval duration at a plurality of intervals calculated from the beginning of the retrospective period.

Specifically, due to the difference in the preset time interval, i.e., the time span, the generated transaction coefficients are also different; the difference in trading coefficients results in different benefits generated by the trading strategy. It is important to select a suitable time span, which is 20 transaction days in the embodiment of the present application.

Namely, 20 trading days are taken as preset time intervals, 100 trading days are determined to be 5 coverage periods, and the 5 coverage periods are respectively 1-20, 1-40, 1-60, 1-80 and 1-100.

The first diary of the 1 st coverage period is T1. On the day T1, a moment is randomly selected to buy the stock, and the embodiment of the application selects the stock to buy when the stock price is 4.37, and takes the stock as the initial buying price.

Let the number of stocks per trade L be 100, and the upper limit of the number of stocks held by the investor be 300.

S23: based on big data, carrying out simulation on the stock quantitative transaction model with fixed quantity input, and correspondingly determining the selling coefficient and the variable relation between the buying coefficient and the net income in the coverage period.

The net benefit is the difference between the account balance during the coverage period and the account balance at the beginning of the coverage period.

In particular, embodiments of the present application are directed to computer simulations of established stock quantized transaction models, i.e., representing the stock quantized transaction model with a computer program. In the process, only the optimal trading coefficients, i.e., a and b, and other set fixed amounts (initial price of stock, number of stocks per trade, upper limit of number of stocks held by investors, etc.) need be input to this computer program, which will output a corresponding net benefit (dependent variable) accordingly.

S24: and drawing a scatter diagram corresponding to the coverage period according to the variable relation.

Wherein, step S24 includes:

specifically, in the embodiment of the present application, the preset value interval is 0.01.

The value range of a is 1.01-1.1, and the interval is 0.01; b is 0.9-0.99 and the interval is 0.01.

To sum up 10 x 10 groups (a, b) have 10 x 10 final account balances y, respectively.

specifically, after setting the other variables, a set of values of the sales coefficients (values of a and b) is input into the computer program, and the computer program outputs a set of values of the benefits (y) corresponding to a and b. And then inputting a large number of a and b by adopting a large data technology, and correspondingly obtaining a large number of y corresponding to the large data technology.

Specifically, 100 three-dimensional scatter points can be obtained with a as the abscissa and b as the ordinate, and the benefit value Y as the ordinate, that is, the X-axis, the Y-axis, and the Z-axis.

S25: and carrying out surface fitting on the scatter diagram, and determining the selling coefficient and the buying coefficient corresponding to the coverage period according to the surface fitting diagram obtained after the surface fitting.

Wherein, step S25 includes:

Specifically, a three-dimensional scatter diagram is simulated into a three-dimensional curved surface, and the optimal solution of the model is obtained by searching the vertexes of the three-dimensional curved surface. The coordinates of the vertices of this three-dimensional surface are the optimal values of a and b and the optimal account final balance we want.

In some embodiments, the preset interval may be set to 0.001 or 0.0001, and 10000 or 1000000 three-dimensional scattered points will be obtained correspondingly, and a finer curved surface may be fitted to obtain a more accurate optimal solution.

S26: and repeating the steps S23-S25 until the selling coefficients and buying coefficients corresponding to the coverage periods are obtained.

Specifically, from the 5 coverage periods, the best transaction coefficients for the 5 coverage periods are determined accordingly.

Wherein, step S27 includes:

specifically, a first integrated transaction coefficient is obtained by averaging five sets of optimal transaction coefficients

specifically, the transaction coefficient with the largest occurrence number in the five groups of transaction coefficients is searched as the second comprehensive transaction coefficient

specifically, the transaction coefficient with the largest corresponding benefit in the five groups of transaction coefficients is searched as the third comprehensive transaction coefficient

Specifically, the three composite coefficients are averaged to obtain a final trading coefficient, i.e., an optimal trading coefficient (a ^* ，b ^* )。

and drawing a ladder diagram on the stock trend diagram according to the time sequence according to the stock trading price according to the time sequence change and the selling coefficient and the buying coefficient corresponding to the target investor, so as to obtain a composite diagram comprising the stock trend diagram and the ladder diagram.

Wherein, step S3 includes:

specifically, as shown in fig. 2, fig. 2 is a schematic diagram of a drawing unit of a ladder diagram in an embodiment of the present application. In fig. 2, the upper extension line represents the multiplied price between the stock exchange price and the buying coefficient, and the lower extension line represents the multiplied result between the stock exchange price and the selling coefficient.

specifically, as shown in fig. 3, fig. 3 is a schematic diagram of the step diagram in the embodiment of the application. In fig. 3, when any one of the extension lines intersects with the stock trend graph (the stock trend graph is not shown in fig. 3, the intersection point of the vertical line on the right side of the graph and the horizontal line on the left side of the graph represents the intersection point), then the two extension lines are updated with the stock exchange price of the intersection point, and then sequentially drawn.

In which an extension line, which is not extended, is provided in the previous drawing unit, and is indicated by a broken line in fig. 3.

Specifically, as shown in fig. 4, fig. 4 is a stock exchange simulated trend chart drawn through an optimal trading coefficient in an embodiment of the present application, where the stock exchange simulated trend chart includes: candles and steps.

The step S4 includes:

specifically, the trade date of the target stock may be determined according to the intersection position of the candles and ladder diagrams. By analyzing the stock exchange simulated trend graph, it can be decided to start buying stock on 139 th, 140 th or 142 th day.

Specifically, as shown in fig. 5, fig. 5 is a logic diagram of implementing a stock quantization transaction model according to an embodiment of the present application, and the following is summarized according to the situation shown in fig. 2:

when the price P (t) of the stock at a certain moment is more than or equal to the product of the price of the last purchased stock and the selling coefficient and the number of the stocks in the hand is not empty, selling the stock with fixed number;

when the price of the stock at a certain moment is less than or equal to the product of the price of the last trade stock and the buying coefficient and the number of the stocks in the hand is less than the set number of the most held stocks, buying a fixed number of stocks;

when the stock price at a certain moment is up to the two conditions, then a holding action is taken.

The above steps are now specifically illustrated.

The investor is set to hold a stock upper limit of 300 shares at most, and 100 shares are fixedly traded each time. There are three initial purchase points, accordingly. In turn, the simulated holding stock numbers are 0, 100, and 200 shares.

Strategy one: the investor makes an investment request on the 101 st day, and the first time on the 139 th day the situation that the number of the simulated holding stocks is 0 shares appears, the initial buying point of the investor is used.

Strategy II: after 101 days, the first time a situation in which the number of simulated holding stocks is 100 shares occurs at 140 days, then it is the initial point of purchase for the investor.

Strategy III: after 101 days, the first time a situation occurs at day 142 where the simulated holding stock quantity is 200 shares, this time as the initial point of purchase for the investor.

It should be noted that holding 300 shares of stock is not commercially available because the upper holding limit is reached.

In summary, the embodiment of the application has the following advantages:

(1) The stock quantitative trading model provided by the embodiment of the application can customize a dedicated investment strategy for a target investor, is simple to operate, and can provide accurate stock trading opportunity for the target investor only by knowing the stock and investment principal of the target investor for investment;

(2) The embodiment of the application provides a novel solving mode when solving the stock quantitative transaction model, and the optimal value can be obtained only by computer simulation and big data technology, and the traditional optimizing methods such as numerical calculation and the like are not needed, so that the method is simple, quick and widely applicable to various optimizing problems;

(3) The embodiment of the application draws a novel stock trading simulated trend graph which consists of a candle graph and a ladder graph, and is unique in that the intersection point position of the candle graph and the ladder graph is the stock trading position, so that the data analysis result can be intuitively displayed, and the understanding of investors on market trend and individual presentation is enhanced;

(4) The embodiment of the application can provide multiple investment strategies for a target investor aiming at the same stock for selection by analyzing the stock exchange simulated trend chart.

The foregoing describes embodiments of the present application in detail, but the disclosure is merely a preferred embodiment of the present application and should not be construed as limiting the scope of the embodiments of the present application. All equivalent changes and modifications within the scope of the present application should be made within the scope of the present application.

Claims

1. A method for optimizing quantitative trading of stocks based on big data, comprising:

2. The method for optimizing stock quantization trading of big data according to claim 1, wherein the step S1 comprises:

the objective function in the stock quantized transaction model is as follows:

and, constraints in the stock quantization trading model are as follows:

P(t)∈[P _min (t),P _max (t)]；

1<a<∞；

0<b<1；

3. The method for optimizing stock exchanges based on big data according to claim 1, wherein said step S2 comprises:

4. The method for optimizing stock exchanges based on big data according to claim 3, wherein said step S24 comprises:

5. The method for optimizing stock exchanges based on big data according to claim 3, wherein said step S25 comprises:

6. The method for optimizing stock exchanges based on big data according to claim 3, wherein said step S27 comprises:

7. The method for optimizing stock exchanges based on big data according to claim 1, wherein the step S3 comprises:

8. The method for optimizing stock exchanges based on big data according to claim 1, wherein said step S4 comprises: