KR20150077957A - Method of determining a trend and a turning point of a stock price index using sentiment based indexes according to an analysis of social data and system thereof - Google Patents

Abstract

Provided are a method and a system for determining a trend and a turning point of a stock price index using sentiment-based indexes in accordance with an analysis of social data. The method for determining a trend and a turning point of a stock price index comprises the steps of: collecting a plurality of documents related with an item group from social media data or the like during a first period to an updated date, when the renewal of a date occurs, and a second period longer than the first period and generating and storing sensitivity evaluation data about the entire documents by date; calculating a first moving average of sensitivity evaluation data by date included in the first period and generating accumulative first moving average data including a first moving average before the renewal and a first moving average after the renewal; calculating a second moving average of sensitivity evaluation data by date included in the second period and generating accumulative second moving average data including a second moving average before the renewal and a second moving average after the renewal; and determining a short-term trend in the stock price index related to the item group as a rise or a fall, when the accumulative first moving average data are greater or less than the accumulative second moving average data.

Description

In this paper, we propose a method to determine the turnaround point of a stock index based on sensitivity index based on the analysis of social data. thereof}

The present invention relates to a method and system for determining a trend of a stock index and a turning point, and more particularly, to a method and system for determining a trend of a stock index using a sensitivity index based on an analysis of social data and a turning point determination method.

The stock market may not be able to account for changes in the stock price index, such as the stock price of stocks that include at least one stock or the specific market index of the stock group, due to the complex pricing mechanism, as a result of changes in market fundamentals It happens frequently. Despite the absence of significant changes in fundamentals, we find that prices fluctuate significantly, with the emergence of new news often contributing to price fluctuations. This is because the news includes information on various phenomena that take place in the real world and information about what kind of changes will occur and proceed in the future with regard to politics, economy, society and enterprise in the future. Therefore, news and stock prices are closely related, and news allows market participants to predict the volatility of the stock market in some way.

In recent years, not only news information provided by securities companies, media companies, etc., but also social media data such as tweets, personal blogs related to stock market, Facebook, social data of various portal sites Information provided by services and the like is explosively increasing. Such data is being distributed to market participants in a much larger amount than news information, and is referred to as Big Data.

Social media data is composed of individual subjective viewpoints and has a lower reliability than news information. However, since social media data is provided as a big data class, Not only are the responses derived with considerable objectivity, but the future prospects of the stock group have reached a point where they can be justified.

However, the fundamentals that affect stock prices are so diverse and complex that the circulation of social media data, news and stock prices, and social media data, affect the stock index again.

As a result, social media data may be a factor influencing the stock index and leading indicators of the stock index. However, a lot of news is appearing and disappearing every day, and it is almost impossible to analyze the news one by one to understand the impact on the stock price.

Moreover, it is not easy to grasp clearly whether the contents are positive or negative for the market, because various types of social media data and news such as macro policies, forecast news, daily market conditions, performance, and corporate news are mass-produced in real time. In addition, since it is often the case that both the positive and negative opinions of the stock market are presented by the somewhat neutral nuance of the social media data and news attributes, it is not simple to grasp the hypothesis of the stock market. There is a risk that it will change depending on

Therefore, previous studies have analyzed the stock price index that responds to particular events and news that can easily be identified, or reverse the existence of news that caused the price index to fluctuate significantly. However, most of the news is composed of texts with no fixed form or attribute, and many news items are mass produced every day.

Accordingly, various attempts have been made to predict trends of stock indexes by analyzing big data such as personalized social media data including recent news, or to determine the turning point of stock indexes.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is an object of the present invention to provide a method and system for collecting moving average cumulative data of different periods for emotion evaluation data analyzed using a large amount of data including social data and news related to a stock group, And a system and method for determining a turning point of a stock index.

In addition, by analyzing emotional evaluation data of the stocks for a large amount of data, and calculating the emotion index of the emotion, and comparing with the overheat or stagnation index, the trend of the stock index, And to provide the system.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method for determining a trend and a turning point of a stock index using a sensitivity index based on an analysis of social data, comprising the steps of: Collecting a plurality of documents related to a stock group including at least one item from social media data and stock market related web data during a first period up to a date and a second period longer than the first period, The method according to claim 1, further comprising the steps of: generating and storing emotion evaluation data for the entire period; calculating a first moving average of the emotion evaluation data by date belonging to the first period, Generating cumulative first accumulated moving average data for each of the first period and the second cumulative period, 2 moving average, generating second moving average cumulative data composed of the pre-update second moving average and the updated second moving average, and generating the first moving average cumulative data as the second moving average cumulative data, Wherein when the first moving average cumulative data is lower than the second moving average cumulative data, the short-term trend of the stock price index related to the stock group is judged as an increase, And determining a short-term trend as a decline.

The details of other embodiments are included in the detailed description and drawings.

According to the present invention, moving average cumulative data of different periods are calculated and compared with the emotion evaluation data analyzed by using a large amount of data including social data and news related to the stock group, so that the short term trend of the stock index related to the stock group It is possible to predict the grasp and provide a leading indicator of the trend change of the stock group.

In addition, if the trend is ascending or descending through short-term trends, it is predicted that the stock market will turn into a bull market or a bear market if it is confirmed that the trading volume related to the stock group obtained from stock market index data increases or decreases.

According to the present invention, the emotional evaluation data of the stock group for a large amount of data is analyzed, and the emotional impact index as a turning point index is calculated and compared with the overheat or stagnation index to grasp the market situation of the stock group, Can be grasped more accurately. In addition, it is possible to predict when the stock index of the stock group will rise or fall through comparison with the conversion index corresponding to the median value of the sensitivity index.

1 is a configuration diagram of a stock price forecasting system including a trend and a turning point determination system of a stock price index according to an embodiment of the present invention.
2 is a block diagram of a keyword database.
3 is a block diagram of the document storage unit.
4 is a block diagram of the data analysis unit.
5 is a block diagram of the emotion dictionary database.
6 is a configuration diagram of the emotion based index portion.
7 is a block diagram of the correlation analysis / decision unit.
8 is a flowchart of a stock price prediction method including a process of generating emotion evaluation data.
FIG. 9 is a flowchart illustrating a process of a trend prediction unit for implementing a trend and a turning point determination method of a stock price index according to an embodiment of the present invention.
FIG. 10 is a diagram showing collection of emotion evaluation data while moving in the setting period of the first and second periods.
11 is a diagram showing the first and second moving average cumulative data and the short term trend results of the stock price index on the display unit.
12 is a flowchart illustrating a process of a conversion predicting unit for implementing a trend and a turning point determination method of a stock price index according to another embodiment of the present invention.
13 is a flowchart illustrating a process of a conversion predicting unit for implementing a trend and a turning point determination method according to another embodiment of the present invention.
FIGS. 14A and 14B are diagrams illustrating a process of calculating a daily net increase amount and a net decrease amount, and a process of calculating a daily increase amount and a real decrease amount.
FIG. 15 is a diagram showing the index cumulative data, the market conditions of the stock group, and the up / down switch of the stock index of the stock group on the display unit.
FIG. 16 is a flowchart showing a collection period of the sensitivity evaluation data, a determination of a delay period, and a selection process of evaluation data.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings and the following description. However, the present invention is not limited to the embodiments described herein but may be embodied in other forms. Rather, the embodiments disclosed herein are being provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. Like reference numerals designate like elements throughout the specification. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. &Quot; comprises "and / or" comprising ", as used herein, unless the recited element, step, operation, and / Or additions.

Hereinafter, a trend and a turning point determination system of a stock price index according to an embodiment of the present invention will be described with reference to FIGS. 1 to 7. FIG. 1 is a configuration diagram of a stock price prediction system including a trend and a turning point determination system of a stock price index according to an embodiment of the present invention. FIG. 2 is a block diagram of a keyword database, FIG. 3 is a block diagram of a document storage unit, and FIG. 4 is a block diagram of a data analysis unit. 5 is a block diagram of the emotion dictionary database, FIG. 6 is a block diagram of the emotion-based index unit, and FIG. 7 is a block diagram of the correlation analysis / decision unit.

The trend and change point determination system of the stock index of the present invention will be described with reference to the system according to the present invention in the stock price prediction system 100 in the document collecting / extracting unit 110, the document storing unit 120, the morpheme analyzing unit 140, The data analysis unit 150, the evaluation data storage unit 165 and the emotion-based index unit 200. Hereinafter, the configuration of the determination system will be described in detail along with the elements constituting the stock price prediction system 100 .

The stock price forecasting system 100 predicts the stock price index of the stock group based on the emotion evaluation data generated by emotionally evaluating each of the keywords extracted from the social media data 10 and the stock market related web data 20, In addition, we generate moving averages, cumulative moving averages data, and emotion impact indexes for different periods as stock price trend indicators of the stock group, and generate data related to the short-term trend of the stock price index of the stock group and the market situation forecast of the stock group. In this case, the stock group includes at least one stock (ie, individual company), the stock price index is the stock price of the stock, and the stock index is a stock index For example, the KOSPI 200 index.

Also, the moving average is a value obtained by arithmetically averaging the emotion evaluation data during a specific period of movement, and the cumulative moving average data is data accumulated by connecting moving moving average. The emotion impact index is a leading indicator indicative of a trend pattern or a conversion pattern in the stock price index of the stock group by indexing cumulative emotion evaluation data of the stock group using a predetermined formula.

Specifically, the stock price forecasting system 100 includes a document collecting / extracting unit 110 (FIG. 1) for collecting a large amount of documents from the social media data 10 and the stock market related web data 20 every time a date is updated, A morpheme analysis unit 140 for analyzing morphemes with respect to expressions or sentences included in a plurality of documents for each individual company, a keyword extracted from the analyzed morpheme, And a data analyzer 150 for analyzing data of all the plurality of documents by evaluating emotions of the plurality of documents by performing emotional evaluation on the stock group (combination of individual companies or a plurality of companies) .

The stock price prediction system 100 also includes an evaluation data storage 165 for storing emotion evaluation data generated by the analyzer 150 for each date and a moving average, cumulative moving average data, Based index unit 200 for generating data related to the short-term trend of the stock price index of the stock group and the market situation prediction on the basis thereof and displaying the data on the display unit 190.

The stock price forecasting system 100 also includes a correlation analysis / decision unit (not shown) that generates analysis data from the correlation between the stock market index data and the economic indicator data, together with the emotion evaluation data selected by the predetermined condition among the cumulative sensitivity evaluation data A stock price predicting unit 180 for predicting the stock price index of the stock group based on the selected emotion evaluation data and analytical data, and a display unit 190 for displaying a forecast result derived from the stock price predicting unit 180 have.

The document collecting / extracting unit 110 collects a large amount of documents related to the stock group from the social media data 10 and the stock market related web data 20 every time a date update occurs, . Here, the items included in the stock group are companies listed on the stock market, and the collected documents can be implemented in the form of at least one of html, PDF (Portable Document Format), image and moving image.

The social media data 10 is media data input via a fixed computer or a mobile device connected to a network such as the Internet and is data that can be mutually shared with other users connected to the network. For example, the social media data 10 may be social media sites 12 operated by a social media server and blog sites 14 operated by various portal sites and including personalized contents. The social media sites 12 may be social media serving on so-called SNS, twitter, facebook, and various portal sites.

The stock market related web data 20 is web data provided from a media company, a national wave broadcasting company, a cable broadcasting company, a portal site news, a financial corporation, a stock market related institution or the like, and is stock market related data which is more professional or credible than the social media data 10. The stock market related web data 20 includes stock market news 22 that is provided from stock market information provided by a press company, a broadcasting company, a portal site news, and a portal site, a financial service company such as a bank, a securities company, Related statistic sites 26 that provide analytical information related to the stock market at the financial institution portal sites 24 and the stock related public or private institutions.

The stock index data 30 is stock information for each individual stock listed on the stock, and for example, market information such as market price, high price, low price, close price, closing price, transaction amount, transaction amount, transaction price, transaction source, upper limit price, lower limit price, . ≪ / RTI >

 When collecting a large amount of documents from the social media data 10 and the market related web data 20, the document collecting / extracting unit 110 does not collect all the documents but refers to the keyword database 120, Is to collect documents related to.

As shown in FIG. 2, the keyword database 120 includes a main keyword 122 associated with a company name of an individual item, Related keywords 126 related to the company's executives and the like, words that may affect the individual items, company-related keywords 128 related to the context, and the like May be stored. The sub keyword may exist in a categorized form classified for each company as a specific word, context or the like of the corresponding company.

For example, the main keyword 122 may be a company name of an individual item listed on the market such as Samsung Electronics, LG Electronics, KT, etc. In the case of Samsung Electronics, the main keyword 122 may include a product / May be "Galaxy", "smartphone", "Hauzen", "tablet", "appmarket" and the like, and the human-related keywords 126 may be executives of major executives of Samsung Electronics, The keywords related to the company situation (128) are words that can affect the stock price of Samsung Electronics and various words such as "maximum ever", "performance", "goodbye", " . ≪ / RTI >

The document collecting / extracting unit 110 extracts documents including the main keyword 122, the product / service related keyword 124 and the human related keyword 126 among the keywords included in the collected plurality of documents. Thus, document data suitable for sensitivity evaluation can be efficiently selected.

The document storage unit 130 may store the extracted documents in a form suitable for morphological analysis. For example, as shown in FIG. 3, pdf 133, image 134, moving image 135, and the like.

The morpheme analysis unit 140 is a pre-processing unit for processing the morpheme in a form suitable for emotion evaluation, and analyzes the morpheme that is the smallest language unit having a meaning with respect to the format of the stored plurality of documents, and performs processing for specifying each part of speech. In this case, the morpheme analysis unit 140 can perform morphological analysis in parallel on each format through a process suitable for each format shown in Fig.

In addition, the morpheme analysis unit 140 may classify sentences, contexts, and the like in the expressions included in the document format in units of words, and may parse keywords adjacent to keywords related to individual items. For example, in a case where a sentence related to Samsung Electronics and a sentence related to the LG Electronics coexist in a blog site of a particular person, the morphological analysis unit 140 analyzes the sentence structure of the blog site We classify the text into an e-word unit, and then search for keywords such as Samsung Electronics or LG Electronics' names, products / services, personal information, etc., parse words and phrases adjacent thereto, and classify them into keywords for Samsung Electronics and LG Electronics And stores it.

Referring to FIG. 4, the data analyzing unit 150 may include a data sensitivity evaluating unit 150 for evaluating emotion evaluation data of the stock group through the entirety of a plurality of documents by evaluating the sensitivity of each keyword processed by the morphology analyzing unit 140, And a keyword analysis unit 154 for statistically processing keywords processed by the morpheme analysis unit 140 and the keyword analysis unit 152. [

The data sensitivity evaluation unit 152 refers to the emotion dictionary database 160 storing an evaluation of affirmative, neutral or negative for each keyword from the morpheme analysis unit 140 and a score associated with the evaluation, Scored by evaluating by date, either positive, neutral or negative. The scoring algorithm may be Naive bayes algorithm, Simple voter algorithm, K Nearest Neighborhood (KNN), SVM (Support Vector Machine). As an example of the simple voter algorithm, the emotion dictionaries database 160 can store the keywords of affirmative, neutral, and negation in the form of a table as emotion evaluation for the keyword, as shown in FIG. Most of the parts of a keyword related to such emotional evaluation can be composed of nouns and adjectives. For example, in the affirmative evaluation table 162, there are keywords such as "rise "," maximum ever ", "ascend ", and score" 1 " In the negative evaluation table 166, keywords such as "recession "," down ", and "complaint" exist and the score "-1" The score given to the keyword stored in the neutral evaluation table 164 is "0 ". The score shown in FIG. 5 is exemplified for distinguishing between positive and negative. However, a score associated with positive or negative evaluation is different from a score according to the degree of sensitivity of market participants to the keyword, And can be composed of different scores.

The data sensitivity evaluation unit 152 can calculate the emotion evaluation data of the stock group for all of the plurality of documents by summing the scores given for the keywords determined as positive, neutral, and negative by the emotion dictionaries database 160 for each date . Here, the data sensitivity evaluation unit 152 does not perform evaluation of affirmative, neutral, and negative for each document after performing sensitivity evaluation on keywords of all documents. If an emotional evaluation is performed on a document to determine the sensitivity nuances of the document, each document may be given a negative evaluation of an equivalent score, even though there are many more negatively valued keywords compared to other documents . Accordingly, the ratio of the positive or negative elements of the stock group existing from the entire plurality of documents extracted from the social media data 10 and the stock market related web data 20 can be analyzed to be distorted. Therefore, in this embodiment, the analysis is prevented from being distorted by performing the emotion evaluation without grouping the morphologically analyzed keywords from the entire plurality of documents by document.

The keyword analyzing unit 154 may perform a statistical analysis on the analyzed keywords from the morpheme analyzing unit 140, such as the number of collected data per period and the correlation analysis between the keywords, and provide the result to the display unit 190. The keyword analysis unit 154 selects keywords that are not registered in the keyword database 120 among the analyzed keywords and the newly selected keywords are updated and stored in the keyword database 120 so that the document collection / 110), and the manager can store the keyword to be reflected in the emotion evaluation of the new keyword in the emotion dictionary database 160. [0053] FIG.

The evaluation data storage unit 165 stores the emotion evaluation data of the stock group calculated from the data emotion evaluation unit 152 by date and delivers the stored emotion evaluation data to the emotion based index unit 200.

The emotion-based index unit 200 calculates and analyzes moving average and cumulative moving average data for different periods of time to determine trends related to the bull market / bull market, (Not shown). In addition, the emotion-based index unit 200 calculates emotional impact indexes as indexes of change in the stock price index from the emotion evaluation data accumulated over a predetermined period of time, thereby analyzing the market conditions related to overheating / stagnation of the stocks, And a conversion prediction unit 200 for determining a future up and down.

The trend prediction unit 210 includes a first moving average calculation unit 212, a second moving average calculation unit 214, a cross analysis unit 216, a long term prediction unit 217, and a trend indicator unit 218 .

The first moving average calculation unit 212 calculates a first moving average of the sensitivity evaluation data by date belonging to the first period among the sensitivity evaluation data of the stock group stored in the evaluation data storage unit 165 by date, 1 moving average and the first moving average after the update. The first moving average is calculated for short-term trend recognition. For example, as shown in Fig. 10, the emotion evaluation data corresponding to the first period is added up and divided by the total number of days in the first period. Here, the first period may be set to a period suitable for grasping the short-term trend, for example, 12 business days.

In addition, the first moving average is an average value of the emotion evaluation data corresponding to the first period until the date when the date is updated, as shown in FIG. Therefore, the first moving average accumulation data can be generated in the form of the line shown in 1110 of FIG. 11 by continuously accumulating the first moving average before and after the update.

The second moving average calculation unit 214 calculates a second moving average of the sensitivity evaluation data by date belonging to the second period longer than the first period among the sensitivity evaluation data of the stock group stored in the evaluation data storage unit 165 by date And generates second moving average accumulated data composed of a second moving average before updating and a second moving average after updating. The second moving average is calculated in order to grasp the mid-term trend. For example, as shown in Fig. 10, the emotion evaluation data corresponding to the second period is added up and divided by the total number of days in the second period. Here, the second period may be 26 days, for example, on a business day basis to be suitable for grasping the mid-term trend.

Similarly to the first moving average, the second moving average is an average value of the emotion evaluation data corresponding to the second period up to the day when the date is updated, as shown in Fig. Thus, the second moving average cumulative data can be generated in the form of the line shown in 1120 of FIG. 11 continuously accumulating the second moving average before and after the update.

The cross analyzer 216 receives the first and second moving average cumulative data from the moving average calculators 212 and 214. When the first moving average cumulative data is the second moving average cumulative data as in 1130 of FIG. 11, the first moving average cumulative data is determined as the second moving average cumulative cumulative cumulative cumulative cumulative cumulative cumulative cumulative cumulative data In the case of a dead cross that falls downwards from the data, the short term trend of the stock index declines.

When the short-term forecasting unit 217 determines that the short-term trend of the stock price index related to the stock group is predicted as rising, the long-term forecasting unit 217 receives the transaction amount of the corresponding stock group among the stock index data 30, Can be expected to turn into a bull market. When the crossing analysis unit 216 determines that the crossing analysis unit 216 determines that the stock index is related to the stock group and the stock price index related to the stock group is predicted as a short-term trend downward, the long-term forecasting unit 217 receives the transaction amount of the corresponding stock group among the stock index data 30 If the trading volume is confirmed to decrease, it can be predicted that the stock group will be converted into a bear market.

The trend indicator unit 218 generates data for indexing the first and second moving average cumulative data, the short-term trend determination result of the stock index related to the stock group and the bull market / bull market forecast result of the stock group, and displays the indexed data on the display unit 190 .

On the other hand, the conversion predicting unit 220 calculates the sensitivity index as a turning point index to the stock index of the stock group and analyzes the sensitivity index to determine whether the stock index of the stock group is up or down . Specifically, the conversion predicting unit 220 may include a sensitivity index unit 222, a situation analysis unit 224, and a conversion index unit 226.

The emotional impact index unit 222 compares the emotional evaluation data for each day belonging to the third period among the emotional evaluation data of the stock group stored in the evaluation data storage unit 165 with the affirmative evaluation score and the positive ascending score The accumulated downward score can be calculated on a date basis. Specifically, as shown in FIG. 14A, after affirmation and negation are given to each keyword, the scores of the keywords evaluated as positive during the third period are aggregated by date to calculate the rising score 1412, It is possible to calculate the drop score 1414 by counting the scores of the keywords evaluated as negative during each day. The third period can be determined on the basis of the degree of correlation between the accumulated emotion evaluation data and the actual stock price index of the individual stock group independently of the first and second periods, As shown in FIG. The third period used in this embodiment may be 20 days, for example, on a business day basis, so that the fluctuation width corresponds to a dull market characteristic.

Also, based on the ratio of the average value of the daily increment with respect to the score of at least one of the rising score and the falling score calculated during the third period to the average value of the daily decrease with respect to the score, It is possible to generate a sensitivity influence index as a turning point indicator of the turning point. In this case, the daily increment and the daily decrease with respect to this score are calculated as the daily room increment (r) and the daily room decrease (1416) based on the difference value 1416 between the rising score and the falling score calculated for each day as shown in Fig. d). Alternatively, the daily increment and the daily decrease with respect to the score may be a daily increment (u) and a daily decrease (f) based on a rise score calculated for each day as shown in FIG. 14A.

In addition, as in the case of the first and second moving averages, a value corresponding to the third period up to the date when the date is updated can be calculated by a predetermined formula. Therefore, the emotion influence index section 222 can continuously accumulate the before and after sensitivity affect indexes to generate index accumulation data.

The process of generating the emotion index at the emotion index unit 222 will be described later in detail with reference to FIGS. 12 to 14B.

The situation analyzing unit 224 receives the sensitivity index for the third period generated by the sensitivity index unit 222 and determines that the market condition of the stock group is overheated when the sensitivity index is higher than the superheat index, If the sensitivity index is below the stagnation index, it can be determined that the market situation of the stock group is stagnant. Here, the superheat index and the stagnation index may be 70 and 30, respectively, as shown in FIG.

In addition, when the cumulative index data, which is another value derived from the sensitivity index unit 222, exceeds the conversion index 50 shown in FIG. 15, the situation analyzer 224 determines that the stock index of the stock group , And when the index cumulative data falls to a value lower than 50, which is the conversion index, the stock price index of the stock group can be determined as a downward conversion.

The conversion indicator unit 226 generates data for indexing the index accumulation data, the determination result of the market condition of the stock group and the up / down conversion prediction result of the stock group, and transmits the indexed data to the display unit 190.

On the other hand, the correlation analysis / decision unit 170 can generate analysis data from the correlation between the stock market index data and the economic index data, together with the emotion evaluation data selected by the predetermined condition among the accumulated emotional evaluation data. 7, the correlation analysis / determination unit 170 includes a first correlation table unit 172, an evaluation data collection period determination unit 173, an evaluation data selection unit 174, a delay period determination unit 175, An economic index database 176 and a second correlation table section 177. [

The first correlation table unit 172 receives emotion evaluation data accumulated in the evaluation data storage unit 171 on a date-by-date basis and performs correlation analysis with the stock index data 30 input from the outside, The analyzed correlation between the stock index data 30 of the individual stock and the corresponding evaluation data is stored in the first correlation table portion 172. [

In addition, the first correlation table unit 172 judges an upward / downward trend of the stock group determined through the sensitivity index, and when there is a discrepancy between the determined trend and the actual stock index trend of the stock group, The addition can notify the occurrence of the trend change.

The evaluation data collection period determining unit 173 determines the collection period of the evaluation data that affects the stock index of the stock group based on the past correlation stored in the first correlation table unit 172, May select evaluation data corresponding to the collection period among the sensitivity evaluation data accumulated in the evaluation data storage unit 171 and provide the evaluation data to the stock price prediction unit 180. [ This collection period differs from the third period used in the emotion influence index section 222.

The delay period determination unit 175 determines a delay period that elapses until the emotion evaluation data is reflected in the stock price index of the stock group based on the past correlation of the first correlation table unit 172, It is possible to predict the stock price index after the delay period by providing the delay period at the stock index 180 in the stock index prediction of the stock group.

By providing the collection period and the delay period in the prediction of the stock predicting unit 180 as described above, it is possible to utilize more effective emotion evaluation data and more accurately specify the stock price prediction timing.

The second correlation table unit 177 also stores the analysis data derived from the correlation between the stock index data 30 and the economic index data related to the macro economic index accumulated in the economic index database 176, 180). In this case, the economic indicator data are basically common economic indicators for all individual items, such as interest rates, exchange rates, projected growth rates, price indexes, balance of payments, and so on.

1, the stock price predicting unit 180 calculates the stock price of the stock group based on the emotion evaluation data selected from the correlation analysis / decision unit 170, the delay period, and the analysis data generated from the second correlation table unit 177 The index can be predicted. The stock price index prediction is based on the time series analysis based on the stock market index data 30 and the economic index data and the evaluation data analyzed from the news of the social media data 10 and the stock market related web data 20 is calculated from the time series analysis Can be combined with a term that corrects the predicted stock price index. In order to further improve the accuracy of the stock price index prediction, the weight value calculated based on the correlation of the first correlation table section 172 is given to the sensitivity evaluation data, so that the weighted sensitivity evaluation data may be reflected in the stock index have. The predicted stock prices of the individual items calculated by the stock price estimating unit 180 and their statistical values are displayed on the display unit 190.

According to the above-described stock price forecasting system 100, the emotion evaluation data on a large amount of data including social data and news is reflected, so that the market atmosphere and information on the stock group are extracted objectively and meaningfully from various viewpoints of market participants It is possible to predict the stock price index of the stock group more reliably. Particularly, the reason why the stock price prediction through the emotional evaluation of the social media data including the news analysis is more accurate and reliable than the stock price prediction by the analysis of the news produced by the stock market related web data 20 is that the social media data Because they are produced with much more data and statistically closer to the population.

Hereinafter, with reference to FIG. 1 and FIG. 8 to FIG. 11, a description will be made in detail of the process of the trend forecasting unit for implementing the stock index exponentiation method and the trend and change point determination method of the stock index according to the present embodiment.

FIG. 8 is a flow chart of a stock price prediction method including a process of generating emotion evaluation data, FIG. 9 is a flowchart illustrating a process of a trend prediction unit for implementing a trend and a turning point determination method of a stock price index according to an embodiment of the present invention It is a flowchart. FIG. 10 is a diagram showing collection of emotion evaluation data while moving in the setting period of the first and second periods, FIG. 11 shows the results of the first and second moving average cumulative data and the short- Fig.

The document collecting / extracting unit 110 collects, from the social media data 10 and the market related web data 20, a large amount of documents related to the stock group including at least one item, such as html, PDF, Image and moving image, and receives stock indicator data 30 (S810).

In this case, the social media data 10 is operated as a so-called SNS on twitter, facebook, social media sites 12 such as social media serving on various portal sites, and various portal sites Or blog sites 14 containing personalized content. The stock market related web data 20 includes stock market news sites 22 served by media companies, broadcasters and portal sites, financial company portal sites 24 provided by financial institutions such as banks, Related statistical sites 26 that provide analytical information related to the stock market at the relevant public or private institution.

 Next, the document collecting / extracting unit 110 collects documents related to the stock group by referring to the keyword database 120, and the document storing unit 130 may store the extracted documents in a form suitable for morphological analysis (S820 ). The document collecting / extracting unit 110 extracts a main keyword 122, a product / service-related keyword 124, and a personal keyword 122 from the keywords stored in the keyword database 120 shown in FIG. 2 among the expressions contained in the collected plurality of documents. By extracting the documents including the related keywords 126, document data suitable for emotion evaluation can be efficiently selected.

3, the document storage unit 130 stores the extracted documents according to the format of the extracted documents, that is, html 132, pdf 133, image 134, 135) or the like.

Then, the morpheme analysis unit 140 analyzes morphemes for the format of a plurality of stored documents as a pre-processing for processing in a form suitable for emotion evaluation (S830). In this case, the morpheme analysis unit 140 can perform morphological analysis in parallel on each format through a process suitable for each format shown in Fig. In addition, the morpheme analysis unit 140 may classify sentences, contexts, and the like in the expressions included in the document format in units of words, and may parse the keywords adjacent to the keywords associated with individual items or combinations of plural items. The detailed description thereof will be omitted in the morpheme analysis unit 140 of the stock price prediction system 100.

Next, the data sensitivity evaluation unit 152 of the data analysis unit 150 refers to the emotion dictionaries database 160 shown in Fig. 5 and determines whether the keyword is positive or negative for each keyword processed by the morphology analysis unit 140 The emotion of the plurality of documents is evaluated by emotion evaluation (S840). As a result, the data sensitivity evaluation unit 152 generates emotion evaluation data related to the stock group for all the plurality of documents by date.

More specifically, the data analysis unit 150 refers to the emotion dictionary database 160 storing an evaluation of affirmative, neutral, or negative for each keyword from the morpheme analysis unit 140 and a score associated with the evaluation, And evaluates the keyword as positive, neutral, or negative, and scores it. The data emotion evaluation unit 152 can calculate the emotion evaluation data of the stock group for all of the plurality of documents by summing the scores given for the keywords determined as positive, neutral, and negative by the emotion dictionaries database 160 have.

Then, the evaluation data storage unit 165 continuously stores the emotion evaluation data of the stock group calculated from the data emotion evaluation unit 152 for each date, and stores the stored emotion evaluation data in the first and second 2 moving average calculating units 212 and 214 (S850).

Next, referring to FIG. 9, the first moving average calculating unit 212 calculates a first moving average of the statistical evaluation data of the stock group stored in the evaluation data storage unit 165, The moving average is calculated, and the first moving average accumulated data including the first moving average before the update and the first moving average after the updating is generated (S910).

The first moving average is calculated for short-term trend recognition. For example, as shown in Fig. 10, the emotion evaluation data corresponding to the first period is added up and divided by the total number of days in the first period. Here, the first period may be set to a period suitable for grasping the short-term trend, for example, 12 business days.

In addition, the first moving average is an average value of the emotion evaluation data corresponding to the first period until the date when the date is updated, as shown in FIG. Accordingly, the first moving average accumulated data 1110 can be generated in the form of a line in which the first moving average before and after the update is continuously accumulated, as shown in Fig.

Next, the second moving average calculator 214 calculates a second moving average of the emotion evaluation data of each of the stock group stored in the evaluation data storage unit 165 for each day belonging to the second period, which is longer than the first period, And generates second moving average cumulative data composed of a second moving average before the update and a second moving average after the updating in operation S920.

The second moving average is calculated in order to grasp the mid-term trend. For example, as shown in Fig. 10, the emotion evaluation data corresponding to the second period is added up and divided by the total number of days in the second period. Here, the second period may be, for example, 26 business days.

Similarly to the first moving average, the second moving average is an average value of the emotion evaluation data corresponding to the second period up to the day when the date is updated, as shown in Fig. Therefore, the second moving average accumulated data 1120 can be generated in the form of a line in which the second moving average before and after the update is continuously accumulated, as shown in Fig.

Then, the cross analysis unit 216 receives the first and second moving average accumulated data 1110 and 1120 from the moving average calculating units 212 and 214, and the first moving average accumulated data 1110 , It is determined that the short-term trend of the stock price index related to the stock group is ascending, and when the first moving average accumulated data 1110 is in the case of the golden cross 1130 that exceeds the second moving average accumulated data 1120 In the case of the dead cross 1140 falling downward from the second moving average accumulated data 1120, it is determined that the short-term trend of the stock price index falls (S930).

Accordingly, by calculating and comparing moving average cumulative data of different periods with respect to the sensitivity evaluation data, it is possible to predict the short-term trend of the stock price index related to the stock group, and to provide the leading index of the trend change of the stock group.

Next, when the short-term forecasting unit 217 determines that the short-term trend of the stock index related to the stock group is predicted to be a golden cross 1130 in the cross analysis unit 216, If it is confirmed that the transaction volume is increased by receiving the transaction volume, it can be predicted that the stock group is converted into the bull market (S940). If the stock index related to the stock group is predicted as a short-term trend decline, the long-season forecasting unit 217 predicts the trading volume of the stock group among the stock index data 30 (S940), it can be predicted that the stock group will be converted into the bear market.

According to this, if the trend is ascending or descending through short-term trends, it can be predicted that the stock market will turn into a bull market or a bear market if it is confirmed that the trading volume related to the stock group acquired from stock market index data increases or decreases.

Next, the trend indicator unit 218 generates data for indexing the first and second moving average cumulative data, the short-term trend determination result of the stock price index related to the stock group, and the bullish / bear market prediction result of the stock group, To the display unit 190 (S950).

Referring again to FIG. 8, the keyword analyzing unit 154 analyzes the keywords analyzed by the morphological analysis unit 140 during the emotion evaluation performed by the data emotion evaluation unit 152, Analysis, and the like, and provide the result to the display unit 190. [0213] FIG. The keyword analyzing unit 154 updates and stores the keywords not analyzed in the keyword database 120 among the analyzed keywords in the keyword database 120, Can be stored in the dictionary database 160. [

Next, the correlation analysis / decision section 170 can generate analysis data from the correlation between the stock market index data and the economic index data, together with the emotion evaluation data selected by the predetermined condition among the accumulated emotional evaluation data.

 The process of selecting emotion evaluation data according to a predetermined condition will be described with reference to FIGS. 7 and 16. FIG. FIG. 16 is a flowchart showing a collection period of the sensitivity evaluation data, a determination of a delay period, and a selection process of evaluation data.

On the basis of the correlation analysis result of the first correlation table unit 172 in which the past correlation between the sensitivity evaluation data accumulated in the daily accumulation and the stock index indicator data 30 is stored for each stock group in the evaluation data storage unit 165 The data collection period determining unit 173 determines the collection period of the evaluation data that affects the stock price of the individual stock (S852).

Next, the delay period determination unit 175 determines a delay period that elapses until the sensitivity evaluation data is reflected in the stock price of the individual item, based on the past correlation of the first correlation table unit 172 (S854).

Subsequently, the evaluation data selection unit 174 selects emotion evaluation data corresponding to the collection period among the evaluation data cumulatively stored in the evaluation data storage unit 165 (S856). Then, the correlation analysis / decision unit 170 provides the selected sensitivity evaluation data and the delay period to the stock price prediction unit 180 (S858).

8, the stock price predicting unit 180 predicts the stock price of the stock group based on the emotion evaluation data selected from the correlation analysis / decision unit 170, the delay period, and the analysis data generated from the second correlation table unit 177 The index is predicted (S860).

On the other hand, the first correlation table unit 172 determines an upward / downward trend of the individual item through the sensitivity index generated in the sensitivity index unit 222, and determines whether there is a discrepancy between the determined trend and the trend of the actual stock index of the stock group It is possible to display, on the display unit 190, a predicted result that a trend change occurs in the actual stock index of the stock group together with the predicted stock index.

Hereinafter, with reference to FIG. 1, FIG. 8, and FIG. 12 to FIG. 15, a detailed description will be given of the process of the stock index exponentiation method and the process of the conversion predicting part for implementing the trend and change point determination method of the stock index according to the present embodiment do.

12 is a flowchart illustrating a process of a conversion predicting unit for implementing a trend and a turning point determination method of a stock price index according to another embodiment of the present invention.

8, the evaluation data storage unit 165 continuously stores the emotion evaluation data of the stock group calculated from the data emotion evaluation unit 152 for each date, and stores the stored emotion evaluation data in the emotion-based index unit 200 To the index unit 222 (S850).

Subsequently, the emotion-influenced index unit 222 compares the emotion evaluation data of the third period among the emotion evaluation data of the stock group stored by date in the evaluation data storage unit 165 with the affirmative evaluation score of the emotion evaluation data by date, And the accumulated downward score can be calculated on a date basis. Specifically, as shown in FIG. 14A, after affirmation and negation are given to each keyword, the scores of the keywords evaluated as positive during the third period are aggregated by date to calculate the rising score 1412, It is possible to calculate the drop score 1414 by counting the scores of the keywords evaluated as negative during each day. The third period used in the present embodiment is independent of the first and second periods, and may be 20 days, for example, on a business day basis so that the fluctuation width corresponds to a dull market characteristic.

14B, after the rise score 1412 and the drop score 1414 are aggregated by date, the emotion influence index section 222 calculates the rise score 1412 and the drop score 1414, which are calculated for each day, The daily yarn increment r and the daily yarn reduction d can be calculated at step S1210. FIG. 14B is a diagram illustrating a process of calculating the daily room increase and the room decrease.

Subsequently, the emotion influence index section 222 can calculate the average value of the daily room increment r and the average value of the daily room decrease d in the aggregation period (S1220).

Next, the sensitivity index unit 222 can calculate the sensitivity index of the stock group by inputting the ratio of the average value of the daily room increment r and the average value of the daily room decrease d to the equation (1) (S1230 ). The sensitivity index obtained by the following equation (1) indicates that the trend pattern of the individual item increases as the value approaches 100, and if it is the opposite, the trend pattern of the individual item decreases.

[Equation 1]

Emotion Impact Index = 100- (100 / (1 + ES_1))

(Where ES (Effective Score) _1 = (average value of the daily room increment in the third period) / (average value of the daily room decrement in the third period)

At the same time, as in the case of the first and second moving averages, when the date is updated, a value corresponding to the third period up to the updated date can be calculated by the expression (1) have. Therefore, the emotion influence index section 222 accumulates the before and after sensitivity affect index continuously, and generates the index accumulation data as shown in FIG. 15 (S1230). FIG. 15 is a diagram showing the index cumulative data, the market conditions of the stock group, and the up / down switch of the stock index of the stock group on the display unit.

Next, the situation analyzing unit 224 receives the sensitivity index for the third period generated by the sensitivity index unit 222, and if the sensitivity index is higher than the superheat index, the market condition of the stock group is overheated (See 1510 in Fig. 15), and when the sensitivity index is lower than the stagnation index, it can be determined that the market situation of the stock group is stagnant (S1240). Here, the superheat index and the stagnation index may be 70 and 30, respectively, as shown in FIG.

Then, when the index cumulative data, which is another value derived from the sensitivity index unit 222, exceeds the conversion index 50 shown in FIG. 15, the situation analyzer 224 updates the stock price index of the stock group (See 1520 in FIG. 15). If the index cumulative data falls below the conversion index of 50, the stock index of the stock group is determined to be a downward conversion (see 1530 in FIG. 15) (S1240).

Subsequently, the conversion indicator unit 226 generates data for indexing the index accumulation data, the determination result of the market condition of the stock group and the up / down conversion prediction result of the stock group, and transmits the indexed data to the display unit 190 (S1260).

In the above-described embodiment, all of the daily room increase r and the daily room decrease d during the third period are all included in the case of obtaining the average value for calculating the emotion influence index. However, as a modified embodiment, The index unit 222 can select the daily room increment r and the daily room decrease d used to calculate the average value according to a specific condition.

Before describing the average value calculation (S1220), the emotion influence index section 222 determines whether the daily room increase r is increased to be equal to or smaller than the threshold ratio or the daily room decrease d It is possible to judge whether or not it is reduced to be equal to or less than the critical ratio with respect to the date immediately before the corresponding date. The threshold ratio is the rate of day-to-day rise or fall that causes the stock market to suspend trading of individual stocks, for example, 15% of the previous day.

After the determination is performed, when the sensitivity index unit 222 performs the average value calculation (S1220), the daily room increase r and the daily room decrease d that are increased or decreased in the range below the threshold ratio The average value can be calculated. In the subsequent process, the process of S1230 may be performed to generate the emotion influence index and the index accumulation data.

The embodiment according to Figures 12 and 14b uses the ratio of the daily room increment r and the daily room decrease d based on the difference 1416 between the rising score 1412 and the falling score 1414 calculated for each day In other embodiments shown in Figs. 13 and 14A, the emotion index is calculated by using the daily increment (u) and the daily decrease (f) based on the rise score 1412 It shows the process.

13 is a flowchart illustrating a process of a conversion predicting unit for implementing a trend and a turning point determination method according to another embodiment of the present invention. 14A is a diagram illustrating a process of calculating a net addition amount and a net decrease amount.

The embodiment according to Figs. 13 and 14A corresponds to steps S1240, S1250. S1260. Therefore, only different points will be described.

The emotion influence index unit 222 may calculate the daily increment u and the daily decrease f of the rising score 1412 during the third period S1210a.

Subsequently, the emotion influence index section 222 can calculate the average value of the daily net increment u and the average of the daily net decrease f in the third period (S1220a).

Next, the emotion influence index unit 222 may calculate the emotion influence index by inputting the ratio of the average value of the daily net increment u and the average value of the daily net decrease f to the following equation (S1230a). The sensitivity index obtained by the following equation (2) indicates that the trend pattern of individual items is on an upward trend as the index is closer to 100, and on the contrary, it indicates that the trend pattern of individual items is on a downward trend.

&Quot; (2) "

Emotion Impact Index = 100- (100 / (1 + ES_2))

(Where ES_2 = (average value of the daily increment of the third period) / (average value of the daily decrement of the third period)

At the same time, as in the description of Fig. 12, the emotion influence index section 222 can calculate the value corresponding to the third period from the date when the date is updated to the date when it is updated, using the above-mentioned equation (2). Therefore, the emotion influence index section 222 may accumulate the before and after emotion influence indexes continuously to generate index accumulation data as shown in FIG. 15 (S1230a).

12-15, the ratio of the difference value 1416 between the rising score 1412 and the falling score 1414 or the average value of the increments and decrements based on the rising score 812 alone can be calculated using Equations 1 or 2 However, it is not limited to the above-described embodiment to obtain the increment and decrement, but it is possible to obtain the increase and decrease by various combinations of the rise score 1412 and the drop score 1414 can do. For example, after calculating the average value of the increase and decrease of the downward score 1414 alone or the average of the increase and decrease of the increase score 1412 and the increase and decrease of the decrease score 1414, The ratio of the increment to the decrease can be obtained by combining the average values.

According to the embodiment described with reference to Figs. 12 to 15, the emotional evaluation data of the stock group is analyzed, and the emotional impact index as the turning point index is calculated and compared with the overheat or stagnation index to grasp the market situation of the stock group, It is possible to more accurately grasp the time point when the inversion occurs. In addition, it is possible to predict when the stock index of the stock group will rise or fall through comparison with the conversion index corresponding to the median value of the sensitivity index.

8, 9, 12, and 13 and the short-term trend of the stock group shown in Figs. 8, 9, 12, and 13 and the constituent elements of the stock price prediction system 100 including the stock index- The method for determining the situation prediction can be recorded in a computer-readable recording medium in the form of a program realizing the function. Here, the computer-readable recording medium refers to a recording medium that can be read by a computer by accumulating information such as data and programs by electric, magnetic, optical, mechanical, or chemical action. Examples of such a recording medium that can be detached from a computer include a flexible disk, a magneto-optical disk, a CD-ROM, a CD-R / W, a DVD, a DAT, and a memory card. In addition, a hard disk, a ROM, or the like is used as a recording medium fixed to a computer.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be construed as limiting the scope of the present invention. I will understand. Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be determined by all changes or modifications derived from the scope of the appended claims and the appended claims.

100: stock price prediction system 110: document collection /
120: keyword database 130: document storage unit
140: Morphological analysis unit 150: Data analysis unit
160: Sensibility dictionary database 165: Evaluation data storage unit
170: correlation analysis / decision unit 180:
190: Display section 200: Emotion-based index section

Claims (10)

A method of determining a trend and a turning point of a stock price index using a sensitivity based index according to an analysis of social data,
Wherein, in the event that an update of the date occurs, during the first period up to the updated date and during the second period longer than the first period, the item group including at least one item from the social media data and market- Collecting a plurality of documents related to the plurality of documents and generating and storing emotion evaluation data for all the plurality of documents by date;
Calculating a first moving average of the emotion evaluation data by date belonging to the first period, and generating first moving average accumulated data composed of the first moving average before update and the first moving average after updating;
Calculating a second moving average of the sensitivity evaluation data by date belonging to the second period, generating second moving average cumulative data composed of the pre-update second moving average and the updated second moving average; And
When the first moving average cumulative data exceeds the second moving average cumulative data upwardly, it is determined that the short-term trend of the stock index related to the stock group is ascending, and when the first moving average cumulative data is greater than the second moving average And determining that the short-term trend of the stock price index declines when the price falls below the cumulative data. The method according to claim 1,
If the short-term trend of the stock price index is judged to be an increase, it is predicted that the stock group will be switched to a bull market if the trading volume related to the stock group increases, and if the short- A method of determining a trend and a turning point of a stock price index that predicts that the stock group will transition to a bear market if trading volume decreases. The method according to claim 1,
If the stock price index is the stock price of the stock, and if the stocks included in the stock group include a plurality of stocks, the stock price index is a stock price index that is indexed based on the market cap of the stocks ≪ / RTI > The method according to claim 1,
Wherein the generating and storing the emotion evaluation data comprises:
Collecting a plurality of documents related to the stock group from the social media data and the stock market related web data during the first period and the second period if the update of the date occurs;
Analyzing morphemes for the plurality of documents; And
And evaluating the sensitivity of the stock group to the entirety of the plurality of documents for each date by evaluating the sensitivity of the keywords extracted from the analyzed morpheme to either positive or negative. 5. The method of claim 4,
Collecting the plurality of documents further comprises collecting a plurality of documents related to the stock group from the social media data and the market related web data during a third period when the date update occurs After the step of evaluating the emotion of the stock group for all the plurality of documents by the date,
Calculating a rising score calculated by the positive evaluation and a falling score calculated by evaluating the negative;
As the turning point index of the stock price index of the stock group, based on the ratio of the average value of the daily increment with respect to the score of at least one of the rising score and the falling score calculated during the third period and the average value of the daily decrease with respect to the score Creating an influence index; And
Determining that the market condition of the stock group is overheated when the emotion index is greater than or equal to the superheat index and determining that the market situation of the stock group is stagnant when the emotion index is lower than the stagnation index How to determine trends and turning points in stock indexes. 6. The method of claim 5,
Wherein the superheating index is 70 and the stagnation index is 30. 6. The method of claim 5,
The step of generating the emotion influence index may further include generating index accumulation data composed of the pre-update emotion influence index and the post-update emotion influence index,
After the step of determining that the market condition of the stock group is overheating or stagnating,
When the index cumulative data exceeds the conversion index of 50 upwardly, it is determined that the stock price index of the stock group is ascending conversion, and when the index cumulative data falls downward from the conversion index of 50, And determining the stock price index as a downward conversion. 6. The method of claim 5,
Wherein the daily increment and the daily decrease associated with the score are a daily room increment and a daily room decrease based on the difference between the rising score and the falling score calculated for each day,
Wherein the generating the emotional impact index comprises:
Calculating a difference between the rising score and the falling score by the date during the third period to calculate the daily room increment and the daily room decrease;
Calculating an average value of the daily room increment and the average value of the daily room decrease in the third period; And
And calculating the emotional impact index by inputting the ratio of the average value of the daily room increase and the average value of the daily room decrease to the following equation (1).
[Equation 1]
Emotion Impact Index = 100- (100 / (1 + ES_1))
(Where ES (Effective Score) _1 = (average value of the daily room increment in the third period) / (average value of the daily room decrement in the third period) 6. The method of claim 5,
Wherein the daily increment and the daily decrement relating to the score are a daily increment and a daily decrement based on the rising score calculated for each day,
Wherein the generating the emotional impact index comprises:
Calculating the daily increment and the daily decrement of the rising score during the third period;
Calculating an average value of the daily increment in the third period and an average value of the daily decrement in the third period; And
And calculating the emotion index by inputting the ratio of the average of the daily net increment and the average of the daily net decrease to the following equation (2).
&Quot; (2) "
Emotion Impact Index = 100- (100 / (1 + ES_2))
(Where ES_2 = (average value of the daily increment of the third period) / (average value of the daily decrement of the third period) A system for determining a trend and a turning point of a stock price index using a sensitivity based index according to an analysis of social data,
Related data from social media data and stock market related web data for a first period up to the updated date and a second period longer than the first period when an update of the date occurs An evaluation data storage unit for storing emotional evaluation data for all the plurality of documents collected by the date;
A first moving average calculating unit configured to calculate a first moving average of the evaluation data by date belonging to the first period and to generate first moving average cumulative data composed of the first moving average before updating and the first moving average after updating, A calculating unit;
A second moving average that generates second moving average cumulative data composed of the pre-update second moving average and the updated second moving average, calculating a second moving average of the evaluation data by date belonging to the second period, A calculating unit; And
When the first moving average cumulative data exceeds the second moving average cumulative data upwardly, it is determined that the short-term trend of the stock index related to the stock group is ascending, and when the first moving average cumulative data is greater than the second moving average And a cross analysis unit for determining a short-term trend of the stock price index as a fall when the price index falls down below the cumulative data.

Images