scholarly journals Detecting and Analyzing Politically-Themed Stocks Using Text Mining Techniques and Transfer Entropy—Focus on the Republic of Korea’s Case

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 734
Author(s):  
Insu Choi ◽  
Woo Chang Kim
Keyword(s):  
Abnormal Returns ◽  
Investment Strategy ◽  
Causal Relationships ◽  
Volume Data ◽  
Text Data ◽  
Search Volume ◽  
Political Events ◽  
Related Text ◽  
The Republic ◽  
The Empirical Analysis

Politically-themed stocks mainly refer to stocks that benefit from the policies of politicians. This study gave the empirical analysis of the politically-themed stocks in the Republic of Korea and constructed politically-themed stock networks based on the Republic of Korea’s politically-themed stocks, derived mainly from politicians. To select politically-themed stocks, we calculated the daily politician sentiment index (PSI), which means politicians’ daily reputation using politicians’ search volume data and sentiment analysis results from politician-related text data. Additionally, we selected politically-themed stock candidates from politician-related search volume data. To measure causal relationships, we adopted entropy-based measures. We determined politically-themed stocks based on causal relationships from the rates of change of the PSI to their abnormal returns. To illustrate causal relationships between politically-themed stocks, we constructed politically-themed stock networks based on causal relationships using entropy-based approaches. Moreover, we experimented using politically-themed stocks in real-world situations from the schematized networks, focusing on politically-themed stock networks’ dynamic changes. We verified that the investment strategy using the PSI and politically-themed stocks that we selected could benchmark the main stock market indices such as the KOSPI and KOSDAQ around political events.

scholarly journals A Densely Connected GRU Neural Network Based on Coattention Mechanism for Chinese Rice-Related Question Similarity Matching

Agronomy ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1307
Author(s):  
Haoriqin Wang ◽  
Huaji Zhu ◽  
Huarui Wu ◽  
Xiaomin Wang ◽  
Xiao Han ◽  
...  
Keyword(s):  
Related Question ◽  
Similarity Matching ◽  
Frequency Method ◽  
Text Data ◽  
Information Platform ◽  
Document Frequency ◽  
Proposed Model ◽  
Related Text ◽  
Text Features ◽  
Matching Models

In the question-and-answer (Q&A) communities of the “China Agricultural Technology Extension Information Platform”, thousands of rice-related Chinese questions are newly added every day. The rapid detection of the same semantic question is the key to the success of a rice-related intelligent Q&A system. To allow the fast and automatic detection of the same semantic rice-related questions, we propose a new method based on the Coattention-DenseGRU (Gated Recurrent Unit). According to the rice-related question characteristics, we applied word2vec with the TF-IDF (Term Frequency–Inverse Document Frequency) method to process and analyze the text data and compare it with the Word2vec, GloVe, and TF-IDF methods. Combined with the agricultural word segmentation dictionary, we applied Word2vec with the TF-IDF method, effectively solving the problem of high dimension and sparse data in the rice-related text. Each network layer employed the connection information of features and all previous recursive layers’ hidden features. To alleviate the problem of feature vector size increasing due to dense splicing, an autoencoder was used after dense concatenation. The experimental results show that rice-related question similarity matching based on Coattention-DenseGRU can improve the utilization of text features, reduce the loss of features, and achieve fast and accurate similarity matching of the rice-related question dataset. The precision and F1 values of the proposed model were 96.3% and 96.9%, respectively. Compared with seven other kinds of question similarity matching models, we present a new state-of-the-art method with our rice-related question dataset.

Day-of-the-week effect: A sectoral analysis of Pakistan stock exchange

2021 ◽  
pp. 2141006
Author(s):  
Farah Naz ◽  
Kanwal Zahra ◽  
Muhammad Ahmad ◽  
Salman Riaz
Keyword(s):  
Stock Exchange ◽  
Abnormal Returns ◽  
Weak Form ◽  
Investment Strategy ◽  
Ordinary Least Squares ◽  
Financial Decision ◽  
Day Of The Week ◽  
Timing Strategies ◽  
Autoregressive Conditional Heteroscedasticity ◽  
Sector Returns

This study scrutinizes the day-of-the-week effect anomaly in the context of market and industry analysis of the Pakistan stock exchange. For this purpose, daily closing prices of KSE-100, KSE-30, and KSE-All Share Index from January 01, 2009 to December 31, 2018, have been used. Similarly, sector returns are also calculated, taking average log-returns of selected sample firms. To analyze the data ordinary least squares (OLS) regression, general generalized autoregressive conditional heteroscedasticity (GARCH) (1,1) as well as asymmetric threshold GARCH (TGARCH) and exponential GARCH (EGARCH) models have been employed to model the leverage effect of good and bad news on market volatility. The results indicate the evidence of daily seasonality, with significant Monday and Wednesday effect in PSX indices returns as well as in most of the industry returns. Monday is found to be the day with the highest average returns with the highest return volatility. The findings of the study reveal that there exists a weak form of inefficiency in the Pakistan Stock Market, which implies the possibility of earning abnormal returns by investors using timing strategies. In terms of return predictability, this study is essential for international and domestic investors and it may affect their investment strategy and return management. The results might be interesting to the financial experts as they ponder the available conditions in the capital market for financial decision-making. This study is one of its first kind that includes both indices as well as industry returns for analysis of manufacturing industries in Pakistan stock exchange.

scholarly journals Speeding up calibration of latent Dirichlet allocation model to improve topic analysis in software engineering

2021 ◽  
Author(s):  
Jorge Arturo Lopez
Keyword(s):  
Software Engineering ◽  
Simple Formula ◽  
Latent Dirichlet Allocation ◽  
Allocation Model ◽  
Topic Analysis ◽  
Latent Dirichlet Allocation Model ◽  
Related Text ◽  
The Empirical Analysis ◽  
Large Corpus ◽  
Dirichlet Allocation

Extraction of topics from large text corpuses helps improve Software Engineering (SE) processes. Latent Dirichlet Allocation (LDA) represents one of the algorithmic tools to understand, search, exploit, and summarize a large corpus of data (documents), and it is often used to perform such analysis. However, calibration of the models is computationally expensive, especially if iterating over a large number of topics. Our goal is to create a simple formula allowing analysts to estimate the number of topics, so that the top X topics include the desired proportion of documents under study. We derived the formula from the empirical analysis of three SE-related text corpuses. We believe that practitioners can use our formula to expedite LDA analysis. The formula is also of interest to theoreticians, as it suggests that different SE text corpuses have similar underlying properties.

The Investment Strategy of Free Cash Flow Multiple

1998 ◽  
Vol 01 (03) ◽  
pp. 355-367 ◽  
Author(s):  
Eric Liluan Chu
Keyword(s):  
Cash Flow ◽  
Abnormal Returns ◽  
Investment Strategy ◽  
Cash Flows ◽  
Free Cash Flow ◽  
Market Model ◽  
Superior Performance ◽  
Price Ratio ◽  
Cumulative Abnormal Returns ◽  
Daily Returns

This study applies the investment strategy recommended by Hackel and Livnat (1993), the free cash flow (FCF) multiple, in Taiwan after the promulgation of Taiwan's FASB No. 95 in 1989. The results indicate that the portfolio with the higher FCF/Price ratio significantly rewards returns in excess of the market. Instead of using earnings/price ratio in the forming portfolio, the study shows that the decile portfolio with the highest FCF/Price ratio significantly outperforms the market during the period from 1990 to 1994. If daily returns are adjusted by the market model, the decile portfolio presents an average 20.5268% cumulative abnormal returns in the testing period, which is statistically higher than zero. The results also indicate that the annual cumulative abnormal returns of the FCF/Price ratio based portfolio are all positive. The annual results also show that the decile portfolio performs much better when the market declines significantly. The outperformance still exists if returns are adjusted by the market without considering risk. The decile portfolio presents an average 8.198% abnormal with a significant t value returns. The superiority of free cash flow in forming portfolio exists but with a decreasing trend when the portfolio is enlarged. The result implies that either the firms with extremely high FCF/Price ratios are undervalued by the market or the market responses slowly to their superior performance in cash flows. The finding supports Hackel and Livnat's (1993) arguments. It suggests that free cash flow is useful information especially for the forming portfolio. The results also enhance the usefulness of the statement of cash flow.

The development of ferrous metallurgy is an effective way to restore the Syrian economy

2020 ◽  
pp. 69-74
Author(s):  
S. V. Podkur ◽  
◽  
G. I. Kotelnikov ◽  
A. E. Semin ◽  
◽  
...  
Keyword(s):  
Ferrous Metallurgy ◽  
Investment Strategy ◽  
Rolled Sheet ◽  
Initial Stage ◽  
Metal Products ◽  
The Republic ◽  
Post War ◽  
Favorable Conditions ◽  
Hot Rolled ◽  
Stimulation Of

The Middle East is a victim of civilian contacts. Under the current conditions, the question arises of rationalizing the investment strategy of the post-war development of the countries of the region that have managed to overcome this crisis. In the article this problem is considered on the example of Syria. A rational way of multiplicative stimulation of the development of the country’s economy is proposed, based on the approach of J. M. Keynes. This approach consists in choosing the most favorable conditions for investment. According to the results of research at this point (industry) was ferrous metallurgy. At the initial stage of the post-war reconstruction of the republic, it can come out with a locomotive. The optimal configuration and place for the construction of a production metallurgical cluster that provides the market with the most popular types of metal products: 1 million tons per year of hot-rolled sheet (1-12.5 mm), 150 thousand tons of galvanized sheet per year (0.2-2, 5 mm), 200 thousand tons per year of shaped steel (2-8 mm), 50 thousand tons per year of galvanized shaped steel (0.7-3 mm). The functioning of the cluster will provide Syria with sheets and fittings, will contribute to the development of engineering and other sectors of the economy, will lead to an increase in the country’s GDP by 4.5% and a reduction in government debt payments by $ 532.5 million per year.

Discovering business information from search engine query data

2014 ◽  
Vol 38 (4) ◽  
pp. 562-574 ◽  
Author(s):  
Liwen Vaughan
Keyword(s):  
Search Engine ◽  
Business Performance ◽  
Google Trends ◽  
Volume Data ◽  
Content Type ◽  
Search Volume ◽  
Business Information ◽  
Position Data ◽  
Search Data ◽  
One Year

Purpose – The purpose of this paper is to examine the feasibility of discovering business information from search engine query data. Specifically the study tried to determine whether search volumes of company names are correlated with the companies’ business performance and position data. Design/methodology/approach – The top 50 US companies in the 2012 Fortune 500 list were included in the study. The following business performance and position data were collected: revenues, profits, assets, stockholders’ equity, profits as a percentage of revenues, and profits as a percentage of assets. Data on the search volumes of the company names were collected from Google Trends, which is based on search queries users enter into Google. Google Trends data were collected in the two scenarios of worldwide searches and US searches. Findings – The study found significant correlations between search volume data and business performance and position data, suggesting that search engine query data can be used to discover business information. Google Trends’ worldwide search data were better than the US domestic search data for this purpose. Research limitations/implications – The study is limited to only one country and to one year of data. Practical implications – Publicly available search engine query data such as those from Google Trends can be used to estimate business performance and position data which are not always publicly available. Search engine query data are timelier than business data. Originality/value – This is the first study to establish a relationship between search engine query data and business performance and position data.

scholarly journals The use of the recognition heuristic as an investment strategy in European stock markets

2017 ◽  
Vol 22 (43) ◽  
pp. 207-223 ◽  
Author(s):  
Júlio Lobão ◽  
Luís Pacheco ◽  
Carlos Pereira
Keyword(s):  
Financial Markets ◽  
Abnormal Returns ◽  
Investment Strategy ◽  
Google Trends ◽  
Recognition Heuristic ◽  
Monthly Basis ◽  
Content Type ◽  
Additional Information ◽  
Market Portfolio ◽  
Heuristic Strategies

Purpose People often face constraints such as a lack of time or information in taking decisions, which leads them to use heuristics. In these situations, fast and frugal rules may be useful for making adaptive decisions with fewer resources, even if it leads to suboptimal choices. When applied to financial markets, the recognition heuristic predicts that investors acquire the stocks that they are aware of, thereby inflating the price of the most recognized stocks. This paper aims to study the profitability against the market of the most recognized stocks in Europe. Design/methodology/approach In this paper, the authors perform a survey and use Google Trends to study the profitability against the market of the most recognized stocks in Europe. Findings The authors conclude that a recognition heuristic portfolio yields poorer returns than a market portfolio. In contrast, from the data collected on Google Trends, weak evidence was found that strong increases in companies monthly search volumes may lead to abnormal returns in the following month. Research limitations/implications The applied investment strategy does not account for transaction costs, which may jeopardize its profitability given the fact that it is necessary to revise the portfolio on a monthly basis. Despite the results obtained, they are useful to understanding the performance of recognition heuristic strategies over a comprehensive time horizon, and it would be interesting to depict its viability during different market conditions. This analysis could provide additional information about a preferable scenario for employing our strategies and, ultimately, enhance the profitability of recognition heuristic strategies. Practical implications Through the exhaustive analysis performed here on the recognition heuristic in the European stock market, it is possible to conclude that no evidence was found for the viability of exploring this type of strategy. In fact, the investors would always gain better returns when adopting a passive investment strategy. Therefore, it would be wise to assume that the European market presents at least a degree of efficiency where no investment would yield abnormal returns following the recognition heuristic. Originality/value The main objective of this paper is to study the performance of the recognition heuristic in the financial markets and to contribute to the knowledge in this field. Although many authors have already studied this heuristic when applied to financial markets, there is a lack of consensus in the literature.

Information search volume as a predictor of information explanatory power

2015 ◽  
Vol 23 (3) ◽  
pp. 238-252 ◽  
Author(s):  
Bixia Xu ◽  
Zhulin Huang
Keyword(s):  
Information Content ◽  
Information Search ◽  
Web Search ◽  
Explanatory Power ◽  
Accounting Information ◽  
Market Value ◽  
Volume Data ◽  
Content Type ◽  
Search Volume ◽  
The Relationship

Purpose – This paper aims to examine whether information search frequency of accounting information is related to the explanatory power of accounting information for firm market value. It also examines whether information content and state of nature can have an impact on this relationship. Design/methodology/approach – The paper is an empirical study using Web search volume data collected from Google Trends and financial and market data collected from Compustat. Findings – This paper finds that investors use Web search engines as an alternative way to search for information they need, search frequency of accounting information is positively related to the explanatory power of accounting information for firm market value, the relationship is found differential between statements and categories within a statement depending on the information content and the relationship is found stronger during economic upturns. Research limitations/implications – This paper examines 59 accounting items that are cross-firm commonly reported and that have data availability in Compustat. The external validity might be an issue. Practical implications – This paper is of interest to standard setters, corporate management and academics who wish to understand and improve the value of accounting information in the capital market. Originality/value – This paper is the first study which provides a comprehensive examination of the impact of investors’ information search volumes on the explanatory power of accounting information. It is also the first paper that intrudes Google Trends search volume data into accounting research.

Sign in / Sign up

Export Citation Format

Share Document