Influential Stocks Research Articles

Forecasting gold price using machine learning methodologies

This study investigates the potential of advanced Machine Learning (ML) methodologies to predict fluctuations in the price of gold. The study employs data from leading global stock indices, the S&P500 VIX volatility index, major commodity futures, and 10-year bond yields from the US, Germany, France, and Japan. Lagged values of these features up to 10 previous days are also used. Four machine learning models are used: Random Forest, Gradient Boosted Regression Trees (GBRT), and Extreme Gradient Boosting (XGBoost), to forecast future gold prices. The study finds that the most influential stocks indices for prediction are one-day lagged data of ASX, S&P500, TA35, IBEX, and AEX, as well as U.S. and Japan bonds yields and delayed data of gas and silver. Furthermore, the study's models identify that one-day lagged VIX score and our VIX dummy variable have a significant impact on gold price, indicating that economic uncertainty affects gold prices. The results suggest that incorporating various financial indicators and moving averages can be a powerful tool for predicting future gold prices. GBRT and XGBoost can be valuable models for making informed decisions about gold investments.

Causal networks reveal the response of Chinese stocks to modern crises

Changes in stock markets impact the optimal policies for governments, businesses, and even individual households. Causal networks summarizing pairwise directed dependencies between stocks can be used to characterize these changes, as well as to identify influential stocks whose variations have unusually strong effects on the movements of other stocks. In this paper, we apply Granger causality tests in sliding windows to build directed causal networks representing the interactions of stock markets in the world’s second largest economy, China, during recent economic, trade and epidemiological crises. We propose identifying influential stocks by using distance correlation and surrogate tests, rather than linear Pearson correlation and asymptotic distributions, to quantify the strength of general nonlinear dependencies between network centrality and financial indicators. We find that, at the onset of a crisis, influential stocks gain their position by themselves being attentive to the stock market. As the crisis progresses, the stock market steadily adjusts to give a stronger leadership role to influential stocks at the expense of non-influential stocks. Interestingly, the industries to which influential stocks belong are closely related to the nature of crisis events. Finally, we show that industries which contained influential stocks represented better investments.

Identification of the most influential stocks in financial networks

In the financial market, the stock association network can be used to describe the correlations between stock prices. The rise and fall of stock prices and their mutual influence can be described by a reversible cascading failure process. In the reversible spreading processes, the influence of fluctuation of an individual stock price on companies, industries and even the financial markets can be regarded as the influence of the individual stock in the financial networks. In this paper, based on the stock price association networks of nine sectors in China A-stock market, we studied the identification of the most influential nodes in the reversible spreading processes. It is found that due to the high proportion of core nodes in the stock association networks, the k-coreness centrality can not accurately measure the influence of these nodes. A large number of simulations show that the number of out-leaving edges of neighbor nodes can better evaluate the influence of a node in the spreading processes. Then a node strength centrality and s-coreness centrality based on link importance are developed to measure the spreading influence of nodes. Compared with degree centrality and k-coreness centrality, the node strength and s-coreness based on strength have a better performance in identifying the most influential nodes. The ranking algorithm considering the structures and dynamics of local neighbors can further improve the ranking performance. The proposed framework and ranking method open up a new idea in identifying the most influential stocks in financial networks.

Dynamic analysis of influential stocks based on conserved networks

Characterizing temporal evolution of stock markets is a fundamental and challenging problem. The literature on analyzing the dynamics of the markets has focused so far on macro measures with less predictive power. This paper addresses this issue from a micro point of view. Given an investigating period, a series of stock networks are constructed first by the moving-window method and the significance test of stock correlations. Then, several conserved networks are generated to extract different backbones of the market under different states. Finally, influential stocks and corresponding sectors are identified from each conserved network, based on which the longitudinal analysis is performed to describe the evolution of the market. The application of the above procedure to stocks belonging to Standard and Pool’s 500 Index from January 2006 to April 2010 recovers the 2008 financial crisis from the evolutionary perspective.

Phase separation and scaling in correlation structures of financial markets

Financial markets, being spectacular examples of complex systems, display rich correlation structures among price returns of different assets. The correlation structures change drastically, akin to critical phenomena in physics, as do the influential stocks (leaders) and sectors (communities), during market events like crashes. It is crucial to detect their signatures for timely intervention or prevention. Here we use eigenvalue decomposition and eigen-entropy, computed from eigenvector centralities of different stocks in the cross-correlation matrix, to extract information about the disorder in the market. We construct a ‘phase space’, where different market events (bubbles, crashes, etc) undergo phase separation and display order–disorder movements. An entropy functional exhibits scaling behavior. We propose a generic indicator that facilitates the continuous monitoring of the internal structure of the market—important for managing risk and stress-testing the financial system. Our methodology would help in understanding and foreseeing tipping points or fluctuation patterns in complex systems.

Transfer entropy calculation for short time sequences with application to stock markets

We investigate the estimation of transfer entropy (TE) for short time sequences by correlation-dependent balanced estimation of diffusion entropy employed in the transfer entropy (CBEDETE) method and the normal transfer entropy (NTE) method. Our finding shows that the CBEDETE method is more effective than the NTE method on TE calculation for short time series. Based on this conclusion, we use 38 important stock market indices from 4 continents to create successive financial networks with 10∼60-day windows and 1-day step by the CBEDETE method. By extracting the evolution characteristics of out-/in-degree of stock networks, we obtain the most influential stocks RTS, KOSPI, PSI, NIKKE and AORD of Europe, Asia and Oceania and the most influenced stocks IBOVESPA, NYSE, NASD and MERV of America. Finally, by monitoring the ratio of link numbers of each network and smoothing the curves, we find an interesting result that almost all effective peaks in the smoothed ratio curves are prior to the financial crises, such as the global financial crisis in 2008, China’s stock market crash in 2015, etc.

An empirical evaluation of the influential nodes for stock market network: Chinese A-shares case

This paper aims to rank the influential nodes for Chinese A-share market by employing complex network analysis approach. More than one hundred directed weighted stock market networks are constructed by the methods of Engle-Granger test, Granger Causality test and moving window among 847 stocks for the time period from January 2006 to June 2019. Then the identification of important nodes is investigated by using weighted LeaderRank algorithm. The results show that: (i) the average clustering coefficient and global efficiency increase sharply in the run-up to, and during the financial crisis, and decline rapidly afterwards. (ii) 66.98% of stock market networks have scale-free property. (iii) the influential companies are generally large-capitalization companies. In addition, an interesting finding is that, top 3 influential stocks are high price stocks which are so called “hundred shares” by Chinese investors.

Shock Diffusion Analysis for a Directed Market Network Constructed with Use of the Risk Measure ΔCoVaR

This paper studies a complex network formed as a directed graph in which nodes represent the companies traded on the NYSE or NASDAQ while directed edges represent a connectedness measure between the financial assets. The directed edge weight between any two nodes is calculated with use of the value of ΔCoVaR, one of the most popular systemic risk measures proposed by M. Brunnermeier and T. Adrian in 2011. The value of ΔCoVaR measures the relationship between any two assets and is based not only on the yields of the assets, but take into account the mutual effect of its performance. In contrast with correlation coefficient, ΔCoVaR is asymmetric. The analysis is focused on the static model of the ΔCoVaR estimation. Moreover, this paper uses statistical testing procedures to assess the significance of the findings and interpretations based on this co-risk measure. We examine the intrinsic properties and regularities of stock market analyzing the directed complex network with more than 3700 stocks as nodes which have been traded on the NYSE and NASDAQ in recent years. We connect any two stock with a directed edge if the value of the corresponding ΔCoVaR is statistically significant and its normalized value is greater than a given threshold. We discuss both out-degree and in-degree distributions and find essential vertices in the network, which represent the leading stocks. We demonstrate that the network follows the power-law distribution and behaves scale-free. Moreover, we address the problem of finding influential spreaders, i.e. companies which are more likely to spread negative shocks in a large part of the network. In this paper we use three different measures (closeness centrality, betweenness centrality, PageRank) to determine the most influential stocks in the directed market graph.

Identifying influential nodes based on fluctuation conduction network model

Identifying influential stocks and determining the diffusion mechanism in a complex stock network are helpful for recognizing and avoiding the risk of a financial crisis. We define the influence of a stock according to the price fluctuation that it triggers in other stocks. Meanwhile, we propose the fluctuation conduction network (FCN) model, a novel dynamic model that can provide an econometrics basis. Through the data of the closing price, we analyze the price fluctuation influence capacity (PFIC) of stocks. First, we test the validity of our method and compare the PFIC of stocks with other features of stocks; second, we rank the stocks and make an empirical analysis of the influential stocks. From this, we find the following: (1) The closeness centrality has a tight correlation with the PFIC. (2) From the individual stock level, the 10 most influential stocks in the giant component of the stock network have strong leadership and reputations in China. (3) From the industry sector level, “Finance” and “Electric, thermal, gas, water production and supply” are the most influential sectors. (4) Most stocks reach their maximum influence range at step 3 of the price conduction.

A Network Analysis of the Stock Market in Malaysia, Singapore and Indonesia

In this study, we investigate the stock market network among the stocks traded in Malaysia, Singapore and Indonesia using the minimal spanning tree approach. Based on the market capitalization, the monthly adjusted closing prices from 2016 until 2017 of 10 companies for each stock market are chosen to construct the network, and the most influential stocks between Malaysia, Singapore and Indonesia stock markets are identified. Findings of this study show that 3 out of 30 companies are identified as the most influential in the Malaysia, Singapore and Indonesia stock market.

Network Topology of Renewable Energy Sector in Stock Exchange

In today's global economy, the most prominent position clean energy is basically viewed as the highest-speed growing branch. Sustainable energy, perpetual climate change, and technological advancements are the reasons from which this foreground position results from. Regarding the debate of effects of pollution and the importance of the alternative fuels, the more awareness people improve, the more interested they are to invest in clean energy. This paper brings to a focus the inspection of clean energy and the way any market would analysis the influential stocks which have an effect on the other. In this regard, correlation network approach has extensively applied to explore the financial markets properties. In econophysics, technical topology network is defined for analyzing the interaction between stocks to find significant implications to optimize the portfolio. Network topology shows the physical layout of a network. It refers to the way in which per stock is located and interconnected to other stocks. This study analyse the topological properties of network on a set of 62 stocks in renewable energy companies from 30th February 2015 to 3th March 2016 to aid to the interpretation of relationships in the network structure and find influencing stocks.

A new weighting-scheme for equity indexes

This paper proposes a novel methodology for computing a cross capitalization-weighted index, coined CCWI, that characterizes the most influential stocks that drive the index. The methodology, based on the factor analysis approach combined with the Equi-correlation model of Engle and Kelly (2012), encapsulates all the main information to replicate any given large equity stock index. We build a proxy that tracks accurately the S&P 500 while reducing the cost of duplication for large equity indexes with the methodology combining the PCA approach and the DECO model. We provide an application to the S&P 500 by constructing an aggregate stock index composed of the most influential stocks. The analysis reveals that the CCWI is useful for asset and risk management. Robustness checks expand the equity index universe to MIB, TSX, CAC, DAX, FTSE, NIKKEI, HSI and DJIA, both during full- and sub-periods.

Investigating the Influence Relationship Models for Stocks in Indian Equity Market: A Weighted Network Modelling Study.

The socio-economic systems today possess high levels of both interconnectedness and interdependencies, and such system-level relationships behave very dynamically. In such situations, it is all around perceived that influence is a perplexing power that has an overseeing part in affecting the dynamics and behaviours of involved ones. As a result of the force & direction of influence, the transformative change of one entity has a cogent aftereffect on the other entities in the system. The current study employs directed weighted networks for investigating the influential relationship patterns existent in a typical equity market as an outcome of inter-stock interactions happening at the market level, the sectorial level and the industrial level. The study dataset is derived from 335 constituent stocks of ‘Standard & Poor Bombay Stock Exchange 500 index’ and study period is 1st June 2005 to 30th June 2015. The study identifies the set of most dynamically influential stocks & their respective temporal pattern at three hierarchical levels: the complete equity market, different sectors, and constituting industry segments of those sectors. A detailed influence relationship analysis is performed for the sectorial level network of the construction sector, and it was found that stocks belonging to the cement industry possessed high influence within this sector. Also, the detailed network analysis of construction sector revealed that it follows scale-free characteristics and power law distribution. In the industry specific influence relationship analysis for cement industry, methods based on threshold filtering and minimum spanning tree were employed to derive a set of sub-graphs having temporally stable high-correlation structure over this ten years period.

A network approach to portfolio selection

Abstract In this study, a financial market is conceived as a network where the securities are nodes and the links account for returns' correlations. We theoretically prove the negative relationship between the centrality of assets in this financial market network and their optimal weights under the Markowitz framework. Therefore, optimal portfolios overweight low-central securities to avoid the large variances that result when highly influential stocks are included in the investor's opportunity set. Next, we empirically investigate the major financial and market determinants of stock's centralities. The evidence indicates that highly central nodes tend to coincide with older, larger-cap, cheaper and financially riskier securities. Finally, we explore by means of in-sample and out-of-sample analysis the extent to which the structure of the stock market network can be employed to improve the portfolio selection process. We propose a network-based investment strategy that outperforms well-known benchmarks while presenting positive and significant Carhart alphas. The major contribution of the paper is to employ the financial market network as a useful device to improve the portfolio selection process by targeting a group of assets according to their centrality.

A Network Approach to Portfolio Selection

In this study a financial market is conceived as a network where the securities are nodes and the links account for returns’ correlations. We theoretically prove the negative relationship between the centrality of assets in this financial market network and their optimal weights under the Markowitz framework. Therefore, optimal portfolios overweight low-central securities to avoid the large variances that result when highly influential stocks are included in the investor’s opportunity set. Next, we empirically investigate the major financial and market determinants of stock’s centralities. The evidence indicates that highly central nodes tend to coincide with older, larger-cap, cheaper and financially riskier securities. Finally, we explore by means of in-sample and out-of-sample analysis the extent to which the structure of the stock market network can be employed to improve the portfolio selection process. We propose a network-based investment strategy that outperforms well-known benchmarks while presenting positive and significant Carhart alphas. The major contribution of the paper is to employ the financial market network as a useful device to improve the portfolio selection process by targeting a group of assets according to their centrality.

Dominating Clasp of the Financial Sector Revealed by Partial Correlation Analysis of the Stock Market

What are the dominant stocks which drive the correlations present among stocks traded in a stock market? Can a correlation analysis provide an answer to this question? In the past, correlation based networks have been proposed as a tool to uncover the underlying backbone of the market. Correlation based networks represent the stocks and their relationships, which are then investigated using different network theory methodologies. Here we introduce a new concept to tackle the above question—the partial correlation network. Partial correlation is a measure of how the correlation between two variables, e.g., stock returns, is affected by a third variable. By using it we define a proxy of stock influence, which is then used to construct partial correlation networks. The empirical part of this study is performed on a specific financial system, namely the set of 300 highly capitalized stocks traded at the New York Stock Exchange, in the time period 2001–2003. By constructing the partial correlation network, unlike the case of standard correlation based networks, we find that stocks belonging to the financial sector and, in particular, to the investment services sub-sector, are the most influential stocks affecting the correlation profile of the system. Using a moving window analysis, we find that the strong influence of the financial stocks is conserved across time for the investigated trading period. Our findings shed a new light on the underlying mechanisms and driving forces controlling the correlation profile observed in a financial market.

Greek market efficiency and its international integration

Political, economic and legal risks are among the causes of market inefficiency and the consequent under-development of financial markets. To further the understanding of the factors affecting market development, this study evaluates the Athens Stock Exchange (ASE). The Greek market provides a unique opportunity to isolate market efficiency as a factor in market development. Since its membership to the European Union (EU) in 1981, political and legal risks in the Greek market are similar to those of the other EU member countries such as the U.K., Germany and France. Greece's inclusion in the Eurozone in 2000 has eliminated many of the economic risks. The unrealized potential of the ASE is therefore questioned. Considering the relatively small number of stocks in the ASE, market level analysis is potentially inappropriate: studies may be rejecting the ASE's efficiency due to irregularities in a few influential stocks. Thus, this study analyzes the efficiency of the ASE by evaluating the market's, as well as individual stocks’, returns. A well documented anomaly for the ASE, the day-of-the-week effect, is evaluated as are return predictability tests including a runs test, causality from other markets, and causality from liquidity. Both on the market level and on the individual level, evidence of inefficiencies are found. Based on the evidence that about 94% of Greek stocks’ returns are Granger-caused by at least one foreign market, it is concluded that the Greek market lacks the appeal for international diversification. Overall, the ASE's unrealized potential is blamed on lingering market inefficiencies and especially on its causal relationship with international markets.