CN106447135A - Stock short-term prediction method based on most similar tendency - Google Patents
Stock short-term prediction method based on most similar tendency Download PDFInfo
- Publication number
- CN106447135A CN106447135A CN201610969059.0A CN201610969059A CN106447135A CN 106447135 A CN106447135 A CN 106447135A CN 201610969059 A CN201610969059 A CN 201610969059A CN 106447135 A CN106447135 A CN 106447135A
- Authority
- CN
- China
- Prior art keywords
- stock
- tendency
- price
- amount
- day
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a stock short-term prediction method based on the most similar tendency. The method can predict the tendency of the stock short-term 2-week-longer trading days. The predicted result comprises the closing price and price limit of each day and further comprises the opening price, the top price, the lower price, the turnover and the like of each day. According to the main idea of the method, firstly, each stock is subjected to relative quantity calculation, and relative quantities comprise the transverse relative quantity and the longitudinal relative quantity; historical data of all the stocks is matched segment by segment through the price limit tendency within a recent time period of the stocks to be predicted, and former stocks with highest similarity are obtained through search; finally, the later tendency of the stocks to be predicted is calculated and reduced into the short-term prediction result in combination with the transverse relative quantity and the longitudinal relative quantity through tendency data of after the most similar stock matching date. The method can provide decision-making support for stock short-term operation.
Description
Technical field
The present invention relates to stock certificate data digging technology field, especially relate to a kind of stock short-term based on most like tendency
Forecasting Methodology.
Background technology
Equity investment has become as the important component part in people's life, effectively carries out Prediction of Stock Price, maximum
Degree evades Stock Risk, increases investment return, is the hot issue of stock investor's concern.Therefore Stock Market Forecasting method
Research has extremely important using value and theory significance.
Conventional stock method for digging has:Time series analysis method, neural net prediction method, regression analysis, time
Sequence exponential smoothing, trend curve modelling, Random time sequence Forecasting Methodology, Markov Pre-measurement and discriminant analysis predicted method
Deng.Because in stock market, enchancement factor is a lot, the impact to stock index, price is notable, and price fluctuation is violent, dry sound pitch, performance
Go out very strong non-linear, uncertain.Although have important directive function in real work in these processes, but still deposit
In some places not fully up to expectations, as poor in regression model extrapolation, analogy Y-factor method Y accuracy is poor, neural computing
Amount is big, the problems such as be also easy to produce over-fitting.
Content of the invention
The present invention is open to propose a kind of New Approach of Short-term Stock Prediction based on most like tendency.Here short-term forecast one
As refer to the prediction of following to stock more than the 2 weeks days of trade, prediction in such as 20 days, prediction on the 30th, prediction on the 60th etc..Side of the present invention
The prediction being not only to following a period of time closing price, amount of increase and amount of decrease that predicts the outcome of method, also include daily opening price, highest price,
The prediction of the aspects such as lowest price, exchange hand.
The main thought of the inventive method is：First every stock is carried out with the calculating of relative quantity, including laterally opposed amount
With longitudinally opposed amount；Then the history number to all stocks with the amount of increase and amount of decrease tendency in the recent certain time of stock to be predicted
According to carrying out piecewise coupling, search obtains former stocks of similarity highest；After the last coupling date with most like stock
Tendency data, in conjunction with transverse and longitudinal relative quantity, calculate the later stage tendency reducing stock to be predicted as its short-term forecast result.This
Inventive method is a kind of big data method for digging based on all stock certificate datas, and method can provide decision-making to prop up for stock short operation
Hold.
The step of the inventive method is as follows：
(1) calculating of laterally opposed amount is carried out to each day of trade of every stock；
(2) calculating of longitudinally opposed amount is carried out to each day of trade relatively previous day of trade of every stock；
(3) the recent tendency fragment of stock to be predicted is moved weighted registration with the historical data of every stock one by one, obtain
Take the corresponding matching section of front T stock the most similar and coupling date；
(4) based on the tendency data after most like stock matching section mates the date, in conjunction with horizontal, longitudinally opposed amount, calculate
Reduce the later stage tendency of stock to be predicted.
Wherein, in step (1), the calculating of laterally opposed amount was carried out for each day of trade of every stock, calculating be
With respect to the increase and decrease amplitude of same day closing price, the relative quantity generally requiring calculating includes：Opening price increase and decrease amplitude, highest price increase and decrease
Amplitude, lowest price increase and decrease amplitude.
Wherein, in step (2), the calculating of longitudinally opposed amount is also to carry out each day of trade to every stock, different
Be relative quantity be to be calculated with respect to the previous day of trade.Calculative field includes exchange hand, turnover rate, conclusion of the business stroke count
Deng.
Wherein, in step (3), the recent tendency fragment of stock to be predicted refers to the amount of increase and amount of decrease data of recent a period of time, will
This segment data tendency fragment isometric with all stock historical datas moves one by one mates；Obtain first in every stock
One minimum matching value, then obtains T smallest match value of global minima again in all of stock, obtains these simultaneously
Smallest match is worth the corresponding coupling date.
In the matching process, the matching process of two shares changing tendency fragments has considered various factors.First to position
Weighting, position weight more on the right side is bigger；Next same tropism is weighted, give larger power with rising or with the position fallen
Weight；Finally subtract each other absolute value by what weight was multiplied by relevant position amount of increase and amount of decrease, as final comparison distance.
Wherein, the tendency data after similar stock mates the date in step (4) refers to amount of increase and amount of decrease, relatively exchange hand, phase
To turnover rate etc..These tendency nests are used former stock to be predicted, such as by the amount of increase and amount of decrease that the later stage is daily, with former to be predicted
Based on the closing price of last day of trade of stock, its subsequently daily closing price can be calculated, in conjunction with laterally opposed amount then
Can be with the daily opening price of backwards calculation, highest price and lowest price；By the longitudinally opposed exchange hand of similar stock, with former treat pre-
Based on surveying the exchange hand of last day of trade of stock, its subsequently daily exchange hand can be calculated；Other longitudinally opposed amounts
Similarly applied.
Brief description
Fig. 1 is the flow chart of New Approach of Short-term Stock Prediction of the present invention.
Fig. 2 be a certain stock Short Term based on the inventive method output predict the outcome 1.
Fig. 3 be a certain stock Short Term based on the inventive method output predict the outcome 2.
Here most like number of share of stock T value is 2, provides predicting the outcome of 2 Short Terms in therefore Fig. 2 and Fig. 3.Dotted line
It is to predict the outcome afterwards, coupling segment length L of in figure stock to be matched and prediction transaction number of days N are taken as 30.
Specific embodiment
Below in conjunction with the accompanying drawings and example, the present invention is described in detail.
Short-term forecast refers generally to the prediction of following to stock more than the 2 weeks days of trade, prediction in such as 20 days, prediction on the 30th, and 60
Day prediction etc..
Predicting the outcome of the inventive method not only includes the prediction of daily closing price, amount of increase and amount of decrease, also include daily opening price,
The prediction of the aspects such as highest price, lowest price, exchange hand.
Hypothesis stock list is S, S=[S1, S2,…,Si,…,Sn], n is the quantity of stock in stock pond, such as in China
The quantity of city's stock or the quantity of listed stock of the U.S..
For every stock it is assumed that stock to be predicted is Sm, m=1 ..., the concrete prediction steps of n are as follows.
First, stock certificate data pretreatment.
Preprocessing process is primarily directed to the calculating of some relative quantities, including laterally opposed amount and longitudinally opposed amount.
Assume there is following data field for every stock in stock list S：Opening price Open, closing price Close,
Highest price High, lowest price Low, amount of increase and amount of decrease Change, exchange hand Volume, turnover rate Turnover etc., wherein closing price
Close is front power price again.Process of data preprocessing is as follows.
1.1 laterally opposed amounts.Calculate the increase and decrease amplitude with respect to same day closing price Close, and add newer field.Need to count
The field calculated includes opening price Open, highest price High and lowest price Low, specific as follows：
Opening price increase and decrease amplitude StdOpen=100* (Open-Close)/Close;
Highest price increase and decrease amplitude StdHigh=100* (High-Close)/Close;
Lowest price increase and decrease amplitude StdLow=100* (Low-Close)/Close.
1.2 longitudinally opposed amounts.Calculate the increase and decrease amplitude of the relatively previous day of trade, and add newer field.Calculative word
Section includes exchange hand Volume and turnover rate Turnover, specific as follows：
Exchange hand increases and decreases amplitude StdVolume=100* (Volume- lastVolume)/lastVolume, wherein,
LastVolume represents the exchange hand of the previous day of trade；
Turnover rate increases and decreases amplitude StdTurnover=100* (Turnover- lastTurnover)/lastTurnover, its
In, lastTurnover represents the turnover rate of the previous day of trade.
Need to predict if there are other fields, such as conclusion of the business stroke count, turnover etc., can be similar to calculate corresponding relatively
Value, adds corresponding field.Calculate gained relative value to use in the final step of the inventive method.
2nd, the loading of stock certificate data.
This step mainly completes the set-up procedure of data, obtains the recent friendship of stock to be predicted from original issue stock database
The historical trading day data of easily day data and stock to be matched.
2.1 obtaining stock S to be predictedmThe nearly L day of trade amount of increase and amount of decrease data, formed an array, be designated as A,
A=[a1,a2,…,ai,…aL]
Wherein, aiRepresent the amount of increase and amount of decrease of the day of trade of nearly L-i.a0Represent the amount of increase and amount of decrease of current trading day.The value of L at least must accord with
Close the requirement of the short-term forecast day of trade, such as>=20.
Every stock in 2.2 couples of S, since obtaining certain time point（As on January 1st, 2005）, arrive current trading day
The data of the front L day of trade, forms another array, is designated as Bi,i=[1,n],
Bi=[bi1,bi2,…,bij,…bik]
Wherein, bijRepresent the amount of increase and amount of decrease of the j position corresponding day of trade of i-th stock.Each BiLength k be not necessarily equal
, because there being the impact of the factors such as suspension in the middle of stock.
Record b simultaneouslyijTrade date, be designated as another array Ci,i=[1,n],
Ci=[ci1,ci2,…,cij,…cik]
Wherein, cijThe j position representing i-th stock corresponds to trade date.
3rd, piecewise shifted matching between stock.
This step mainly completes stock to be predicted and certain only matching process between stock to be matched, and acquires and treat
The minimum of a value of coupling stock coupling and Corresponding matching date.
Matching process is in A and BiLaunch, the length of A is L, BiLength be K, K>=L, concrete matching process is as follows：
3.1 with step-length for 1, and circulation is from BiThe middle amount of increase and amount of decrease data obtaining length L, is designated as B；
3.2 A and B is compared, and obtains matching value.Matching process weights to position first, and position weight more on the right side is more
Greatly；Next same tropism is weighted, give larger weight with rising or with the position fallen；Finally weight is multiplied by relevant position to rise
Drop range subtract each other absolute value, as final comparison distance；
The minimum of a value of 3.3 matching values recording all comparisons and sub-minimum, and its corresponding coupling date, as A and BiCoupling
Final result, that is, two matching results of every stock record, are designated as P respectivelyi, Pi+n,i=[1,n],
Pi=[Vi,Di], Pi+n=[Vi+n,Di+n]
Wherein, Vi、Vi+nRepresent A and B respectivelyiMinimum and time little matching value；Di、Di+nRepresent smallest match value respectively little with secondary
The matching value corresponding coupling date.
Why stock coupling between any two records two results, is because that being possible to most like coupling all just goes out
In now same stock.
4th, former forward similar stocks of matching value sequence are obtained.
This step is based on previous step and moves weighted registration result array P, obtains T only most like stock.Detailed process is：
P to array PiNumerical value is ranked up from small to large, obtains numerical value minimum front T Pi and its corresponding Di, formed after sequence
New array Mt,t=[1,T], Mt=[Pt,Dt].Here the value of T should not take too greatly, typically takes 2, because the value generation of T
The short-term forecast result of T kind by table.This step obtain most like stock process can be combined with turnover rate, exchange hand etc. because
Element is carried out.
5th, obtain similar stock and mate the later stage tendency data after the date.
This step obtains N number of day of trade (N is typically the taken as 20-30) data after similar stock mates the date, the number of acquisition
According to including amount of increase and amount of decrease Change, and newly-increased each increase and decrease amplitude field in step 1, here as StdOpen, StdHigh,
StdLow, StdVolume, StdTurnover etc..
6th, obtain the data of stock current trading day to be predicted.
This step obtains stock current trading day data to be predicted, and it is (front multiple that the data of acquisition includes closing price Close
Power), and in step 1, have the original field calculating previous day of trade increasing degree relatively, as Volume here,
Turnover.
7th, Stock Prediction result generates.
This step is predicted the outcome based on the data genaration that front several steps are already prepared to.Basic thought is, with to be predicted
The data of the current trading day of stock, as " the previous day of trade " reference data, mates the tendency number after the date in conjunction with similar stock
According to calculating is reduced into the tendency data of Stock Prediction to be predicted.
The tendency of each similar stock that preceding step obtains all will be reduced into a kind of short-term forecast result, detailed process
As follows：
Data Close of stock current trading day to be predicted, Volume, Turnover are set to the previous day of trade by 7.1
LastClose, lastVolume, lastTurnover result；Obtain a certain similar stock and mate the tendency number after the date
According to；
7.2 reducing the prediction data of next day of trade, reduction process is：
Next day of trade closing price Close=lastClose+lastClose*Change/100;
Next day of trade opening price Open=Close+Close*StdOpen/100;
Next day of trade highest price High=Close+Close*StdHigh/100;
Next day of trade lowest price Low=Close+Close*StdLow/100;
Next daily turnover Volume=lastVolume+lastVolume * StdVolume/100 that concludes the business;
Next day of trade turnover rate Turnover=lastTurnover+lastTurnover * StdTurnover/100;
7.3 by closing price Close of current trading day, exchange hand Volume, and turnover rate Turnover is set to the previous day of trade
LastClose, lastVolume, lastTurnover result；
7.4 repeat 7.2,7.3 steps, until restoring desired whole day of trade prediction data.
Above step will obtain predicting the outcome based on a certain similar shares changing tendency.The T being the previously calculated only phase
Like stock, the T Short Term that can get stock to be predicted is predicted the outcome.
In sum, the present invention proposes a kind of New Approach of Short-term Stock Prediction based on most like tendency, takes full advantage of
The historical data of all stocks, can make preferable prediction to the Short Term of stock, and prediction not only includes daily closing price, rises
The prediction of drop range, also includes the prediction of the aspects such as daily opening price, highest price, lowest price, exchange hand.
The inventive method is similarly applied to the data that security class has time series feature, such as fund, futures etc..Cause
This, although disclosing the specific embodiments and the drawings of the present invention for the purpose of illustration, its object is to help understand that the present invention's is interior
Hold and implement according to this, but it will be appreciated by those skilled in the art that：In the essence without departing from the present invention and appended claim
In god and scope, various replacements, to change and modifications be all impossible.Therefore, the present invention should not be limited to most preferred embodiment and
Accompanying drawing disclosure of that.Presently disclosed embodiment should be understood illustrative in all respects rather than it be claimed
Scope restriction.
Claims (6)
1. a kind of New Approach of Short-term Stock Prediction based on most like tendency is it is characterised in that methods described comprises the steps：
The calculating of laterally opposed amount is carried out to each day of trade of every stock；
The calculating of longitudinally opposed amount is carried out to each day of trade relatively previous day of trade of every stock；
The recent tendency fragment of stock to be predicted is moved one by one weighted registration with the historical data of every stock, obtain
For the similar corresponding matching section of front T stock and coupling date；
Based on tendency data after most like stock matching section mates the date, in conjunction with horizontal, longitudinally opposed amount, calculate reduction
The later stage tendency of stock to be predicted.
2. the New Approach of Short-term Stock Prediction based on most like tendency according to claim 1 is it is characterised in that pre- in data
Processing stage laterally opposed amount and the calculating of longitudinally opposed amount, laterally opposed amount refer to each of every stock opening price the day of trade,
Highest price, lowest price are with respect to the increasing degree of same day closing price；Longitudinally opposed amount refers to the one-tenth of every each day of trade of stock
The increasing degree of the analog value with respect to the previous day of trade for the variables such as friendship amount, turnover rate.
3. the New Approach of Short-term Stock Prediction based on most like tendency according to claim 1 it is characterised in that most like walk
The acquisition of gesture stock is by the recent tendency section of stock to be predicted and all stocks are carried out mobile weighting ratio by turn one by one
Relatively acquisition.
4. the New Approach of Short-term Stock Prediction based on most like tendency according to claim 1 is it is characterised in that obtaining entirely
Before the most like stock matching section of office, every stock remains the best match section of two candidates, and most like to cover the overall situation two
Individual coupling just appears at the situation in same stock.
5. the New Approach of Short-term Stock Prediction based on most like tendency according to claim 1 is it is characterised in that predict tendency
The combination of the later stage tendency data of most like stock and stock current trading day data to be predicted in generating process, by most like stock
Coupling later stage on the date amount of increase and amount of decrease of ticket, the longitudinally varying amount of history etc. are grafted onto the current trading day of stock to be predicted, thus calculating
Reduction generates daily closing price, opening price, highest price, lowest price, exchange hand etc..
6. the New Approach of Short-term Stock Prediction based on most like tendency according to claim 1 is it is characterised in that to be predicted
The prediction of stock is not only the prediction to following a period of time closing price, amount of increase and amount of decrease, also includes daily opening price, highest price,
At a low price, the prediction of the aspect such as exchange hand, turnover rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610969059.0A CN106447135A (en) | 2016-11-06 | 2016-11-06 | Stock short-term prediction method based on most similar tendency |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610969059.0A CN106447135A (en) | 2016-11-06 | 2016-11-06 | Stock short-term prediction method based on most similar tendency |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447135A true CN106447135A (en) | 2017-02-22 |
Family
ID=58180550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610969059.0A Pending CN106447135A (en) | 2016-11-06 | 2016-11-06 | Stock short-term prediction method based on most similar tendency |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447135A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292742A (en) * | 2017-05-25 | 2017-10-24 | 武汉楚鼎信息技术有限公司 | A kind of system and implementation method invested in stock according to any indicator combination |
| CN107480819A (en) * | 2017-08-09 | 2017-12-15 | 灯塔财经信息有限公司 | A kind of method and device of data analysis |
| CN109117991A (en) * | 2018-07-26 | 2019-01-01 | 北京京东金融科技控股有限公司 | One B shareB order transaction method and apparatus |
| CN110009222A (en) * | 2019-02-13 | 2019-07-12 | 王龙 | A kind of fund risk early warning system based on big data analysis |
| CN111199419A (en) * | 2019-12-19 | 2020-05-26 | 成都数联铭品科技有限公司 | Method and system for identifying abnormal stock transaction |
-
2016
- 2016-11-06 CN CN201610969059.0A patent/CN106447135A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292742A (en) * | 2017-05-25 | 2017-10-24 | 武汉楚鼎信息技术有限公司 | A kind of system and implementation method invested in stock according to any indicator combination |
| CN107480819A (en) * | 2017-08-09 | 2017-12-15 | 灯塔财经信息有限公司 | A kind of method and device of data analysis |
| CN109117991A (en) * | 2018-07-26 | 2019-01-01 | 北京京东金融科技控股有限公司 | One B shareB order transaction method and apparatus |
| CN110009222A (en) * | 2019-02-13 | 2019-07-12 | 王龙 | A kind of fund risk early warning system based on big data analysis |
| CN110009222B (en) * | 2019-02-13 | 2022-03-22 | 广州经传多贏投资咨询有限公司 | Fund risk early warning system based on big data analysis |
| CN111199419A (en) * | 2019-12-19 | 2020-05-26 | 成都数联铭品科技有限公司 | Method and system for identifying abnormal stock transaction |
| CN111199419B (en) * | 2019-12-19 | 2023-09-15 | 成都数联铭品科技有限公司 | Stock abnormal transaction identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tan et al. | Stock selection with random forest: An exploitation of excess return in the Chinese stock market | |
| Roh | Forecasting the volatility of stock price index | |
| Wei | A GA-weighted ANFIS model based on multiple stock market volatility causality for TAIEX forecasting | |
| CN106447135A (en) | Stock short-term prediction method based on most similar tendency | |
| Alimoradi et al. | A league championship algorithm equipped with network structure and backward Q-learning for extracting stock trading rules | |
| Kempa et al. | Investigation of bagging ensembles of genetic neural networks and fuzzy systems for real estate appraisal | |
| Niu et al. | A hybrid model combining variational mode decomposition and an attention-GRU network for stock price index forecasting | |
| CN108229750A (en) | A kind of stock yield Forecasting Methodology | |
| Xu et al. | An optimized decomposition integration framework for carbon price prediction based on multi-factor two-stage feature dimension reduction | |
| Cai et al. | Gaussian weighting reversion strategy for accurate online portfolio selection | |
| Ruxanda et al. | Configuring artificial neural networks for stock market predictions | |
| He et al. | Nonparametric probabilistic load forecasting based on quantile combination in electrical power systems | |
| Ma et al. | A novel prediction based portfolio optimization model using deep learning | |
| Jin | A mean-VaR based deep reinforcement learning framework for practical algorithmic trading | |
| Feng et al. | Factor investing: Hierarchical ensemble learning | |
| Badawy et al. | Genetic algorithms for predicting the Egyptian stock market | |
| Chen et al. | Hedge fund return prediction and fund selection: A machine-learning approach | |
| Romero | Generative adversarial network for stock market price prediction | |
| Ky et al. | A Markov-fuzzy combination model for stock market forecasting | |
| Yin et al. | Nonlinear analysis and prediction of soybean futures. | |
| Zha et al. | A hierarchical reinforcement learning framework for stock selection and portfolio | |
| Malim et al. | Prediction of FTSE Bursa Malaysia KLCI Stock Market using LSTM Recurrent Neural Network | |
| Matviychuk | Fuzzy logic approach to identification and forecasting of financial time series using Elliott wave theory | |
| Aye et al. | Forecasting Indian macroeconomic variables using medium-scale var models | |
| Yang et al. | A Dynamic Weighted Distancedbased Fuzzy Time Series Neural Network with Bootstrap Model for Option Price Forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |