TWI705408B - Prediction method for price trend of financial product and prediction system using thereof - Google Patents

Abstract

A prediction system for the price trend of a financial product is applicable to predict the price trend of the financial product at a Jth day after the predicted period. The prediction system includes a processor, a storage module, and an output module signally connected with each other. Accordingly, similar information can be selected and recognized in a two-stage process, so that the possible price trend of the financial product at a certain time in the future can be determined in a more objective manner, thus facilitating the user to make investment strategy properly.

Description

Forecasting method and system of financial commodity price trend

The present invention relates to the trend prediction of a financial commodity price, in particular to a method and system for predicting the price trend of a financial commodity.

With the improvement of human living standards, in addition to earning active income through work, more and more people are earning passive income through investment and financial management. The list of eligible investment targets is endless, and various financial products (such as stocks, bonds, funds, etc.) are more popular due to the relatively abundant public information.

The current forecast of the price trend of financial products is mainly based on judging the past market transactions and the rules of experience of forecasters. However, this kind of forecasting method may not properly reflect the real investment environment due to the subjective consciousness of forecasters.

In view of this, a financial product price trend prediction system is suitable for predicting the price trend of financial products on the J day after the estimated time period. The prediction system includes a processor, a storage module and an output module, and the processor signal connection Between the storage module and the output module. The processor obtains multiple historical price images and estimated price images of financial products from the storage module. These historical price images correspond to the price data of financial products in multiple historical time periods, and the estimated price images correspond to Price data for the estimated time period. The processor divides each historical price image into Multiple historical price blocks and divide the estimated price image into multiple estimated price blocks, and each historical price block is located in a different position of the corresponding historical price image, and each estimated price block is located at the estimated price Different positions of the image. The processor compares the estimated price blocks of the estimated price image and the price blocks of each historical price image, and selects a plurality of comparable price images from the historical price images, the analogous ones The price image corresponds to multiple comparable price data. The processor classifies the comparable price data into the rising group and the falling group according to the price data on the 0th day and the J day after the corresponding historical time interval for each comparable price data, where J is greater than 0. The processor compares the estimated price data corresponding to the estimated price image with the comparable price data to determine the classification result of the estimated price data, and the classification result corresponds to one of the rising group and the falling group. Finally, the output module outputs the classification results.

In one or more embodiments, the processor further determines whether each comparable price data is an ascending group or a descending group based on the ratio of the price data on the 0th day and the Jth day after the corresponding historical time period. .

In one or more embodiments, the processor further obtains each comparable price data according to the ratio of the price data from day -J to day +J to day 0 after each comparable price data in the corresponding historical time period The processor further determines the value of the estimated price data based on the Euclidean distance from the -J day to the +J day after the average curve of the estimated price data and each comparable price data in the corresponding historical time period Classification results.

In one or more embodiments, the processor further determines the closing price, at least one technical indicator, and at least one general economic indicator of each comparable price data from day 0 to day J after the corresponding historical time period. The comparable price images are classified as rising or falling groups. Wherein, the processor further uses the closing price, the at least one technical indicator, and the at least one overall economic indicator As a plurality of characteristic values, input the clustering algorithm with these characteristic values to compare the estimated price data with the comparable price data to determine the classification result of the estimated price data. Further, the processor further determines an importance order of the characteristic values according to the price data of the estimated price data on the I day after the estimated time period, where I is less than J.

In one or more embodiments, the processor further determines the classification result of the estimated price data based on the price data of the estimated price data on the first day after the estimated time period, where I is less than J.

In another embodiment, a method for predicting the price trend of financial products is suitable for predicting the price trend of financial products on the J-th day after the estimated time period. The method includes the following steps. Historical price image acquisition step: Obtain multiple historical price images of financial products, where the historical price images correspond to the price data of the financial product in multiple historical time periods, and each historical price image includes multiple historical prices Block, each historical price block is located in a different position of the corresponding historical price image; the step of obtaining the estimated price image: obtain the estimated price image of the financial product, where the estimated price image corresponds to the estimated time period Price information, the estimated price image includes multiple estimated price blocks, and each estimated price block is located in a different position of the estimated price image; the first-stage type identification step: compare the value of the estimated price image The estimated price blocks and the historical price blocks of each historical price image, and a plurality of comparable price images are selected from the historical price images, wherein the comparable price images correspond to a plurality of comparable prices Data; the second-stage pattern identification step: According to the price data of each comparable price data on the 0th day and the J day after the corresponding historical time period, the comparable price data are classified into rising and falling groups, Where J is greater than 0; and the trend determination step: compare the estimated price data corresponding to the estimated price image with the comparable price data to determine whether the estimated price data is a rising group or a falling group group.

In one or more embodiments, in the second-stage pattern recognition step, it further includes: according to the ratio of the price data on the 0th day to the Jth day after each comparable price data in the corresponding historical time period, each Comparable price data are classified as rising or falling groups.

In one or more embodiments, in the second-stage pattern recognition step, the step further includes: according to each comparable price data, from the -J day to the +J day and the 0 day after the corresponding historical time period The ratio of the price data to obtain the average curve of each comparable price data; in the trend determination step, it further includes: according to the average curve of the estimated price data and each comparable price data on the -J day after the corresponding historical time period The Euclidean distance to the +J day determines whether the estimated price data is the rising group or the falling group.

In one or more embodiments, in the second-stage pattern recognition step, it further includes: a closing price from day 0 to day J after each comparable price data in the corresponding historical time period, at least one Technical indicators and at least one overall economic indicator classify each comparable price image into an up or down ethnic group. Wherein, in the trend determination step, it further includes: using the closing price, the at least one technical indicator, and the at least one overall economic indicator as multiple feature values, and inputting the clustering algorithm with the feature values to compare the estimated price data With these comparable price data, determine whether the estimated price data is an up or down group. Furthermore, the aforementioned prediction method further includes a feedback correction step: according to the price data of the estimated price data on the first day after the estimated time period, the importance order of the characteristic values is re-determined, where I is less than J.

In one or more embodiments, the aforementioned forecasting method further includes a feedback correction step: according to the price data of the estimated price data on the first day after the estimated time period, re-determine whether the estimated price data is the rising group or the falling group, Where I is less than J.

In summary, according to the system and method for predicting the price trend of financial products according to one or more embodiments of the present invention, similar data can be screened by two-stage type identification, and it is possible to more objectively judge whether a financial product is in the future. The possible price trends and trends at a time point are conducive to the user's formulation of investment strategies. In addition, through its feedback correction mechanism, the investment strategy can be appropriately modified according to the actual situation, and the practicability of the system can be improved.

80: prediction system

81: processor

82: storage module

83: Image capture module

84: output module

S101~S108, S1051~S1053, S1061~S1062: steps

FIG. 1 is a schematic structural diagram of a system for predicting the price trend of financial commodities according to the first embodiment of the present invention.

Fig. 2 is a flow chart of the steps of the method for predicting the price trend of financial commodities according to the second embodiment of the present invention.

Fig. 3 is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the third embodiment of the present invention.

4 is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the fourth embodiment of the present invention.

Fig. 5 is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the fifth embodiment of the present invention.

Fig. 6 is a flow chart of detailed steps of the method for predicting the price trend of financial commodities according to the sixth embodiment of the present invention.

Fig. 7 is a flow chart of the steps of the method for predicting the price trend of financial commodities according to the seventh embodiment of the present invention.

Fig. 8 is the flow of steps of the method for predicting the price trend of financial commodities according to the eighth embodiment of the present invention Cheng Tu.

As shown in FIG. 1, it is a schematic structural diagram of a system for predicting the price trend of financial products according to the first embodiment of the present invention, which is suitable for predicting the price trend of a financial product on the Jth day after the estimated time period. Financial products can be, for example, various securities in domestic and foreign markets, such as stocks, bonds, currencies, commercial papers, etc., and financial products can also be derivative financial products such as futures, options, and warrants.

As shown in FIG. 1, the prediction system 80 includes a processor 81, a storage module 82, an image capture module 83 and an output module 84. The processor 81, the storage module 82, the image capture module 83, and the output module 84 are directly or indirectly connected to each other through wired or wireless signals. For example, the prediction system 80 may be an industrial computer, a personal computer, a notebook computer, a smart phone, a tablet computer, etc. Here, the processor 81 may be implemented by one or more processing elements. Here, each processing element can be a microprocessor, a microcontroller, a digital signal processor, a microcomputer, a central processing unit, a field programming gate array, a programmable logic device, a state machine, a logic circuit, an analog circuit, a digital circuit, and / Or any device based on the operation command operation signal (analog and/or digital), but it is not limited here. The storage module 82 may be realized by one or more storage elements. Among them, each storage element can be, for example, a non-volatile memory, a hard disk, an optical disk, or a tape, but it is not limited here. In addition, it should be noted that the data stored in the storage module 82 can come from a terminal connected via a wired or wireless connection, and can be updated in real time. The image capturing module 83 can be a camera, a video camera, etc., but it is not limited here. The output module 84 can be a screen, a printer, or a voice output device (such as a speaker), but it is not limited here. The following is a further description of the functions of each component in the prediction system 80.

First, the processor 81 obtains multiple historical price data and estimated price data of financial commodities from the storage module 82. Among them, the historical price data respectively correspond to the price data of the financial product in multiple historical time periods, and the estimated price data corresponds to the price data of the estimated time period. For example, Table 1 shows the first 10 records of historical price data of a certain financial product. Each historical price data corresponds to the price data of the financial product in different historical time periods; and in this embodiment, each historical price data covers The data interval is about one and a half months, but it is not limited to this. In addition, in one embodiment, the price data is the closing price of a financial product, but the price data can also include multiple types of data, for example, it can be a combination of the closing price, transaction volume, or technical indicators of financial products. The technical indicators can be It is MACD, KD, Bollinger Band, RSI, etc.

It should be noted that, in one embodiment, the historical price data and the estimated price The data can be graphical data. Alternatively, in some embodiments, historical price data and estimated price data may also be non-graphical data. Therefore, the image capturing module 83 is used to capture a plurality of historical price images according to the historical price data and the estimated price images according to the estimated price data. Specifically, the image capture module 83 can take photos, computer screenshots, etc., on the historical price data and estimated price data to obtain historical price images and estimated price images (hereinafter collectively referred to as images) These images can be stored in the storage module 82 or provided to the processor 81 for subsequent processing immediately after being acquired.

After acquiring the image, the processor 81 divides each historical price image into multiple historical price blocks and the estimated price image into multiple estimated price blocks, where each historical price block is located in the corresponding historical price block. Different positions of the price image, and each estimated price block is located in a different position of the estimated price image. Furthermore, the processor 81 can divide the image into N x N blocks of the same size according to the size of the acquired image and the length of the time interval covered by the image through parameter setting, and each block has Multiple pixels. In other words, when the time interval of the image is longer, the price information covered is more, so the image needs to be divided into more blocks before it can be effectively identified in the subsequent procedures; When the time interval is short, the price information covered is less, so it is only necessary to divide the image into fewer blocks for subsequent procedures. However, it should be noted that in response to different needs, the image can be divided into more blocks when the time interval of the image is short, or the image can be divided into fewer blocks when the time interval of the image is long. As in this embodiment, each image system is divided into 6 x 6 blocks.

It should be noted that if the price data includes more than two data types, the image obtained from the image capture module 83 can be processed by the processor 81 first, and only the data type that needs to be compared is selected as Price information, and then the processed map will be processed by the processor 81 The image is divided into blocks. For example, if the price data includes closing price, trading volume, KD value, and MACD value, the processor 81 may first perform image processing on the image to filter out unnecessary data types, and then divide the processed image into regions. Piece. In addition, in some embodiments, the processor 81 can also select each data type in the price data separately and divide it into blocks, that is, there can be multiple image processing corresponding to a single historical price image or a single estimated price image. Each price image includes multiple blocks corresponding to different locations.

Next, the processor 81 compares the estimated price blocks of the estimated price image and the price blocks of each historical price image to select a plurality of comparable price images from the historical price images, where The comparable price images correspond to multiple comparable price data. Specifically, at this time, the processor 81 performs the first-stage type recognition, compares the similarity between each historical price image and each corresponding block of the estimated price image, and judges the compared historical price image Whether the image is a comparable price image. For example, the processor 81 may calculate the ratio of the number of overlapping pixels to the number of non-overlapping pixels between the corresponding blocks in the historical price image and the estimated price image, and then according to the historical price image block and the received price ratio. Estimate the distance between the blocks of the price image and multiply it by the distance weight; in other words, the greater the difference between two valuable blocks, the greater the distance weight. In other embodiments, the processor 81 calculates the ratio of the number of overlapping pixels to the number of non-overlapping pixels between the corresponding blocks in the historical price image and the estimated price image, and then accumulates the ratio value. The total ratio value, and when the total ratio value exceeds the threshold value, it is judged that the compared historical price image is a comparable price image.

In one or more embodiments, the processor 81, as described above, determines that the compared historical price image is a preliminary screening price image when the total ratio exceeds the threshold value, and the processor 81 also calculates the received price images. Between the estimated price data and the price data corresponding to each preliminary screening price image The amount of error, and when the amount of error exceeds the threshold, it is judged that the compared preliminary screening price image is a comparable price image. Specifically, the error amount may be at least one of the error amount of the overlapping pixels of the price image, the error amount of the statistical value of the price data, and the error amount of the technical indicator, as described in the following paragraph.

When the price data is the closing price, the processor 81 can first convert the closing prices of the estimated price blocks and the price blocks of the preliminary screening price images into price images, and calculate the estimated price images. The amount of error in the degree of coincidence between all the estimated price blocks and each preliminary screened price image. Alternatively, the processor 81 may further calculate the amount of error of various statistical values (such as average, standard deviation, median, etc.) based on the estimated price data and the price data corresponding to each preliminary screening price image; on the other hand, When the price data is a technical indicator, the processor 81 may calculate the error amount of various technical indicators based on the estimated price data and the price data corresponding to each preliminary screening price image. In one or more embodiments, the blocks have different weights for the calculation of the amount of error; for example, blocks with newer data times have higher weights.

In one or more embodiments, after the foregoing error calculation procedure, the processor 81 may output the comparison table as shown in Table 2 through the output module 84.

Incidentally, the decision on the serial number of historical price data in Table 2 is sorted by the sum of the pixel coincidence error value of the price image, the error value of the statistical value of the price data, and the error value of the technical indicators. When the sum is smaller, it means The smaller the error, the higher the degree of similarity, and the smaller the serial number of the price data.

Then, the processor 81 performs the second-stage type identification, and classifies the comparable price data as rising according to the price data on the 0th day and the J day after each of the corresponding historical time intervals. Ethnic groups and descending ethnic groups, where J is greater than 0; for example, J can be 10 but is not limited to this. Then the processor 81 compares the estimated price data with the comparable price data to determine the classification result of the estimated price data, and the output module 84 outputs the classification result. Among them, the classification result corresponds to one of the rising group and the falling group. Specifically, when the output module 84 is a display screen, the classification result of the estimated price can be presented in text, image, video, or a combination of the above, but it should be understood that it is not limited to this; the output module 84 also It can be a printer to print out the classification result, or the output module 84 can also be a speaker to present the classification result of the estimated price in the form of sound or music.

In one or more embodiments of the present invention, the following two methods are used to classify comparable price data: statistical methods and algorithms.

In one or more embodiments of the present invention, a statistical method is used to classify the comparable price data in the second stage of type identification. In an implementation aspect, the processor 81 further determines whether each comparable price data is an increasing group or a decreasing group according to the ratio of the price data on the 0th day and the J day after the corresponding historical time period. For example, when the ratio is less than 1, it means that the comparable price data shows a decline on day J and should be classified as a descending group; when the ratio is greater than or equal to 1, the comparable price data is classified as an increasing group . In another implementation aspect, the processor 81 further obtains each comparable price data according to the ratio of the price data from day -J to day +J to day 0 after each comparable price data in the corresponding historical time period. The processor 81 determines the estimated price data based on the Euclidean distance between the -J day and the +J day after the average curve of the estimated price data and each comparable price data in the corresponding historical time period The classification results. In other words, in this implementation mode, each price data and each comparable price data in the estimated time period of the estimated price data are based on the -J day to +th day after the corresponding historical time period. J-day average curve is determined by the minimum straight line distance. For example, when the Euclidean distance is less than the threshold, the estimated price data is determined as the rising group; when the Euclidean distance is greater than or equal to the threshold, the estimated price data is determined For the descending ethnic group.

On the other hand, in another or more embodiments of the present invention, an algorithm is used to classify the comparable price data in the second stage of type identification. Specifically, in an implementation aspect, the processor 81 further based on the closing price of each comparable price data from day 0 to day J after the corresponding historical time period, at least one technical indicator, and at least one general economic indicator , Classify the images of comparable prices as rising or falling groups. Specifically, here, the processor 81 not only classifies each comparable price image according to the price data, but also uses the price data of the financial product itself, financial information corresponding to the regional market, and overall economic indicators (such as exchange rates). ) Etc. It can be classified in a multi-variable way to compare price images as rising or falling ethnic groups. Then, the processor 81 further inputs the aforementioned characteristic value into the clustering algorithm to compare the estimated price data with the comparable price data to determine the classification result of the estimated price data. Here, the clustering algorithm is KNN clustering algorithm (K-Nearest Neighbor Clustering Algorithm), but not limited to this; the clustering algorithm used here can also be Decision Trees algorithm, support vector machine (Support Vector Machine, SVM), Logistic Regression Classifier, Naïve Bayes Classifier, etc. In addition, in addition to directly inputting the aforementioned characteristic value into the clustering algorithm to determine the classification result of the estimated price data, it is also possible to compare the estimated price data with the comparable price data based on the aforementioned characteristic value by using mathematical statistics to determine the classification result. The classification result of the estimated price data.

It should be noted that the importance of different eigenvalues to the algorithm may also be different. Therefore, before inputting the feature values into the clustering algorithm, the Gradient tree boosting algorithm can be used to determine the importance of each feature value first, and then select several (for example, 10) features with higher importance. The value is input to the grouping algorithm to improve the prediction accuracy and save computing time. In addition to the aforementioned gradient tree lifting algorithm, decision tree algorithm, random sampling method, etc. can also be used to determine the importance ranking among the eigenvalues. In addition, eigenvalues with higher importance can be configured with higher weights to appropriately reflect the influence of the eigenvalues in the calculation results.

In one or more embodiments, the prediction system 80 may also have a feedback correction mechanism. Specifically, the processor 81 further determines the classification result of the estimated price data based on the price data of the estimated price data on the I day after the estimated time period, where I is less than J; in this example, I can be 5 But the same is not limited to this. In other embodiments, the processor 81 may also be Data, re-determine the importance ranking of eigenvalues used by the clustering algorithm. In still other embodiments, the processor 81 may also change the weight of a certain characteristic value according to the aforementioned price data. Through this feedback correction mechanism, the investment strategy can be appropriately modified according to the actual situation to enhance its practicality.

Referring to FIG. 2, FIG. 2 is a flow chart of the steps of the method for predicting the price trend of financial products according to the second embodiment of the present invention, which is suitable for predicting the price trend of financial products on the J day after the estimated time period. As shown in FIG. 2, one or more embodiments of the present invention further disclose a method for predicting the price trend of financial commodities, which includes the following steps: historical price data acquisition step S101, historical price image acquisition step S102, and estimated price image acquisition In step S103, the first-stage pattern recognition step S104, the second-stage pattern recognition step S105, and the trend determination step S106, each step is described as follows.

The historical price data obtaining step includes obtaining multiple historical price data of the financial product, as shown in step S101; wherein the historical price data respectively correspond to the price data of the financial product in multiple historical time segments.

The historical price image obtaining step includes obtaining multiple historical price images according to the historical price data, as shown in step S102; wherein each historical price image includes multiple historical price blocks, and each historical price block is located in a corresponding Different positions of historical price images.

The step of obtaining the estimated price image includes obtaining the estimated price image based on the estimated price data of the financial product, as shown in step S103; wherein the estimated price data corresponds to the price data of the estimated time period, and the estimated price image It includes multiple estimated price blocks, and each estimated price block is located in a different position of the estimated price image.

The first-stage type recognition step includes comparing the estimated price blocks of the estimated price image and the historical price blocks of each historical price image from the historical price maps. For example, selecting a plurality of comparable price images is as shown in step S104; wherein the comparable price images correspond to a plurality of comparable price data.

The second-stage pattern identification step includes classifying the comparable price data into the rising group and the falling group based on the price data on the 0th day and the J day after the corresponding historical period of time for each comparable price data, as in step Shown in S105; where J is greater than 0.

The trend determination step includes comparing the estimated price data with the comparable price data to determine whether the estimated price data is an increasing group or a decreasing group, as shown in step S106.

Please refer to FIG. 3, which is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the third embodiment of the present invention. As shown in FIG. 3, according to one or more embodiments of the present invention, in the second-stage pattern recognition step S105, the step S1051 is further included: according to each comparable price data, the 0th day after the corresponding historical time period and The ratio of the price data on the J day classifies the comparable price data as rising or falling groups.

Please refer to FIG. 4, which is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the fourth embodiment of the present invention. As shown in FIG. 4, according to one or more embodiments of the present invention, in the second-stage pattern recognition step S105, the step S1052 is further included: according to each comparable price data, after the corresponding historical period of time -J The ratio of the price data from day to day +J to day 0 obtains the average curve of each comparable price data. And, corresponding to the trend determination step S106, it further includes step S1061: According to the average curve of the estimated price data and the comparable price data, the Euclidean date from day -J to day +J after the corresponding historical time period The distance determines whether the estimated price data is the rising group or the falling group.

Please refer to FIG. 5, which is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the fifth embodiment of the present invention. As shown in Fig. 5, according to one or more embodiments of the present invention, In the second-stage pattern recognition step S105, the step S1053 is further included: a closing price, at least one technical indicator, and at least one overall price from the 0th day to the Jth day after the corresponding historical time period according to each comparable price data Economic indicators, which classify each comparable price image as rising or falling.

Furthermore, please refer to FIG. 6, which is a flowchart of detailed steps of the method for predicting the price trend of financial commodities according to the sixth embodiment of the present invention. As shown in FIG. 6, according to one or more embodiments of the present invention, in the trend determination step S106, the step S1062 is further included: using the closing price, the at least one technical indicator, and the at least one overall economic indicator as multiple characteristic values , And use the characteristic values to input the clustering algorithm to compare the estimated price data with the comparable price data to determine whether the estimated price data is an up or down group.

The aforementioned prediction method may further include a feedback correction step. Fig. 7 is a flow chart of the steps of the method for predicting the price trend of financial commodities according to the seventh embodiment of the present invention. As shown in FIG. 7, in one or more embodiments of the present invention, the feedback correction step S107 includes re-determining the estimated price data as the rising group based on the price data of the estimated price data on the first day after the estimated time period. Or descending group, where I is less than J. Fig. 8 is a flow chart of the steps of the method for predicting the price trend of financial commodities according to the eighth embodiment of the present invention. As shown in FIG. 8, in another or more embodiments of the present invention, the feedback correction step S108 includes re-determining the importance of the characteristic values according to the price data of the estimated price data on the first day after the estimated time period. Sexual sorting.

In summary, according to the system and method for predicting the price trend of financial products according to one or more embodiments of the present invention, similar data can be screened by two-stage type identification, and it is possible to more objectively judge whether a financial product is in the future. The possible price trends and trends at a time point are conducive to the user's formulation of investment strategies. In addition, through its feedback correction mechanism, it can also be based on actual conditions. The investment strategy should be appropriately revised to improve the practicability of the system.

80: prediction system

81: processor

82: storage module

83: Image capture module

84: output module

Claims (8)

A system for predicting the price trend of financial products, which is suitable for predicting the price trend of a financial product on the Jth day after an estimated time period. The prediction system includes: a processor, a storage module, and an output module. The processor signal is connected between the storage module and the output module, wherein: the processor obtains a plurality of historical price images of the financial commodity and an estimated price image from the storage module, the historical prices The images correspond to the price data of the financial commodity in multiple historical time periods, and the estimated price image corresponds to the price data in the estimated time period; the processor divides each historical price image into multiple historical periods Price block and dividing the estimated price image into multiple estimated price blocks, and each historical price block is located at a different position of the corresponding historical price image, and each estimated price block is located in the Different positions of the estimated price image; the processor compares the estimated price blocks of the estimated price image and the historical price blocks of each historical price image and selects from the historical price images A plurality of comparable price images, and the analogous price images correspond to a plurality of comparable price data; the processor according to each of the comparable price data is on the 0th day and the Jth day after the corresponding historical time period Price data, classify the comparable price data into a rising group and a falling group, where J is greater than 0; the processor compares an estimated price data corresponding to the estimated price image with the comparable prices The data determines a classification result of the estimated price data, and the classification result corresponds to one of the rising group and the falling group; the output module outputs the classification result; The processor further obtains an average curve of each comparable price data according to the ratio of the price data from the -J day to the +J day to the 0th day after each of the comparable price data in the corresponding historical time period. , And the processor further determines the estimated price based on the Euclidean distance between the average curve of the estimated price data and each of the comparable price data from the -J day to the +J day after the corresponding historical time period The classification result of the price data. A system for predicting the price trend of financial products, which is suitable for predicting the price trend of a financial product on the Jth day after an estimated time period. The prediction system includes: a processor, a storage module, and an output module. The processor signal is connected between the storage module and the output module, wherein: the processor obtains a plurality of historical price images of the financial commodity and an estimated price image from the storage module, the historical prices The images correspond to the price data of the financial commodity in multiple historical time periods, and the estimated price image corresponds to the price data in the estimated time period; the processor divides each historical price image into multiple historical periods Price block and dividing the estimated price image into multiple estimated price blocks, and each historical price block is located at a different position of the corresponding historical price image, and each estimated price block is located in the Different positions of the estimated price image; the processor compares the estimated price blocks of the estimated price image and the historical price blocks of each historical price image and selects from the historical price images A plurality of comparable price images, and the analogous price images correspond to a plurality of comparable price data; the processor according to each of the comparable price data is on the 0th day and the Jth day after the corresponding historical time period Price data, classify these comparable price data into an increasing group and a decreasing group, where J is greater than 0; The processor compares an estimated price data corresponding to the estimated price image with the comparable price data to determine a classification result of the estimated price data. The classification result corresponds to the rising group and the falling group. One of them; the output module outputs the classification result; wherein the processor is further based on a closing price and at least one technical indicator from day 0 to day J after each of the comparable price data in the corresponding historical time period And at least one general economic indicator, classifying each of the comparable price images as the rising group or the falling group; the processor further uses the closing price, the at least one technical indicator, and the at least one general economic indicator as multiple Characteristic values, and input a clustering algorithm with the characteristic values to compare the estimated price data with the comparable price data to determine the classification result of the estimated price data; the processor further determines the classification result of the estimated price data based on the estimated price data Based on the price data on the first day after the estimated time period, an importance ranking of the characteristic values is determined again, where I is less than J. The system for predicting the price trend of financial products according to claim 1 or 2, wherein the processor is further based on the ratio of the price data on the 0th day and the J day after each of the comparable price data in the corresponding historical time period Decide whether each comparable price data is the rising group or the falling group. The system for predicting the price trend of financial products according to claim 1 or 2, wherein the processor further determines the estimated price data based on the price data of the estimated price data on the first day after the estimated time period The classification result of, where I is less than J. A method for predicting the price trend of financial products, which is suitable for predicting the price trend of a financial product on the J-th day after an estimated time period. The prediction method includes: Historical price image acquisition step: Obtain multiple historical price images of the financial product, where the historical price images correspond to the price data of the financial product in multiple historical time periods, and each historical price image includes multiple historical price images. Each historical price block is located in a different position of the corresponding historical price image; the step of obtaining the estimated price image: obtain an estimated price image of the financial commodity, wherein the estimated price image The image corresponds to the price data of the estimated time period, the estimated price image includes multiple estimated price blocks, each of the estimated price blocks is located in a different position of the estimated price image; the first stage type Identification step: compare the estimated price blocks of the estimated price image and the historical price blocks of each historical price image, and select multiple comparable price images from the historical price images, The analogous price images correspond to multiple comparable price data; the second-stage pattern recognition step: According to the corresponding price data on the 0th day and the J day after the corresponding historical time period , Classify the comparable price data into a rising group and a falling group, where J is greater than 0; and the trend determination step: compare an estimated price data corresponding to the estimated price image with the comparable prices Data to determine whether the estimated price data is the rising group or the falling group; wherein, in the second-stage type identification step, it further includes: according to each of the comparable price data, the first-after the corresponding historical time period The ratio of the price data from day J to day +J to day 0 obtains an average curve of each comparable price data; the trend determination step further includes: according to the estimated price data and each of the comparable price data The average curve of the price data corresponds to the Euclidean distance from the -J day to the +J day after the historical time period, and determines whether the estimated price data is the rising group or the falling group. A method for predicting the price trend of financial products, which is suitable for predicting the price trend of a financial product on the J-th day after an estimated time period. The prediction method includes: historical price image acquisition step: obtaining multiple histories of the financial product Price images, where the historical price images correspond to the price data of financial commodities in multiple historical time segments, each historical price image includes multiple historical price blocks, and each historical price block is located in a corresponding Different positions of the historical price image; the step of obtaining the estimated price image: obtain an estimated price image of the financial commodity, where the estimated price image corresponds to the price data of the estimated time period, and the estimated price image The price image includes a plurality of estimated price blocks, each of which is located at a different position of the estimated price image; the first-stage type identification step: compare the estimated price images Evaluate price blocks and the historical price blocks of each historical price image, and select multiple comparable price images from the historical price images, where the comparable price images correspond to multiple comparable price data ; The second stage pattern identification step: According to the price data of each of the comparable price data on the 0th day and the J day after the corresponding historical time period, the comparable price data are classified into an increasing group and a Declining group, where J is greater than 0; and the trend determination step: comparing an estimated price data corresponding to the estimated price image with the comparable price data to determine whether the estimated price data is the rising group or the falling group Ethnic groups; wherein in the second-stage pattern identification step, it further includes: a closing price from day 0 to day J after each of the comparable price data in the corresponding historical time period, at least one technical indicator, and At least one general economic indicator, classifying each comparable price image into the rising group or the falling group; The step of determining the trend further includes: using the closing price, the at least one technical indicator, and the at least one overall economic indicator as a plurality of characteristic values, and inputting the characteristic values into a clustering algorithm to compare the receiving The estimated price data and the comparable price data determine whether the estimated price data is the rising group or the falling group; the prediction method further includes the price based on the estimated price data on the first day after the estimated time period Data, re-determine an importance ranking of the feature values, where I is less than J. The method for predicting the price trend of financial products according to claim 5 or 6, wherein in the second-stage type identification step, it further includes: according to each of the comparable price data, the value is 0th after the corresponding historical time period. The ratio of the price data on day J to the J day classifies each comparable price data as the rising group or the falling group. The method for predicting the price trend of financial products as described in claim 5 or 6, further includes: a feedback correction step: based on the price data of the valued price data on the first day after the valued time period, re-determine the valued price The price information is the rising group or the falling group, where I is less than J.

Images