Structure and dynamics of financial networks by feature ranking method

Much research has been done on time series of financial market in last two decades using linear and non-linear correlation of the returns of stocks. In this paper, we design a method of network reconstruction for the financial market by using the insights from machine learning tool. To do so, we analyze the time series of financial indices of S&P 500 around some financial crises from 1998 to 2012 by using feature ranking approach where we use the returns of stocks in a certain day to predict the feature ranks of the next day. We use two different feature ranking approaches—Random Forest and Gradient Boosting—to rank the importance of each node for predicting the returns of each other node, which produces the feature ranking matrix. To construct threshold network, we assign a threshold which is equal to mean of the feature ranking matrix. The dynamics of network topology in threshold networks constructed by new approach can identify the financial crises covered by the monitored time series. We observe that the most influential companies during global financial crisis were in the sector of energy and financial services while during European debt crisis, the companies are in the communication services. The Shannon entropy is calculated from the feature ranking which is seen to increase over time before market crash. The rise of entropy implies the influences of stocks to each other are becoming equal, can be used as a precursor of market crash. The technique of feature ranking can be an alternative way to infer more accurate network structure for financial market than existing methods, can be used for the development of the market.

Heuristic methods for stock selection and allocation in an index tracking problem

Index tracking is one of the most popular passive strategy in portfolio management. However, due to some practical constrains, a full replication is difficult to obtain. Many mathematical models have failed to generate good results for partial replicated portfolios, but in the last years a data driven approach began to take shape. This paper proposes three heuristic methods for both selection and allocation of the most informative stocks in an index tracking problem, respectively XGBoost, Random Forest and LASSO with stability selection. Among those, latest deep autoencoders have also been tested. All selected algorithms have outperformed the benchmarks in terms of tracking error. The empirical study has been conducted on one of the biggest financial indices in terms of number of components in three different countries, respectively Russell 1000 for the USA, FTSE 350 for the UK, and Nikkei 225 for Japan.

On the Risk-based Contagion of G7 Banking System and the COVID-19 Pandemic

We revisit the discussion on banking system contagion by proposing a risk-based empirical analysis during the current pandemic period. We use daily returns on G7 banking sector indices from 1 January 2015 to 31 December 2019 (pre-pandemic), and from 1 January 2020 to 16 October 2020 (pandemic). Based on the dissimilarities, the pandemic has intensified banking contagion. Frequency-based Granger causality is useful to tell the history of the pass-through of this health crisis across G7 banking sectors. We highlight the increase in the predictive relevance of Italian banking cycles during the pandemic. VaR ratio analysis, considering 21 possible pairwise combinations with the G7 financial indices, suggests a stronger contagion between banking systems. The greatest contagion is evident in the Italian and French banking systems, countries severely affected by deaths by COVID-19, while we find less contagion between Japan and Germany, countries least affected by the first wave of COVID-19.

Applications of Machine Learning For Precision Agriculture and Smart Farming

Recent deglobalization movements have had a transformativeimpact and an increase in uncertainty on manyindustries. The advent of technology, Big Data, and MachineLearning (ML) further accelerated this disposition.Many quantitative metrics that measure the globaleconomy’s equilibrium have strong and interdependentrelationships with the agricultural supply chain and internationaltrade flows. Our research employs econometricsusing ML techniques to determine relationshipsbetween commonplace financial indices (such asthe DowJones), and the production, consumption, andpricing of global agricultural commodities. Producersand farmers can use this data to make their productionmore effective while precisely following global demand.In order to make production more efficient, producerscan implement smart farming and precision agriculturemethods using the processes proposed. It enablesthem to have a farm management system that providesreal-time data to observe, measure, and respondto variability in crops. Drones and robots can be usedfor precise crop maintenance that optimize yield returnswhile minimizing resource expenditure. We developML models which can be used in combinationwith the smart farm data to accurately predict the economicvariables relevant to the farm. To ensure the accuracyof the insights generated by the models, ML assuranceis deployed to evaluate algorithmic trust.

Clean Development Mechanism (CDM)-based Development of Grid-connected Rice Husk-fuelled Bio-power Plants in Mekong Delta, Vietnam

The research is designed for developing the pilot small-scale clean development mechanism bundled project activities in Vietnam electricity/ energy sector. Its overall purpose is to assess the potential of rice husk - fuelled bio-power development projects in Mekong delta. Based on estimating the electricity potential of a bundle of rice husk-fuelled bio-power development projects in Mekong delta with the capacity of 11 MW per project, assessing their CO2 emission reductions (CERs) and CER credits, calculating and comparing their financial indices (NPV, B/C, IRR) in two cases: W/O CDM and W/CDM, the research expects to establish a rice husk energy balance flowchart for the whole Mekong delta in the year 2021 and recommend policies to use for bio-power generation the unused rice husk that is dumped and discharged from local paddy milling centers into rivers and canals, as well as, to put forward a safe and environmentally friendly solution to minimize thoroughly the current serious pollution of rivers and canals in Mekong delta with the increasing unused rice husk quantity in the context is where the sea level rise phenomenon is the strongest in the world .

Clean Development Mechanism (CDM) – Based Development of Grid-Connected Rice Husk-Fuelled Bio-Power Plants in Mekong Delta, Vietnam

The research is designed for developing the pilot small-scale clean development mechanism bundled project activities in Vietnam electricity/ energy sector. Its overall purpose is to assess the potential of rice husk - fuelled bio-power development projects in Mekong delta. Based on estimating the electricity potential of a bundle of rice husk-fuelled bio-power development projects in Mekong delta with the capacity of 11 MW per project, assessing their CO2 emission reductions (CERs) and CER credits, calculating and comparing their financial indices (NPV, B/C, IRR) in two cases: W/O CDM and W/CDM, the research expects to establish a rice husk energy balance flowchart for the whole Mekong delta in the year 2021 and recommend policies to use for bio-power generation the unused rice husk that is dumped and discharged from local paddy milling centers into rivers and canals, as well as, to put forward a safe and environmentally friendly solution to minimize thoroughly the current serious pollution of rivers and canals in Mekong delta with the increasing unused rice husk quantity in the context is where the sea level rise phenomenon is the strongest in the world .

Testing the Resilience of CSR Stocks during the COVID-19 Crisis: A Transcontinental Analysis

Investors and practitioners are increasingly concerned with financial assets within the scope of corporate social responsibility (CSR) meaning that, in recent times, such assets have become enshrined in the preferences of the new generations of investors and consumers. Just when the interest of investors was at its highest, SARS-CoV-2 (COVID-19) affected all international financial markets, so that, at first sight, it might seem that the financial assets assigned to CSR should have suffered collapses that were identical to the rest; however, our work shows the opposite, providing a comparative analysis of how the pandemic has affected the financial markets of each continent to demonstrate its outstanding resilience through the use of the Wavelets methodology. We analyzed the global impact of the registered cases of COVID-19 on the Dow Jones Sustainability World Index (DJSWI), the world’s leading indicator of sustainable companies, in addition to six other financial indices selected from each continent. The empirical results of this research show that the worldwide repercussions of the sudden outbreak of SARS-CoV-2 has had a substantially smaller effect on sustainability-related indices compared to the other considered indices. Similarly, the methodology employed allowed the establishment of a chronogram with details of the dating of COVID-19 expansion through the considered countries, a certain gradation in terms of the impact of the pandemic on these stock indices, and certain common guidelines describing their devastating effects on each of the financial markets represented by the indices in this research.

Network-centric Indicators for Fragility in Global Financial Indices

Over the last 2 decades, financial systems have been studied and analyzed from the perspective of complex networks, where the nodes and edges in the network represent the various financial components and the strengths of correlations between them. Here, we adopt a similar network-based approach to analyze the daily closing prices of 69 global financial market indices across 65 countries over a period of 2000–2014. We study the correlations among the indices by constructing threshold networks superimposed over minimum spanning trees at different time frames. We investigate the effect of critical events in financial markets (crashes and bubbles) on the interactions among the indices by performing both static and dynamic analyses of the correlations. We compare and contrast the structures of these networks during periods of crashes and bubbles, with respect to the normal periods in the market. In addition, we study the temporal evolution of traditional market indicators, various global network measures, and the recently developed edge-based curvature measures. We show that network-centric measures can be extremely useful in monitoring the fragility in the global financial market indices.