Stock Classification Research Articles

Unsupervised learning modeling of the impact of Black Swan events on financial network reconfiguration: New insights from the COVID-19 outbreak and the Russia-Ukraine war

The emergence of Black Swan events, such as the COVID-19 pandemic and the Russian-Ukrainian war, has presented new challenges for stock markets and necessitates a redesign of portfolio management strategies. This work investigates the impact of unexpected and rare events, like the COVID-19 pandemic and the military conflict between Russia and Ukraine, on the structure of the cross-correlation network of stock returns. This research area has not yet been explored in depth. Previous research has primarily focused on the effects on stock returns, volatility, or changes in the topological properties of complex financial networks. In contrast, this study introduces a novel two-phase approach, integrating complex networks and self-organizing maps (the Kohonen network), to analyze changes in network structure and stock classification. A total of 483 US stocks from the S&P 500 index were analyzed. The findings reveal a notable contrast between the networks constructed before and after the onset of the COVID-19 pandemic (895 quotations for each network), along with significant disparities in stock classification according to centrality measures. Moreover, in-depth analysis has revealed significant distinctions between the SOM classification and the inherent partitioning based on economic sectors for both periods. Our research highlights the process of asset reconfiguration within the cross-correlation network, triggered by uncommon and unexpected events that disrupt financial market quotations. These findings are crucial for investors, portfolio managers, policymakers, and researchers.

ML Model for Stock Classification

Abstract: This study examines how effectively volatility indices can forecast stock market movements by applying different machine learning techniques. It uses a dataset from Kaggle for the TCS Company, including variables such as 'Date,' 'Symbol,' 'Series,' 'Prev Close,' 'Open,' 'High,' 'Low,' 'Last,' 'Close,' 'VWAP,' 'Volume,' 'Turnover,' 'Deliverable Volume,' and '%Deliverable.' Various models were tested and evaluated based on metrics like the AUC-ROC Curve, Accuracy, Precision, Recall, F1-Score, Cross-Validation Accuracy, and the Confusion Matrix. The findings reveal that the Linear Regression (Classification model) surpasses other models in forecasting stock market directions with the highest levels of accuracy across all evaluation metrics. This highlights the potential of machine learning methods in leveraging volatility indices to accurately predict stock market trends

New perspectives for the intelligent rolling stock classification in railways: an artificial neural networks-based approach

New perspectives for the intelligent rolling stock classification in railways: an artificial neural networks-based approach

Numerological superstitions and market-wide herding: Evidence from China

We empirically investigate the effect of traditional Chinese numerological superstitions over market-wide herding in the Shanghai and Shenzhen stock exchanges for the 2000–2020 period, based on a classification of stocks as lucky/unlucky contingent on the presence of digits deemed numerologically lucky/unlucky in their tickers. We find no compelling evidence that herding is more pronounced in those superstitious stocks, as compared to the rest of the stock market. Both superstitious stock-types herd exclusively on high-volatility days and exhibit some pronounced patterns in up vs down markets; these effects are not significantly different from the behaviour of non-superstitious stocks, however. Similarly, herding in both superstitious stock-types is largely noise-driven, but the same effect is observed for non-superstitious stocks. The similarities in herding between superstitious and non-superstitious stocks suggest that numerological superstitions do not motivate significantly stronger herding in Chinese markets.

Building Stock Models for Embodied Carbon Emissions—A Review of a Nascent Field

Building stock modeling emerges as a critical tool in the strategic reduction of embodied carbon emissions, which is pivotal in reshaping the evolving construction sector. This review provides an overall view of modern methodologies in building stock modeling, homing in on the nuances of embodied carbon analysis in construction. Examining 23 seminal papers, our study delineates two primary modeling paradigms—top-down and bottom-up—each further compartmentalized into five innovative methods. This study points out the challenges of data scarcity and computational demands, advocating for methodological advancements that promise to refine the precision of building stock models. A groundbreaking trend in recent research is the incorporation of machine learning algorithms, which have demonstrated remarkable capacity, improving stock classification accuracy by 25% and urban material quantification by 40%. Furthermore, the application of remote sensing has revolutionized data acquisition, enhancing data richness by a factor of five. This review offers a critical examination of current practices and charts a course toward an environmentally prudent future. It underscores the transformative impact of building stock modeling in driving ecological stewardship in the construction industry, positioning it as a cornerstone in the quest for sustainability and its significant contribution toward the grand vision of an eco-efficient built environment.

De-noising classification method for financial time series based on ICEEMDAN and wavelet threshold, and its application

This paper proposes a classification method for financial time series that addresses the significant issue of noise. The proposed method combines improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and wavelet threshold de-noising. The method begins by employing ICEEMDAN to decompose the time series into modal components and residuals. Using the noise component verification approach introduced in this paper, these components are categorized into noisy and de-noised elements. The noisy components are then de-noised using the Wavelet Threshold technique, which separates the non-noise and noise elements. The final de-noised output is produced by merging the non-noise elements with the de-noised components, and the 1-NN (nearest neighbor) algorithm is applied for time series classification. Highlighting its practical value in finance, this paper introduces a two-step stock classification prediction method that combines time series classification with a BP (Backpropagation) neural network. The method first classifies stocks into portfolios with high internal similarity using time series classification. It then employs a BP neural network to predict the classification of stock price movements within these portfolios. Backtesting confirms that this approach can enhance the accuracy of predicting stock price fluctuations.

A Graph Neural Network Node Classification Application Model with Enhanced Node Association

This study combines the present stage of the node classification problem with the fact that there is frequent noise in the graph structure of the graph convolution calculation, which can lead to the omission of some of the actual edge relations between nodes and the appearance of numerous isolated nodes. In this paper, we propose the graph neural network model ENode-GAT for improving the accuracy of small sample node classification using the method of external referencing of similar word nodes, combined with Graph Convolutional Neural Network (GCN), Graph Attention Network (GAT), and the early stop algorithm. In order to demonstrate the applicability of the model, this paper employs two distinct types of node datasets for its investigations. The first is the Cora dataset, which is widely used in node classification at this time, and the second is a small-sample Stock dataset created by Eastern Fortune’s stock prospectus of the Science and Technology Board (STB). The experimental results demonstrate that the ENode-GAT model proposed in this paper obtains 85.1% classification accuracy on the Cora dataset and 85.3% classification accuracy on the Stock dataset, with certain classification advantages. It also verifies the future applicability of the model to the fields of stock classification, tender document classification, news classification, and government announcement classification, among others.

The Implementation of Value Investment Based on Various Indicators for the Building Materials Industry

With the advent of post COVID-19 era, value investing strategy has popularized again in the global stock markets as the changing economic conditions, rising interest rates and different risk appetites. Therefore, it is reasonable to know how to distinguish between value stocks and growth stocks before investing. This paper aims to examine the application of value investment strategies based on the indicators’ performance of five companies selected from the building materials industry. Besides, valuation metrics are derived from three primary dimensions, i.e., growth, profitability and value per unit of growth. This study first identifies the classification and recent performance of value stocks and then compares the financial indicators of companies with value stocks. According to the analysis, the suitable P/E range of value stocks is from 10 to 20, with returns beginning to rise in 2021. By means of this method (utilizes one indicator to identify value stocks), researchers engaged in the financial industry may discover more characteristics about them. Moreover, results also illustrate that value stocks with excellent indicators are more endurable in preventing outside shocks, whereas growth stocks can outperform in profitability as long as they possess ever-increasing revenue and EBITDA. Thus, value investing still remains profitable and practical in the real world.

An integrated framework for classification and selection of stocks for portfolio construction: Evidence from NSE, India

Investment extortion in the stock market is a crucial aspect considered by the investors. Therefore, investors implemented different strategies. This study was intended at constructing an investment portfolio (IP) of stocks within the NSE 100 listed companies of Non-parametric nature, fulfilling the basic premise of portfolio making that is, reducing risks while yielding an attractive return higher than any other instrument for the investors. Using DP omnibus test, the desired sample of companies following the non-normal distribution was achieved. Using financial beta, we have selected the outcome based on the nature of their ‘return’ and ‘risk'. We introduce TOPSIS (Technique for order of performance by similarity to ideal solution), a multi-criteria decision-making process (MCDM) to study the profitability of stocks, rank wise for each year, and finally, the Bayes portfolio model help to select the overall profitability associate with low risk for the construction of the portfolio.

Stock Market Analysis Using Time Series Relational Models for Stock Price Prediction

The ability to predict stock prices is essential for informing investment decisions in the stock market. However, the complexity of various factors influencing stock prices has been widely studied. Traditional methods, which rely on time-series information for a single stock, are incomplete as they lack a holistic perspective. The linkage effect in the stock market, where stock prices are influenced by those of associated stocks, necessitates the use of more comprehensive data. Currently, stock relationship information is mainly obtained through industry classification data from third-party platforms, but these data are often approximate and subject to time lag. To address this, this paper proposes a time series relational model (TSRM) that integrates time and relationship information. The TSRM utilizes transaction data of stocks to automatically obtain stock classification through a K-means model and derives stock relationships. The time series information, extracted using long short-term memory (LSTM), and relationship information, extracted with a graph convolutional network (GCN), are integrated to predict stock prices. The TSRM was tested in the Chinese Shanghai and Shenzhen stock markets, with results showing an improvement in cumulative returns by 44% and 41%, respectively, compared to the baseline, and a reduction in maximum drawdown by 4.9% and 6.6%, respectively.

Population estimate and inter-island movement of sperm whales, Physeter macrocephalus, in the Eastern Caribbean Sea

When a population extends across international boundaries, management becomes more complex. This is especially true within a confined multinational area such as the Caribbean Sea. The population size of sperm whales in the Eastern Caribbean is estimated and the inter-island movements of individuals are quantified using a database of 1,394 photographic identifications taken between 1984 and 2006 by several research groups. A total of 194 individual sperm whales were identified off the leeward coasts of the islands of Dominica, Guadeloupe, Grenada, St. Lucia and Martinique. Population size was estimated using two-component finite mixture models. About 145 (95% CI=94- 219) sperm whales used Lesser Antillean waters in 1995 and this population appears to be growing slowly. There are differences amongst the individuals in their probability of identification. Of all individuals, 57 (29.4%) were identified during more than one year between 1995 and 2006. Long-term reidentification of associated females suggests that social units may be using the area for periods of at least 11 years. Twenty seven confirmed matches were made between islands, the majority (92.6%) of which were between Guadeloupe and Dominica, although there were two longer movements by single individuals between Dominica and the islands of St. Lucia and Grenada. High reidentification rates within the Lesser Antilles and no matches with identifications from nearby seas suggest the population in the Eastern Caribbean Sea is small and quite isolated. As such, we recommend that management actions be taken on a multi-island basis for the Eastern Caribbean, by encouraging the ratification of the SPAW protocols and that the current stock classification for the North Atlantic be reconsidered.

FEATURES OF THE EFFECTIVE STOCK MANAGEMENT SYSTEM AT TRADE ENTERPRISES

The article examines the theoretical foundations of inventory management of a retail trade enterprise. An analysis of the classification of stocks was carried out. The scheme of formation of reserves at the enterprise was analyzed. The main stages of stoc

Enhancement Economic System Based-Graph Neural Network in Stock Classification

As a result of the integration of the stock industry into the entire international economic system, stock companies publish hundreds of prospectuses every second. The ability to quickly and accurately classify the companies and categories to which these data belong, as well as improve the performance of the economic system, has become the key to unlocking its corresponding value at this stage. In order to solve this problem, graph neural network techniques are used to accomplish the classification of stocks in the science and technology version, thus indirectly alleviating the enormous pressure on the economic system. In this study, to complete semi-supervised classification, we propose the PA-GCN model, which takes the lead in graph attention calculation of stock nodes and introduces the Elu activation function. Specifically, in this study, we constructed a stock dataset and implemented a dropout layer to prevent overfitting. The final results on the stock dataset and the publicly accessible Cora dataset demonstrate that this strategy may effectively improve the economic system and that the model has good performance. In the two dataset tests, classification accuracy can be attained at 81.69% and 81.2%, respectively. It also demonstrates the method’s viability for classifying stock nodes.

ВИРОБНИЧІ ЗАПАСИ: ЇХ ЕКОНОМІЧНА ПРИРОДА ТА РОЛЬ В ГОСПОДАРСЬКІЙ ДІЯЛЬНОСТІ ПІДПРИЄМСТВА

Production stocks are an integral part of the production process, and their sufficient quantity and effective use have a significant impact on the economic security of the enterprise. The inventory management system is inextricably linked with the accounting system. Accounting information is the basis for making strategic management decisions. And the possibility of using credentials is ensured by the qualitative properties of the information itself. The article analyzes dissertation works in which “inventories” were studied as an economic and accounting category. The research of the category “inventories” was carried out according to the directions: inventories (in general), production inventories, merchandise inventories, material inventories. It was established that the most popular area of research was production stocks, which were considered taking into account the sectoral characteristics of enterprises. In order to highlight the features that reveal the economic nature of production stocks, the interpretation and approaches to understanding their essence have been studied. Signs that identify stocks as production are: 1) used in production business processes; 2) transfer their cost to the manufactured product; 3) lose (or change) their shape during the production process; 4) are consumed completely during one operating cycle. An important role in scientific knowledge belongs to classification, which makes it possible to detail objects, to highlight connections between them. The article summarizes the views of Ukrainian scientists on the construction of the classification of production stocks. The expediency of their use in the accounting practice of enterprises has been determined. An alternative approach to the grouping of production stocks in the accounting system is proposed, with the allocation of classification features: by sources of income; for the purpose of use in economic activity; according to the evaluation method; according to ways of disposal. The classification is accounting, built through the prism of operations that take place with production stocks in the economic activity of the enterprise. The purpose of the classification is the reliable assessment of production stocks at the stages of their movement, the completeness of the display of operations in the enterprise’s accounting system.

Development of an Information System for the Classification of Warehouse Stocks

In modern conditions, there is an interest of managers in management technologies that improve the quality of the organization's work in various areas and, thus, contribute to the growth of the financial results of its activities. In this article presents a methodology for evaluating restrictions in logistics chains using intermodal transport. Based on scientific methods and consultations with experts, the methodology determines a set of potential limitations in the logistics chain and makes it possible to compare different variants of the implementation of logistics chains. Based on the definition of conditions, the methodology allows the selection of a suitable variant of the logistics chain with emphasis on the specific conditions of the evaluator. The methodology is processed in the form of a software tool, which allows its wide application in practice in the planning and selection of a suitable variant of the logistics chain with the entry of specific conditions.

Promoting Financial Market Development-Financial Stock Classification Using Graph Convolutional Neural Networks

According to surveys, one in seven people in China are involved in stock trading, and the role of stocks in the global economy is growing. In terms of the entire stock market, the Chinese market alone has over 4000 stocks. Faced with a chaotic and diverse assortment of stocks, it is necessary to categorize them. On the one hand, it can facilitate stock market research, and on the other, it can make it easier for stockholders to purchase shares. The graph convolutional neural network-based SK-GCN model developed in this paper delivers excellent results in the categorization of stock classes. This model employs two layers of convolutional layers and activation functions to effectively categorize stocks by incorporating external nodes to expand stock features and drawing inspiration from short text classification. This strategy is highly innovative and produces promising outcomes. In this paper, we constructed the dataset by crawling the information of all stocks listed on the GEM of Oriental Fortune website. We achieved an accuracy of 83.04% and a macro-F1 value of 0.8303 under the assumption of small sample training, and its classification effect is significantly superior to other classification models.

Performance of Social Pillar-Based Portfolio in Developing Capital Market

Research Question: This study examined the preconditions and efficiency of socially responsible investing (SRI) in the developing capital market, specifically the Belgrade Stock Exchange (BSE). Motivation: Considering the increasing trend of SRI (GSIA, 2020) and importance of information on corporate social responsibility (CSR) to investors (Miralles‐Quiros, Miralles‐Quiros, & Arraiano, 2017), especially on social issues (Giese, Nagy, & Lee, 2021), we explored the influence of applying the social criteria in asset selection on investment portfolio performance at the BSE. This study builds on the existing literature that is mostly focused on developed capital markets of Europe, the United States and Canada (Von Wallis & Klein, 2015) by analysing the issue of SRI in the developing market. The provided setup for socially driven portfolio structuring based on market trends and social performance disclosure proved to be efficient in the long-term. Idea: The core idea of this paper was to analyse the terms for SRI and empirically evaluate the performance of social pillar-based portfolio on the BSE in order to provide evidence to support the trend of SRI in developing markets. The structure of the portfolios was set using the best-in-class strategy, while the classes were determined on the basis of the stocks’ return trends. Data: The analysis was conducted using trading data and information from financial and non-financial reports of the companies listed on the BSE. Tools: Cluster analysis was used for classification of stocks, while performances of portfolios were evaluated implementing return, volatility and risk-adjusted measures. Findings: The social pillar-based portfolio outperformed the conventional one and benchmarking indices in the observed five-year period. However, mixed results were obtained in the short-term indicating that specific effects of CSR practice on financial performance of the companies in observed developing market could still be obscured. Contribution: This paper expands the existing research related to SRI in the developing markets and offers practical recommendations for potential socially conscious investors.

Study on the Pakistan stock market using a new stock crisis prediction method.

A Stock market collapse occurs when stock prices drop by more than 10% across all main indexes. Predicting a stock market crisis is difficult because of the increased volatility in the stock market. Stock price drops can be triggered by a variety of factors, including corporate results, geopolitical tensions, financial crises, and pandemic events. For scholars and investors, predicting a crisis is a difficult endeavor. We developed a model for the prediction of stock crisis using Hybridized Feature Selection (HFS) approach. Firstly, we went for the suggestion of the HFS method for the removal of stock’s unnecessary financial attributes. The Naïve Bayes approach, on the other hand, is used for the classification of strong fundamental stocks. In the third step, Stochastic Relative Strength Index (StochRSI) is employed to identify a stock price bubble. In the fourth step, we identified the stock market crisis point in stock prices through moving average statistics. The fifth is the prediction of stock crises by using deep learning algorithms such as Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM). Root Mean Square Error (RMSE), Mean Squared Error (MSE) and Mean Absolute Error (MAE) are implemented for assessing the performance of the models. The HFS-based GRU technique outperformed the HFS-based LSTM method to anticipate the stock crisis. To complete the task, the experiments used Pakistan datasets. The researchers can look at additional technical factors to forecast when a crisis would occur in the future. With a new optimizer, the GRU approach may be improved and fine-tuned even more.

Bank Characteristics and Dividend Payout of Selected Commercial Banks in Kenya

Dividend payout for Tier I banks in Kenya has remained relatively stagnant over the years even with improved financial performance. Central Bank of Kenya reports show that Kenya’s banking sector is very profitable with the average return on asset being about 2.6 per cent for the years between 2016-2021. Thus, this study sought to determine the effect of bank characteristics on dividend payout of Tier I banks. The study specifically aimed at objectively quantifying effect of bank size, liquidity, and profitability on dividend payout. Target population was all nine (9) Tier I banks listed at the Nairobi Securities Exchanges (NSE). Secondary data was acquired from audited and published financial reports of the nine (9) banks for the period between 2016-2021 using document review guide. Descriptive analysis and panel regression were applied for data testing. Independent variables were bank size, liquidity, and profitability while dependent variable was dividend payout. Market capitalization was used as a measure for bank size, book-to-market value as a measure for liquidity and earnings per share as a measure for profitability. Results indicated liquidity had a small negative statistically significant effect on dividend payout while both bank size and profitability had negative statistically insignificant effect on dividend payout. The study thus determined that bank characteristics had insignificant effect on dividend payout for Tier I banks. The study recommends that Central Bank of Kenya consider reducing Cash Reserve Ratio (CRR) and NSE consider an alternative stock classification system which will categorizes stocks in same sector based on size which will give a clear insight of the risk-return trade off characteristics at the NSE. Keywords: Dividend Payout, Commercial Banks, Bank Characteristics, Market Capitalization, Book-to-Market value, Earnings per Share, Kenya.

Effective Fuzzy System for Qualifying the Characteristics of Stocks by Random Trading

Trading strategies can be divided into two categories, i.e., those with momentum characteristic and those that appear contrarian. The characteristics of trading strategies have been widely studied; however, there has been relatively little work on the characteristics of stocks. Furthermore, there is no standard approach to the classification of stocks in terms of momentum and contrarian. This article presents a fuzzy momentum contrarian uncertain characteristic system for the classification and quantification of stock characteristics. Random trading, stop-loss, and take-profit mechanisms are first used to identify characteristics, and then, a novel profitability index with a type-2 fuzzy set module is used to quantify them. In the experiments, 41 stocks on the Taiwan 50 index were deemed suitable for momentum strategies, whereas nine stocks were deemed suitable for contrarian strategies. An uphill relationship between profitability index and trading performance is observed, which produced correlation coefficients of 0.148–0.539 and a classification accuracy of 52.0–60.0%. However, the proposed system greatly improved classification performance, resulting in correlation coefficients of 0.572–0.722 with an accuracy of 63.6–84.5%. In the real-world application, the proposed system outperforms the benchmark among all datasets and increases the profitability by 1.5 times on the Taiwan 50 dataset. These results clearly demonstrate the efficiency of the proposed system in the quantification and classification of stocks suited to momentum- and contrarian-type trading strategies and also in the real-world applications.