Spread of risk across financial markets: better to invest in the peripheries

Global motion filtered nonlinear mutual information analysis: Enhancing dynamic portfolio strategies

The complex financial networks, with their nonlinear nature, often exhibit considerable noises, inhibiting the analysis of the market dynamics and portfolio optimization. Existing studies mainly focus on the application of the global motion filtering on the linear matrix to reduce the noise interference. To minimize the noise in complex financial networks and enhance timing strategies, we introduce an advanced methodology employing global motion filtering on nonlinear dynamic networks derived from mutual information. Subsequently, we construct investment portfolios, focusing on peripheral stocks in both the Chinese and American markets. We utilize the growth and decline patterns of the eigenvalue associated with the global motion to identify trends in collective market movement, revealing the distinctive portfolio performance during periods of reinforced and weakened collective movements and further enhancing the strategy performance. Notably, this is the first instance of applying global motion filtering to mutual information networks to construct an investment portfolio focused on peripheral stocks. The comparative analysis demonstrates that portfolios comprising peripheral stocks within global-motion-filtered mutual information networks exhibit higher Sharpe and Sortino ratios compared to those derived from global-motion-filtered Pearson correlation networks, as well as from full mutual information and Pearson correlation matrices. Moreover, the performance of our strategies proves robust across bearish markets, bullish markets, and turbulent market conditions. Beyond enhancing the portfolio optimization, our results provide significant potential implications for diverse research fields such as biological, atmospheric, and neural sciences.

Enhancing portfolio management using artificial intelligence: literature review

Building an investment portfolio is a problem that numerous researchers have addressed for many years. The key goal has always been to balance risk and reward by optimally allocating assets such as stocks, bonds, and cash. In general, the portfolio management process is based on three steps: planning, execution, and feedback, each of which has its objectives and methods to be employed. Starting from Markowitz's mean-variance portfolio theory, different frameworks have been widely accepted, which considerably renewed how asset allocation is being solved. Recent advances in artificial intelligence provide methodological and technological capabilities to solve highly complex problems, and investment portfolio is no exception. For this reason, the paper reviews the current state-of-the-art approaches by answering the core question of how artificial intelligence is transforming portfolio management steps. Moreover, as the use of artificial intelligence in finance is challenged by transparency, fairness and explainability requirements, the case study of post-hoc explanations for asset allocation is demonstrated. Finally, we discuss recent regulatory developments in the European investment business and highlight specific aspects of this business where explainable artificial intelligence could advance transparency of the investment process.

Centrality measures in psychological networks: A simulation study on identifying effective treatment targets

The network theory of psychopathology suggests that symptoms in a disorder form a network and that identifying central symptoms within this network might be important for an effective and personalized treatment. However, recent evidence has been inconclusive. We analyzed contemporaneous idiographic networks of depression and anxiety symptoms. Two approaches were compared: a cascade-based attack where symptoms were deactivated in decreasing centrality order, and a normal attack where symptoms were deactivated based on original centrality estimates. Results showed that centrality measures significantly affected the attack's magnitude, particularly the number of components and average path length in both normal and cascade attacks. Degree centrality consistently had the highest impact on the network properties. This study emphasizes the importance of considering centrality measures when identifying treatment targets in psychological networks. Further research is needed to better understand the causal relationships and predictive capabilities of centrality measures in personalized treatments for mental disorders.

Market return spillover from the US to the Asia-Pacific Countries: The Role of Geopolitical Risk and the Information & Communication Technologies

This study examines the market return spillovers from the US market to 10 Asia-Pacific stock markets, accounting for approximately 91 per cent of the region's GDP from 1991 to 2022. Our findings indicate an increased return spillover from the US stock market to the Asia-Pacific stock market over time, particularly after major global events such as the 1997 Asian and the 2008 global financial crises, the 2015 China stock market crash, and the COVID-19 pandemic. The 2008 global financial crisis had the most substantial impact on these events. In addition, the findings also indicate that US economic policy uncertainty and US geopolitical risk significantly affect spillovers from the US to the Asia-Pacific markets. In contrast, the geopolitical risk of Asia-Pacific countries reduces these spillovers. The study also highlights the significant impact of information and communication technologies (ICT) on these spillovers. Given the increasing integration of global financial markets, the findings of this research are expected to provide valuable policy implications for investors and policymakers.

Central psychological symptoms from a network analysis of patients with anxiety, somatoform or personality disorders before psychotherapy

BACKGROUND

Cross-sectional network analysis examines the relationships between symptoms to explain how they constitute disorders. Up to now, research focuses mostly on depression, posttraumatic stress disorder, and rarely assesses larger networks of various symptoms measured with instruments independent of classifications. Studies on large groups of psychotherapy patients are also rare.

METHODS

Analyzing triangulated maximally filtered graph (TMFG) networks of 62 psychological symptoms reported by 4616 consecutive nonpsychotic adults in 1980-2015.

RESULTS

Case-dropping and nonparametric bootstrap proved the accuracy, stability and reliability of networks in patients' sex-, age-, and time of visit divided subgroups. Feeling that others are prejudiced against the patient was the most central symptom, followed by catastrophic fears, feeling inferior and underestimated. Sadness, panic, and sex-related complaints were less central than we expected. All analysed symptoms were connected, and we found only small sex-related differences between subsamples' networks. No differences were observed for time of visit and age of patients.

LIMITATION

Analyses were cross-sectional and retrospective, not allowing examination of directionality or causality. Further, data are at the between-person level; thus, it is unknown whether the network remains constant for any person over time. One self-report checklist and building binary network method may bias results. Our results indicate how symptoms co-occured before psychotherapy, not longitudinally. Our sample included public university hospital patients, all White-Europeans, predominantly females and university students.

CONCLUSIONS

Hostile projection, catastrophic fears, feeling inferior and underestimated were the most important psychological phenomena reported before psychotherapy. Exploring these symptoms would possibly lead to enhancement of treatments.

Laplacian Spectra of Persistent Structures in Taiwan, Singapore, and US Stock Markets

An important challenge in the study of complex systems is to identify appropriate effective variables at different times. In this paper, we explain why structures that are persistent with respect to changes in length and time scales are proper effective variables, and illustrate how persistent structures can be identified from the spectra and Fiedler vector of the graph Laplacian at different stages of the topological data analysis (TDA) filtration process for twelve toy models. We then investigated four market crashes, three of which were related to the COVID-19 pandemic. In all four crashes, a persistent gap opens up in the Laplacian spectra when we go from a normal phase to a crash phase. In the crash phase, the persistent structure associated with the gap remains distinguishable up to a characteristic length scale ϵ* where the first non-zero Laplacian eigenvalue changes most rapidly. Before ϵ*, the distribution of components in the Fiedler vector is predominantly bi-modal, and this distribution becomes uni-modal after ϵ*. Our findings hint at the possibility of understanding market crashs in terms of both continuous and discontinuous changes. Beyond the graph Laplacian, we can also employ Hodge Laplacians of higher order for future research.

Network analysis of body-related complaints in patients with neurotic or personality disorders referred to psychotherapy

Background

Psychopathology theory and clinical practice require the most complex knowledge about patients' complaints. In patients seeking for psychotherapy, body-related symptoms often complicate treatment.

Aim

This study aimed at examining connections between body-related symptoms, and identification of symptoms which may be responsible for emergency and sustaining of anxiety, somatoform and personality disorders with the use of network analysis.

Methods

In our retrospective research we used data from a sample of 4616 patients of the Department of Psychotherapy, University Hospital in Cracow, diagnosed with anxiety, somatoform or personality disorders. We constructed the Triangulated Maximally Filtered Graph (TMFG) networks of 44 somatoform symptoms endorsed in the symptom checklist "O" (SCL-O) and identified the most central symptoms within the network for all patients and in subgroups of women vs. men, older vs. younger, and diagnosed in 1980-2000 vs. 2000-2015. We used bootstrap to determine the accuracy and stability of five networks' parameters: strength, expected influence, eigenvector, bridge strength and hybrid centrality.

Results

The most central symptoms within the overall network, and in six subnetworks were dyspnea and migratory pains. We identified some gender-related differences, but no differences were observed for the age and time of diagnosis.

Conclusions

Self-reported dyspnea and migratory pains are potential important targets for treatment procedures.

The effect of self-organizing map architecture based on the value migration network centrality measures on stock return. Evidence from the US market

Complex financial systems are the subject of current research interest. The notion of complex network is used for understanding the value migration process. Based on the stock data of 498 companies listed in the S&P500, the value migration network has been constructed using the MST-Pathfinder filtering network approach. The analysis covered 471 companies included in the largest component of VMN. Three methods: (i) complex networks; (ii) artificial neural networks and (iii) MARS regression, are developed to determine the effect of network centrality measures and rate of return on shares. A network-based data mining analysis has revealed that the topological position in the value migration network has a pronounced impact on the stock's returns.

Information sharing among cryptocurrencies: Evidence from mutual information and approximate entropy during COVID-19

In this paper, we use mutual information approach to investigate the information sharing between cryptocurrencies during the COVID-19 crisis. We also use the approximate entropy to study their dynamics before COVID-19 and during the pandemic. Results from the mutual information measure indicate a rise in information sharing and ordering in the cryptocurrency markets in the pandemic period, while the evidence from the approximate entropy estimates indicates a rise in randomness during the COVID-19 period. Our results provide new insights on the information sharing of cryptocurrencies and their reaction to shocks such as the COVID-19 pandemic.

Stock market network based on bi-dimensional histogram and autoencoder

In this study, we propose a deep learning related framework to analyze S&P500 stocks using bi-dimensional histogram and autoencoder. The bi-dimensional histogram consisting of daily returns of stock price and stock trading volume is plotted for each stock. Autoencoder is applied to the bi-dimensional histogram to reduce data dimension and extract meaningful features of a stock. The histogram distance matrix for stocks are made of the extracted features of stocks, and stock market network is built by applying Planar Maximally Filtered Graph(PMFG) algorithm to the histogram distance matrix. The constructed stock market network represents the latent space of bi-dimensional histogram, and network analysis is performed to investigate the structural properties of the stock market. we discover that the structural properties of stock market network are related to the dispersion of bi-dimensional histogram. Also, we confirm that the autoencoder is effective in extracting the latent feature of the bi-dimensional histogram. Portfolios using the features of bi-dimensional histogram network are constructed and their investment performance is evaluated in comparison with other benchmark portfolios. We observe that the portfolio consisting of stocks corresponding to the peripheral nodes of bi-dimensional histogram network shows better investment performance than other benchmark stock portfolios.

Smart network based portfolios

In this article we deal with the problem of portfolio allocation by enhancing network theory tools. We propose the use of the correlation network dependence structure in constructing some well-known risk-based models in which the estimation of the correlation matrix is a building block in the portfolio optimization. We formulate and solve all these portfolio allocation problems using both the standard approach and the network-based approach. Moreover, in constructing the network-based portfolios we propose the use of three different estimators for the covariance matrix: the sample, the shrinkage toward constant correlation and the depth-based estimators . All the strategies under analysis are implemented on three high-dimensional portfolios having different characteristics. We find that the network-based portfolio consistently performs better and has lower risk compared to the corresponding standard portfolio in an out-of-sample perspective.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s10479-022-04675-7.

A survey of the application of graph-based approaches in stock market analysis and prediction

Graph-based approaches are revolutionizing the analysis of different real-life systems, and the stock market is no exception. Individual stocks and stock market indices are connected, and interesting patterns appear when the stock market is considered as a graph. Researchers are analyzing the stock market using graph-based approaches in recent years, and there is a need to survey those works from multiple perspectives. We discuss the existing graph-based works from five perspectives: (i) stock market graph formulation, (ii) stock market graph filtering, (iii) stock market graph clustering, (iv) stock movement prediction, and (v) portfolio optimization. This study contains a concise description of major techniques and algorithms relevant to graph-based approaches for the stock market.

Understanding Changes in the Topology and Geometry of Financial Market Correlations during a Market Crash

In econophysics, the achievements of information filtering methods over the past 20 years, such as the minimal spanning tree (MST) by Mantegna and the planar maximally filtered graph (PMFG) by Tumminello et al., should be celebrated. Here, we show how one can systematically improve upon this paradigm along two separate directions. First, we used topological data analysis (TDA) to extend the notions of nodes and links in networks to faces, tetrahedrons, or k-simplices in simplicial complexes. Second, we used the Ollivier-Ricci curvature (ORC) to acquire geometric information that cannot be provided by simple information filtering. In this sense, MSTs and PMFGs are but first steps to revealing the topological backbones of financial networks. This is something that TDA can elucidate more fully, following which the ORC can help us flesh out the geometry of financial networks. We applied these two approaches to a recent stock market crash in Taiwan and found that, beyond fusions and fissions, other non-fusion/fission processes such as cavitation, annihilation, rupture, healing, and puncture might also be important. We also successfully identified neck regions that emerged during the crash, based on their negative ORCs, and performed a case study on one such neck region.

The interdependency structure in the Mexican stock exchange: A network approach

Our goal in this paper is to study and characterize the interdependency structure of the Mexican Stock Exchange (mainly stocks from Bolsa Mexicana de Valores) for the period 2000-2019 which provide a one shot big-picture panorama. To this end, we estimate correlation/concentration matrices from different models and then compute centralities and modularity from network theory.

Network Models to Enhance Automated Cryptocurrency Portfolio Management

The usage of cryptocurrencies, together with that of financial automated consultancy, is widely spreading in the last few years. However, automated consultancy services are not yet exploiting the potentiality of this nascent market, which represents a class of innovative financial products that can be proposed by robo-advisors. For this reason, we propose a novel approach to build efficient portfolio allocation strategies involving volatile financial instruments, such as cryptocurrencies. In other words, we develop an extension of the traditional Markowitz model which combines Random Matrix Theory and network measures, in order to achieve portfolio weights enhancing portfolios' risk-return profiles. The results show that overall our model overperforms several competing alternatives, maintaining a relatively low level of risk.

Mutual information based stock networks and portfolio selection for intraday traders using high frequency data: An Indian market case study

In this paper, we explore the problem of establishing a network among the stocks of a market at high frequency level and give an application to program trading. Our work uses high frequency data from the National Stock Exchange, India, for the year 2014. To begin, we analyse the spectrum of the correlation matrix to establish the presence of linear relations amongst the stock returns. A comparison of correlations with pairwise mutual information shows the further existence of non-linear relations which are not captured by correlation. We also see that the non-linear relations are more pronounced at the high frequency level in comparison to the daily returns used in earlier work. We provide two applications of this approach. First, we construct minimal spanning trees for the stock network based on mutual information and study their topology. The year 2014 saw the conduct of general elections in India and the data allows us to explore their impact on aspects of the network, such as the scale-free property and sectorial clusters. Second, having established the presence of non-linear relations, we would like to be able to exploit them. Previous authors have suggested that peripheral stocks in the network would make good proxies for the Markowitz portfolio but with a much smaller number of stocks. We show that peripheral stocks selected using mutual information perform significantly better than ones selected using correlation.

A Pólya urn approach to information filtering in complex networks

The increasing availability of data demands for techniques to filter information in large complex networks of interactions. A number of approaches have been proposed to extract network backbones by assessing the statistical significance of links against null hypotheses of random interaction. Yet, it is well known that the growth of most real-world networks is non-random, as past interactions between nodes typically increase the likelihood of further interaction. Here, we propose a filtering methodology inspired by the Pólya urn, a combinatorial model driven by a self-reinforcement mechanism, which relies on a family of null hypotheses that can be calibrated to assess which links are statistically significant with respect to a given network's own heterogeneity. We provide a full characterization of the filter, and show that it selects links based on a non-trivial interplay between their local importance and the importance of the nodes they belong to.

Risk-aware multi-armed bandit problem with application to portfolio selection

Sequential portfolio selection has attracted increasing interest in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision-making under uncertainty, namely the exploration versus exploitation dilemma, and therefore provides a natural connection to portfolio selection. In this paper, we incorporate risk awareness into the classic multi-armed bandit setting and introduce an algorithm to construct portfolio. Through filtering assets based on the topological structure of the financial market and combining the optimal multi-armed bandit policy with the minimization of a coherent risk measure, we achieve a balance between risk and return.

Dynamic Portfolio Strategy Using Clustering Approach

The problem of portfolio optimization is one of the most important issues in asset management. We here propose a new dynamic portfolio strategy based on the time-varying structures of MST networks in Chinese stock markets, where the market condition is further considered when using the optimal portfolios for investment. A portfolio strategy comprises two stages: First, select the portfolios by choosing central and peripheral stocks in the selection horizon using five topological parameters, namely degree, betweenness centrality, distance on degree criterion, distance on correlation criterion and distance on distance criterion. Second, use the portfolios for investment in the investment horizon. The optimal portfolio is chosen by comparing central and peripheral portfolios under different combinations of market conditions in the selection and investment horizons. Market conditions in our paper are identified by the ratios of the number of trading days with rising index to the total number of trading days, or the sum of the amplitudes of the trading days with rising index to the sum of the amplitudes of the total trading days. We find that central portfolios outperform peripheral portfolios when the market is under a drawup condition, or when the market is stable or drawup in the selection horizon and is under a stable condition in the investment horizon. We also find that peripheral portfolios gain more than central portfolios when the market is stable in the selection horizon and is drawdown in the investment horizon. Empirical tests are carried out based on the optimal portfolio strategy. Among all possible optimal portfolio strategies based on different parameters to select portfolios and different criteria to identify market conditions, 65% of our optimal portfolio strategies outperform the random strategy for the Shanghai A-Share market while the proportion is 70% for the Shenzhen A-Share market.

Parsimonious modeling with information filtering networks

We introduce a methodology to construct parsimonious probabilistic models. This method makes use of information filtering networks to produce a robust estimate of the global sparse inverse covariance from a simple sum of local inverse covariances computed on small subparts of the network. Being based on local and low-dimensional inversions, this method is computationally very efficient and statistically robust, even for the estimation of inverse covariance of high-dimensional, noisy, and short time series. Applied to financial data our method results are computationally more efficient than state-of-the-art methodologies such as Glasso producing, in a fraction of the computation time, models that can have equivalent or better performances but with a sparser inference structure. We also discuss performances with sparse factor models where we notice that relative performances decrease with the number of factors. The local nature of this approach allows us to perform computations in parallel and provides a tool for dynamical adaptation by partial updating when the properties of some variables change without the need of recomputing the whole model. This makes this approach particularly suitable to handle big data sets with large numbers of variables. Examples of practical application for forecasting, stress testing, and risk allocation in financial systems are also provided.

Interplay between past market correlation structure changes and future volatility outbursts

We report significant relations between past changes in the market correlation structure and future changes in the market volatility. This relation is made evident by using a measure of "correlation structure persistence" on correlation-based information filtering networks that quantifies the rate of change of the market dependence structure. We also measured changes in the correlation structure by means of a "metacorrelation" that measures a lagged correlation between correlation matrices computed over different time windows. Both methods show a deep interplay between past changes in correlation structure and future changes in volatility and we demonstrate they can anticipate market risk variations and this can be used to better forecast portfolio risk. Notably, these methods overcome the curse of dimensionality that limits the applicability of traditional econometric tools to portfolios made of a large number of assets. We report on forecasting performances and statistical significance of both methods for two different equity datasets. We also identify an optimal region of parameters in terms of True Positive and False Positive trade-off, through a ROC curve analysis. We find that this forecasting method is robust and it outperforms logistic regression predictors based on past volatility only. Moreover the temporal analysis indicates that methods based on correlation structural persistence are able to adapt to abrupt changes in the market, such as financial crises, more rapidly than methods based on past volatility.

Exploring Market State and Stock Interactions on the Minute Timescale

A stock market is a non-stationary complex system. The stock interactions are important for understanding the state of the market. However, our knowledge on the stock interactions on the minute timescale is limited. Here we apply the random matrix theory and methods in complex networks to study the stock interactions and sector interactions. Further, we construct a new kind of cross-correlation matrix to investigate the correlation between the stock interactions at different minutes within one trading day. Based on 50 million minute-to-minute price data in the Shanghai stock market, we discover that the market states in the morning and afternoon are significantly different. The differences mainly exist in three aspects, i.e. the co-movement of stock prices, interactions of sectors and correlation between the stock interactions at different minutes. In the afternoon, the component stocks of sectors are more robust and the structure of sectors is firmer. Therefore, the market state in the afternoon is more stable. Furthermore, we reveal that the information of the sector interactions can indicate the financial crisis in the market, and the indicator based on the empirical data in the afternoon is more effective.

Relation between financial market structure and the real economy: comparison between clustering methods

We quantify the amount of information filtered by different hierarchical clustering methods on correlations between stock returns comparing the clustering structure with the underlying industrial activity classification. We apply, for the first time to financial data, a novel hierarchical clustering approach, the Directed Bubble Hierarchical Tree and we compare it with other methods including the Linkage and k-medoids. By taking the industrial sector classification of stocks as a benchmark partition, we evaluate how the different methods retrieve this classification. The results show that the Directed Bubble Hierarchical Tree can outperform other methods, being able to retrieve more information with fewer clusters. Moreover, we show that the economic information is hidden at different levels of the hierarchical structures depending on the clustering method. The dynamical analysis on a rolling window also reveals that the different methods show different degrees of sensitivity to events affecting financial markets, like crises. These results can be of interest for all the applications of clustering methods to portfolio optimization and risk hedging.

Can Google Trends search queries contribute to risk diversification?

Portfolio diversification and active risk management are essential parts of financial analysis which became even more crucial (and questioned) during and after the years of the Global Financial Crisis. We propose a novel approach to portfolio diversification using the information of searched items on Google Trends. The diversification is based on an idea that popularity of a stock measured by search queries is correlated with the stock riskiness. We penalize the popular stocks by assigning them lower portfolio weights and we bring forward the less popular, or peripheral, stocks to decrease the total riskiness of the portfolio. Our results indicate that such strategy dominates both the benchmark index and the uniformly weighted portfolio both in-sample and out-of-sample.