CN113793217A - Stock exchange inversion point and abnormal point detection method based on convolutional neural network - Google Patents
Stock exchange inversion point and abnormal point detection method based on convolutional neural network Download PDFInfo
- Publication number
- CN113793217A CN113793217A CN202111064715.XA CN202111064715A CN113793217A CN 113793217 A CN113793217 A CN 113793217A CN 202111064715 A CN202111064715 A CN 202111064715A CN 113793217 A CN113793217 A CN 113793217A
- Authority
- CN
- China
- Prior art keywords
- stock
- points
- layer
- neural network
- convolutional neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims abstract description 9
- 230000000694 effects Effects 0.000 claims abstract description 4
- 238000007689 inspection Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 20
- 230000005284 excitation Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000010365 information processing Effects 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a stock trading reversal point and abnormal point detection method based on a convolutional neural network, and relates to the technical field of stock information processing. The invention comprises the following steps: acquiring historical data of stocks, and marking inversion points and abnormal points on a K line graph; dividing the stock into subsequences by adopting a sliding window, inputting the subsequences into a convolutional neural network for feature learning, and classifying the learned features; repeatedly training the model by adopting a forward propagation algorithm and a backward propagation algorithm; the trained model carries out effect inspection on the test data; stock data is obtained and input into a trained model, and stock inversion points and abnormal points are obtained and counted. The invention inputs the historical data of the stocks into the convolutional neural network for feature learning, classifies the features, adopts a forward propagation algorithm and a backward propagation algorithm to train a model repeatedly, counts abnormal points and reversal points of the stocks, improves the accuracy rate of the stocks analysis of investors and brings economic benefits to the investors.
Description
Technical Field
The invention belongs to the technical field of stock information processing, and particularly relates to a stock trading inversion point and abnormal point detection method based on a convolutional neural network.
Background
Frequent fluctuations and anomalies in stock trading present a situation that exposes investors to risk and trial when choosing stock trading. Since investors want to predict the reversal point of stocks during stock trading to maximize profit by using the valley value of the stock price at the lowest price and the peak value of the stock price at the highest price, it is important to detect abnormal fluctuation points and such reversal points in the stock market.
Disclosure of Invention
The invention aims to provide a stock trading reversal point and abnormal point detection method based on a convolutional neural network, which is characterized in that historical data of stocks are input into the convolutional neural network for feature learning, features are classified, a forward propagation algorithm and a backward propagation algorithm are adopted to train a model repeatedly, abnormal points and reversal points of the stocks are counted, and the problems that the existing investors are inaccurate in stock analysis and easy to cause economic loss are solved.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a stock exchange reversal point and abnormal point detection method based on a convolutional neural network, which comprises the following steps:
step S1: acquiring historical data of stocks, and manually marking inversion points and abnormal points of all stocks according to a K-line graph;
step S2: dividing the stock into subsequences by adopting a sliding window;
step S3: directly inputting the subsequence into a convolutional neural network for feature learning;
step S4: the convolutional neural network inputs the learned characteristics to a fully-connected multilayer perceptron, and the multilayer perceptron classifies the learned characteristics;
step S5: repeatedly training the model by adopting a forward propagation algorithm and a backward propagation algorithm until the parameters are converged;
step S6: performing effect inspection on the test data according to the trained model, and calculating the accuracy;
step S7: and (3) acquiring stock data, inputting the stock data into a trained model, performing wavelet clustering on the learned characteristics, and combining a Markov chain model to obtain stock inversion points and abnormal points and performing statistics.
As a preferable technical solution, in the step S1, stock data is acquired from the internet, and all the inversion points and the abnormal points are manually marked on the K-line graph; the marking method adopts a reversal point judgment method in economics; the inversion points include an upward inversion point, a downward inversion point, and a non-inversion point.
As a preferred technical solution, the method for identifying the stock inversion point is as follows:
time sequence of stock at T1,T2,T3The closing prices corresponding to the time are S1,S2,S3When the formula is satisfied:
(S2-S1)/S2>r and (S)2-S3)/S2>r；
Indicate at time T2The stock price is reversed, and the reversal at the moment is a reversal point with the stock price facing downwards;
when the formula is satisfied:
(S1-S2)/S2>r and (S)3-S2)/S2>r；
Indicate at time T2The stock price is reversed and the reversal at that time is the reversal point for stock price upwards.
As a preferred technical solution, in step S2, the stock information marked with the inversion point is divided into different stock segments by using a division technique, and meanwhile, the classification label of the stock is divided into sub-segments, and the class label of the sub-sequence of each sub-sequence is redefined according to the value of the sub-sequence; the time series of the stocks is divided by a sliding window.
As a preferable technical solution, in the step S4, the convolutional neural network sequentially includes a plurality of volume base layers, an excitation layer, a pooling layer, and a regularization layer;
the expression formula of the volume base layer is as follows:
where f is the excitation function, bijM represents, as a bias term, the number of points in the (i-1) layer that are connected to the layer,
a parameter value representing a p-th convolution kernel of the layer;
the excitation function f adopts a ReLU function, and the ReLU function is as follows:
f(x)＝max(0,x)；
the mathematical expression of the pooling layer is as follows:
in the formula, QiIndicating the size of the pooling area;
the regularization layer is used for carrying out normalization processing on the data output by the previous layer, and the formula of the normalization processing is as follows:
in the formula, k, α, β represent hyper-parameters, and g (j) is a filter to be normalized.
As a preferred technical solution, in step S5, the calculation formula of the forward propagation algorithm is as follows:
in the formula (I), the compound is shown in the specification,
representing the kth dimension of the label corresponding to the nth sample,
indicating correspondence of nth sampleThe kth of the outputs;
the calculation formula of the back propagation algorithm is as follows:
in the formula, xl-1Represents the output of the previous layer, δlThe sensitivity of the l layer is shown.
As a preferable technical solution, in the step S7, the inversion point and the anomaly point of the stock are input into the convolutional neural network, and are processed sequentially through a plurality of volume base layers, an excitation layer, a pooling layer and a regularization layer; after the abnormal points of the stock are output in a planning layer, wavelet clustering processing is required to be carried out; the processing flow of the wavelet clustering is as follows:
step S71: quantizing the feature space, and mapping the data to a new quantized feature space;
step S72: performing wavelet transformation on the quantization result to form a new cluster;
step S73: forming a unique cluster label for each cluster and forming a lookup table;
step S74: after clustering, the data set is subjected to a reduction process.
The invention has the following beneficial effects:
the invention inputs the historical data of the stocks into the convolutional neural network for feature learning, classifies the features, adopts a forward propagation algorithm and a backward propagation algorithm to train a model repeatedly, counts abnormal points and reversal points of the stocks, improves the accuracy rate of the stocks analysis of investors and brings economic benefits to the investors.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a diagram illustrating the steps of a stock exchange reversal point and abnormal point detection method based on a convolutional neural network according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a stock exchange inversion point and abnormal point detection method based on convolutional neural network, including the following steps:
step S1: acquiring historical data of stocks, and manually marking inversion points and abnormal points of all stocks according to a K-line graph;
in step S1, stock data is acquired from the internet in many ways, and all inversion points and abnormal points are manually marked on the K-line graph; the marking method adopts a reversal point judgment method in economics; the inversion points include an upward inversion point, a downward inversion point, and a non-inversion point.
Step S2: dividing the stock into subsequences by adopting a sliding window;
step S3: directly inputting the subsequence into a convolutional neural network for feature learning;
step S4: the convolutional neural network inputs the learned characteristics to a fully-connected multilayer perceptron, and the multilayer perceptron classifies the learned characteristics;
step S5: repeatedly training the model by adopting a forward propagation algorithm and a backward propagation algorithm until the parameters are converged;
step S6: performing effect inspection on the test data according to the trained model, and calculating the accuracy;
step S7: and (3) acquiring stock data, inputting the stock data into a trained model, performing wavelet clustering on the learned characteristics, and combining a Markov chain model to obtain stock inversion points and abnormal points and performing statistics.
Stock reversal points, namely a stock price peak value and a stock price valley value, or a stock price maximum value and a stock price minimum value; acquiring stock time sequence data information, collecting abnormal fluctuation announcement information of stocks, and marking stock inversion points, namely a stock price peak point and a stock price valley point; the identification method of the stock reversal point is as follows:
time sequence of stock at T1,T2,T3The closing prices corresponding to the time are S1,S2,S3When the formula is satisfied:
(S2-S1)/S2>r and (S)2-S3)/S2>r；
Indicate at time T2The stock price is reversed, and the reversal at the moment is a reversal point with the stock price facing downwards;
when the formula is satisfied:
(S1-S2)/S2>r and (S)3-S2)/S2>r；
Indicate at time T2The stock price is reversed and the reversal at that time is the reversal point for stock price upwards.
In step S2, the stock information marked by the inversion point is divided into different stock segments by using a division technique, and meanwhile, the classification label of the stock is divided into sub-segments, and the class label of the sub-sequence of the segment is redefined according to the value of each sub-sequence; the time series of the stocks is divided by a sliding window.
The input of the model is a matrix, and assuming that D dimensions exist, namely D attribute values exist at each moment, the input is the matrix of D length (input), the matrix is divided into small segments by using a sliding window, the size of the sliding window is set as W, and the step length is S; after the input matrix passes through each layer of the convolutional neural network, the result is stillOne matrix but reduced in dimension. The matrix of the jth feature selector of the ith layer is therefore denoted vijThe x-th row and d-th column of the matrix are marked
The operation method comprises the following steps:
in step S4, the convolutional neural network sequentially includes a plurality of volume base layers, an excitation layer, a pooling layer, and a regularization layer;
the expression formula for the volume base layer is as follows:
where f is the excitation function, bijM represents, as a bias term, the number of points in the (i-1) layer that are connected to the layer,
a parameter value representing a p-th convolution kernel of the layer;
the excitation function f adopts a ReLU function which is as follows:
f(x)＝max(0,x)；
the mathematical expression for the pooling layer is as follows:
in the formula, QiIndicating the size of the pooling area;
and the regularization layer is used for carrying out normalization processing on the data output by the previous layer, and the formula of the normalization processing is as follows:
in the formula, k, α, β represent hyper-parameters, and g (j) is a filter to be normalized.
In step S5, the calculation formula of the forward propagation algorithm is as follows:
in the formula (I), the compound is shown in the specification,
representing the kth dimension of the label corresponding to the nth sample,
a kth output representing an output corresponding to the nth sample;
the calculation formula of the back propagation algorithm is as follows:
in the formula, xl-1Represents the output of the previous layer, δlThe sensitivity of the l layer is shown.
In step S7, the inversion point and the anomaly point of the stock are input into a convolutional neural network and are processed by a plurality of volume base layers, excitation layers, pooling layers and regularization layers in sequence; after the abnormal points of the stock are output in the planning layer, wavelet clustering processing is required to be carried out; the processing flow of wavelet clustering is as follows:
step S71: quantizing the feature space, and mapping the data to a new quantized feature space;
step S72: performing wavelet transformation on the quantization result to form a new cluster;
step S73: forming a unique cluster label for each cluster and forming a lookup table;
step S74: after clustering, the data set is subjected to a reduction process.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it can be understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above can be implemented by instructing the relevant hardware through a program, and the corresponding program can be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, or the like.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (7)
1. A stock exchange reversal point and abnormal point detection method based on a convolutional neural network is characterized by comprising the following steps:
step S1: acquiring historical data of stocks, and manually marking inversion points and abnormal points of all stocks according to a K-line graph;
step S2: dividing the stock into subsequences by adopting a sliding window;
step S3: directly inputting the subsequence into a convolutional neural network for feature learning;
step S4: the convolutional neural network inputs the learned characteristics to a fully-connected multilayer perceptron, and the multilayer perceptron classifies the learned characteristics;
step S5: repeatedly training the model by adopting a forward propagation algorithm and a backward propagation algorithm until the parameters are converged;
step S6: performing effect inspection on the test data according to the trained model, and calculating the accuracy;
step S7: and (3) acquiring stock data, inputting the stock data into a trained model, performing wavelet clustering on the learned characteristics, and combining a Markov chain model to obtain stock inversion points and abnormal points and performing statistics.
2. The method for detecting stock exchange inversion points and abnormal points based on the convolutional neural network as claimed in claim 1, wherein in step S1, stock data is obtained from the internet, and all inversion points and abnormal points are manually marked on the K-line graph; the marking method adopts a reversal point judgment method in economics; the inversion points include an upward inversion point, a downward inversion point, and a non-inversion point.
3. The method for detecting stock exchange reversal points and abnormal points based on the convolutional neural network as claimed in claim 2, wherein the identification method of the stock reversal points is as follows:
time sequence of stock at T1,T2,T3The closing prices corresponding to the time are S1,S2,S3When the formula is satisfied:
(S2-S1)/S2>r and (S)2-S3)/S2>r；
Indicate at time T2The stock price is reversed, and the reversal at the moment is a reversal point with the stock price facing downwards;
when the formula is satisfied:
(S1-S2)/S2>r and (S)3-S2)/S2>r；
Indicate at time T2The stock price is reversed and the reversal at that time is the reversal point for stock price upwards.
4. The method as claimed in claim 1, wherein in step S2, the stock information marked with the inversion points is divided into different stock segments by using a division technique, and the classification labels of the stocks are divided into sub-segments, and the class labels of the sub-sequences of the segments are redefined according to the value of each sub-sequence; the time series of the stocks is divided by a sliding window.
5. The method for detecting stock exchange reversal points and abnormal points based on the convolutional neural network as claimed in claim 1, wherein in step S4, the convolutional neural network comprises a plurality of volume base layers, an excitation layer, a pooling layer and a regularization layer in sequence;
the expression formula of the volume base layer is as follows:
where f is the excitation function, bijM represents, as a bias term, the number of points in the (i-1) layer that are connected to the layer,
a parameter value representing a p-th convolution kernel of the layer;
the excitation function f adopts a ReLU function, and the ReLU function is as follows:
f(x)＝max(0,x)；
the mathematical expression of the pooling layer is as follows:
in the formula, QiIndicating the size of the pooling area;
the regularization layer is used for carrying out normalization processing on the data output by the previous layer, and the formula of the normalization processing is as follows:
in the formula, k, α, β represent hyper-parameters, and g (j) is a filter to be normalized.
6. The method for detecting inversion points and abnormal points of stock exchange based on convolutional neural network as claimed in claim 1, wherein in step S5, the calculation formula of the forward propagation algorithm is as follows:
in the formula (I), the compound is shown in the specification,
representing the kth dimension of the label corresponding to the nth sample,
a kth output representing an output corresponding to the nth sample;
the calculation formula of the back propagation algorithm is as follows:
in the formula, xl-1Represents the output of the previous layer, δlThe sensitivity of the l layer is shown.
7. The method as claimed in claim 2, wherein in step S7, the stock trade inversion point and the anomaly point are input into the convolutional neural network, and sequentially processed through a plurality of volume base layers, an excitation layer, a pooling layer and a regularization layer; after the abnormal points of the stock are output in a planning layer, wavelet clustering processing is required to be carried out;
the processing flow of the wavelet clustering is as follows:
step S71: quantizing the feature space, and mapping the data to a new quantized feature space;
step S72: performing wavelet transformation on the quantization result to form a new cluster;
step S73: forming a unique cluster label for each cluster and forming a lookup table;
step S74: after clustering, the data set is subjected to a reduction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111064715.XA CN113793217A (en) | 2021-09-10 | 2021-09-10 | Stock exchange inversion point and abnormal point detection method based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111064715.XA CN113793217A (en) | 2021-09-10 | 2021-09-10 | Stock exchange inversion point and abnormal point detection method based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113793217A true CN113793217A (en) | 2021-12-14 |
Family
ID=78880105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111064715.XA Pending CN113793217A (en) | 2021-09-10 | 2021-09-10 | Stock exchange inversion point and abnormal point detection method based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793217A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114581242A (en) * | 2022-05-05 | 2022-06-03 | 北京中捷互联信息技术有限公司 | Financial data processing system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200945236A (en) * | 2008-04-30 | 2009-11-01 | Univ Nat Taiwan Science Tech | A method of predicting a financial market |
| CN102034211A (en) * | 2011-01-13 | 2011-04-27 | 上海万臣信息科技发展有限公司 | Statistical method for displaying inversion point of stock data by combining computer platform with Hurst model |
| CN103714486A (en) * | 2013-12-31 | 2014-04-09 | 刘建松 | Financial market bargaining transaction display system and method |
| CN106845681A (en) * | 2016-12-21 | 2017-06-13 | 广东工业大学 | A kind of stock trend forecasting method of application depth learning technology |
| CN107316054A (en) * | 2017-05-26 | 2017-11-03 | 昆山遥矽微电子科技有限公司 | Non-standard character recognition methods based on convolutional neural networks and SVMs |
| CN108694476A (en) * | 2018-06-29 | 2018-10-23 | 山东财经大学 | A kind of convolutional neural networks Stock Price Fluctuation prediction technique of combination financial and economic news |
| CN109190834A (en) * | 2018-09-12 | 2019-01-11 | 百色学院 | Stock price trend prediction method and system neural network based |
| CN111222992A (en) * | 2020-01-17 | 2020-06-02 | 大连大学 | Stock price prediction method of long-short term memory neural network based on attention mechanism |
-
2021
- 2021-09-10 CN CN202111064715.XA patent/CN113793217A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200945236A (en) * | 2008-04-30 | 2009-11-01 | Univ Nat Taiwan Science Tech | A method of predicting a financial market |
| CN102034211A (en) * | 2011-01-13 | 2011-04-27 | 上海万臣信息科技发展有限公司 | Statistical method for displaying inversion point of stock data by combining computer platform with Hurst model |
| CN103714486A (en) * | 2013-12-31 | 2014-04-09 | 刘建松 | Financial market bargaining transaction display system and method |
| CN106845681A (en) * | 2016-12-21 | 2017-06-13 | 广东工业大学 | A kind of stock trend forecasting method of application depth learning technology |
| CN107316054A (en) * | 2017-05-26 | 2017-11-03 | 昆山遥矽微电子科技有限公司 | Non-standard character recognition methods based on convolutional neural networks and SVMs |
| CN108694476A (en) * | 2018-06-29 | 2018-10-23 | 山东财经大学 | A kind of convolutional neural networks Stock Price Fluctuation prediction technique of combination financial and economic news |
| CN109190834A (en) * | 2018-09-12 | 2019-01-11 | 百色学院 | Stock price trend prediction method and system neural network based |
| CN111222992A (en) * | 2020-01-17 | 2020-06-02 | 大连大学 | Stock price prediction method of long-short term memory neural network based on attention mechanism |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114581242A (en) * | 2022-05-05 | 2022-06-03 | 北京中捷互联信息技术有限公司 | Financial data processing system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399158B (en) | Attribute emotion classification method based on dependency tree and attention mechanism | |
| CN107292330B (en) | Iterative label noise identification algorithm based on double information of supervised learning and semi-supervised learning | |
| Zhao et al. | Sales forecast in e-commerce using convolutional neural network | |
| CN114970605A (en) | Multi-mode feature fusion neural network refrigeration equipment fault diagnosis method | |
| CN112687374B (en) | Psychological crisis early warning method based on text and image information joint calculation | |
| CN113095927B (en) | Method and equipment for identifying suspected transactions of backwashing money | |
| CN111859010B (en) | Semi-supervised audio event identification method based on depth mutual information maximization | |
| CN111597340A (en) | Text classification method and device and readable storage medium | |
| Li et al. | Multi-factor based stock price prediction using hybrid neural networks with attention mechanism | |
| CN112785441B (en) | Data processing method, device, terminal equipment and storage medium | |
| CN112560948B (en) | Fundus image classification method and imaging method under data deviation | |
| CN112307760A (en) | Deep learning-based financial report emotion analysis method and device and terminal | |
| CN111445339A (en) | Price limiting single prediction analysis method and system for bilinear attention convolution neural network | |
| CN113793217A (en) | Stock exchange inversion point and abnormal point detection method based on convolutional neural network | |
| CN113177578A (en) | Agricultural product quality classification method based on LSTM | |
| CN111445341A (en) | Futures model training and transaction implementation method based on multi-scale self-attention | |
| CN114778485B (en) | Variety identification method and system based on near infrared spectrum and attention mechanism network | |
| CN114764575B (en) | Multi-modal data classification method based on deep learning and time sequence attention mechanism | |
| CN114722918A (en) | Tumor classification method based on DNA methylation | |
| CN111160419A (en) | Electronic transformer data classification prediction method and device based on deep learning | |
| Lv | Classification of Grapevine Leaf Images with Deep Learning Ensemble Models | |
| Apel et al. | VEMUT-Sub-Sampling: A Novel Method for Sparse Multivariate Time-Series Vehicle Data | |
| CN116303088A (en) | Test case ordering method based on deep neural network cross entropy loss | |
| Mohite et al. | Deep Learning-Based Fruit Recognition and Quality Assessment: A Convolutional Neural Network Approach | |
| CN118098288A (en) | Weak supervision voice depression detection method based on self-learning label correction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |