Trade Data Research Articles

Stock price prediction for new energy vehicle companies based on multi-source data and hybrid attention structure

In recent years, with the rapid advancement of new energy vehicle (NEV) technology, an increasing number of individuals have begun to invest in the stock market of NEV companies. Accurate prediction holds great significance for investors as it not only mitigates investment risks but also enhances the potential returns. However, the accurate prediction of stock prices is subject to the influence of numerous factors from different aspects. Therefore, to improve the prediction accuracy of stock prices, this paper integrates multi-source data and introduces an LSTM-GRU-SA-AM model. The model comprises Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Self-Attention (SA), and the hybrid attention structure SA-AM, with SA representing self-attention and AM representing attention mechanism. The multi-source data consists of stock market trading data, stock data of pertinent companies, and financial news data. We have selected four stocks of Chinese NEV companies to validate the efficacy of utilizing multi-source data, and compared our LSTM-GRU-SA-AM model with six baseline models. The experimental results demonstrate that incorporating multi-source data significantly improves prediction accuracy. Moreover, among all the models examined, our proposed LSTM-GRU-SA-AM model exhibits superior performance.

A Methodology to Correct and Harmonize International Trade Data in Mineral Resources

ABSTRACT There are often discrepancies in complementary trade data published by different countries. This article develops a method that compares the data for each country with those of its partner countries and assigns reliability scores which are then used to calculate a harmonized dataset. The whole process, from procuring and preparing the data to calculating the harmonized dataset, is described and discussed. The focus of this study is methodological. No actual analysis of trade data is provided. The approach contains numerous elements that might be useful when reconciling data from different sources without external indicators for true values.

Assessing the trade response to pandemic-related non-tariff measures

ABSTRACT This paper assesses the global trade effects of COVID-19-related non-tariff measures (NTMs), with a particular emphasis on their varied impacts across products and income groups over time. Utilizing a newly constructed NTM dataset alongside monthly trade data at the product level, we employ an event study framework to analyze the implications of trade-facilitating and trade-restricting NTMs implemented during the pandemic. Our main findings indicate an average increase of 1.2% in imports due to trade-facilitating NTMs and a 12% decrease in exports due to trade-restricting NTMs. Additionally, the analysis highlights variations in trade responses at the product level and significant differences across countries of varying income levels. This research enhances our understanding of the trade response to sudden trade cost shocks, offering critical insights into the impact of temporary trade measures within the context of a global health crisis and accompanying supply chain disruptions.

Advanced Machine Learning Techniques for Predicting Gold and Silver Futures

This research focuses on predicting the future values of gold and silver futures by employing advanced machine learning algorithms. Traditional econometric models often struggle with commodity prices’ non-linear and dynamic nature. To address this, the study evaluates the performance of four unconventional machine learning algorithms: Gaussian Processes, Quantile Regression Forests, Extreme Learning Machines, and Support Vector Regression with an RBF kernel. The dataset used includes monthly trading data for gold and silver futures. The research findings indicate that these machine- learning models significantly enhance prediction accuracy. Support Vector Regression with an RBF kernel demonstrated the highest accuracy for gold futures predictions, while Extreme Learning Machines performed competitively for silver futures. This study highlights the potential of advanced machine learning techniques in financial forecasting, providing valuable insights for traders and investors in optimizing their strategies.

Achieving European Union strategic autonomy: circularity in critical raw materials value chains

Abstract Why is it important to understand the potential of circular economy for security? With the green transition in full swing and vulnerabilities in value chains as a consequence of the COVID–19 pandemic and Russian aggression towards Ukraine, this question has never been more timely. Titanium metal constitutes a poignant case, as it is a critical raw material essential for the strategic civil aerospace and defence sectors. In addition, circular economy solutions constitute a viable solution to mitigate import dependencies in the case of this particular raw material. The European Union, with one of the largest aviation industries globally, is dependent on titanium imports from Russia and the United States. The latter, in turn, (re)imports titanium scrap from EU aviation manufacturing to increase material efficiency and reduce costs through recycling. Based on extensive stakeholder interviews across several countries and quantitative trade data, this article presents a first-time analysis of how, in the case of the titanium value chain, circular economy solutions can support the EU Open Strategic Autonomy (OSA) objectives, as enshrined in the 2023 Critical Raw Materials Act. We suggest that in order for the EU to achieve both the OSA and decarbonization objectives, it is essential to prioritize the establishment of recycling facilities as part of reshoring of the mid-value titanium industry. With the prospect of Ukraine becoming an EU member state, this strategy could be complemented by investments into the decarbonization of the upstream value chain in Ukraine while meshing it further with the EU industrial base. We argue that such reshoring could be best achieved through careful intergovernmental and industrial negotiations between the US and EU stakeholders within the formerly established channels for aviation dispute resolutions and within the framework of Ukraine's postwar reconstruction and potential EU accession.

Quantifying global redundant fisheries trade to streamline seafood supply chains.

Seafood plays an important role in sustainably feeding the world and is one of the most traded food products globally. However sustainability improvements are often focused on its production (e.g., aquaculture, fishing) rather than trade. Here, we quantify the magnitude and extent of global 'redundant two-way' seafood trade-the exchange of the same quantity of the same taxonomic species between two countries-to examine its prevalence and potential implications across the seafood supply chain. We focused on wild-caught seafood trade and found that redundant two-way trade has increased by 43%, between 2000 and 2015, making up 3.2% (7.7 Mt) of global seafood trade during that period. Although most countries were involved in redundant two-way seafood trade (111 of 212 analyzed), the majority occurred between five trade partners: Canada and the United States (15%), Germany and the Netherlands (11.8%); Denmark and Sweden (10.6%); Germany and Denmark (7.1%); and France and Norway (7%). Nearly 50% of redundant trade is made up of just four species including Atlantic herring, Atlantic cod, Skipjack tuna and Atlantic mackerel. While deficiencies in global seafood trade data mask seasonal and product heterogeneity, redundant trade could have implications for meeting conservation and sustainable development goals. Future research should build upon these findings to explore specific environmental, economic, and social implications associated with redundant two-way trade to benefit producers and consumers within the seafood supply chain.

Modelling Mixed-Frequency Time Series with Structural Change

AbstractPredictive ability of time series models is easily compromised in the presence of structural breaks, common among financial and economic variables amidst market shocks and policy regime shifts. We address this problem by estimating a semiparametric mixed-frequency model, that incorporate high frequency data either in the conditional mean or the conditional variance equation. The inclusion of high frequency data through non-parametric smoothing functions complements the low frequency data to capture possible non-linear relationships triggered by the structural change. Simulation studies indicate that in the presence of structural change, the varying frequency in the mean model provides improved in-sample fit and superior out-of-sample predictive ability relative to low frequency time series models. These hold across a broad range of simulation settings, such as varying time series lengths, nature of structural break points, and temporal dependencies. We illustrate the relative advantage of the method in predicting stock returns and foreign exchange rates in the case of the Philippines.

WALDATA: Wavelet transform based adversarial learning for the detection of anomalous trading activities

Detecting manipulative activities in stock market trading poses a significant challenge due to the complex temporal correlations inherent to the dynamically changing stock price data. This challenge is further exacerbated by the limited availability of labelled anomalous trading data instances. Stock price manipulations, which consist of infrequent anomalies in stock price trading data, are challenging to capture due to their sporadic occurrence and dynamically evolving nature. This scarcity and inherent complexity significantly complicate the creation of labelled datasets hence hinders the development of robust detection of different stock price manipulation schemes through supervised learning methods. Overcoming these challenges is crucial for enhancing our understanding of market dynamics and implementing robust market surveillance systems. To address these challenges, we introduce a novel stock price manipulation detection approach called WALDATA (Wavelet Transform based Adversarial Learning for the Detection of Anomalous Trading Activities). We leverage the Wavelet Transform (WT) to decompose non-stationary stock price time series into informative features and capture multi-scale dynamics within the data. We encode stock price data by transforming it into scalogram images through the Continuous Wavelet Transform, effectively converting stock price time series data into a 2D image representation. Subsequently, we employ a Generative Adversarial Network (GAN) architecture, originally applied to computer vision, to learn the underlying distribution of normal trading behaviour from the encoded images. We then train the discriminator as an anomaly detector for identifying manipulative trading activities in the stock market. The efficacy of WALDATA is rigorously evaluated on diverse real-world stock datasets using 1-level tick data from the LOBSTER project and the experimental results demonstrate the significant performance of our approach achieving an average AUC of 0.99 while maintaining low false alarm rates across various market conditions. These findings not only validate the effectiveness of the proposed WALDATA approach in accurately identifying stock price manipulations but also provide investors and regulators alike with valuable insights for the development of advanced market surveillance systems. This research demonstrates the promising potential of combining wavelet-based feature extraction and stock price time series to image representation with generative adversarial learning frameworks for anomaly detection in financial time series data. The successful implementation of WALDATA contributes to the development of advanced market surveillance systems and paves the way for further advancements in market surveillance, contributing towards a more efficient and robust financial system and a fair market environment.

Downscaling spatial interaction with socioeconomic attributes

A variety of complex socioeconomic phenomena, for example, migration, commuting, and trade can be abstracted by spatial interaction networks, where nodes represent geographic locations and weighted edges convey the interaction and its strength. However, obtaining fine-grained spatial interaction data is very challenging in practice due to limitations in collection methods and costs, so spatial interaction data such as transportation data and trade data are often only available at a coarse scale. Here, we propose a gravity downscaling (GD) method based on readily accessible socioeconomic data and the gravity law to infer fine-grained interactions from coarse-grained data. GD assumes that interactions of different spatial scales are governed by the similar gravity law and thus can transfer the parameters estimated from coarse-grained regions to fine-grained regions. Results show that GD has an average improvement of 24.6% in Mean Absolute Percentage Error over alternative downscaling methods (i.e., the areal-weighted method and machine learning models) across datasets with different spatial scales and in various regions. Using simple assumptions, GD enables accurate downscaling of spatial interactions, making it applicable to a wide range of fields, including human mobility, transportation, and trade.

The impact of cryptocurrency-related cyberattacks on return, volatility, and trading volume of cryptocurrencies and traditional financial assets

We investigate the impact of cryptocurrency-related cyberattacks on the cryptocurrency market and traditional financial markets. The dataset consists of historical cyberattack data and trading data for twenty cryptocurrencies, three cryptocurrency uncertainty indices, five payment companies, four stock indices, a commodity index, and gold. We find that cyberattacks are associated with negative returns, increased volatility, and increased trading volume not only for the cryptocurrencies but also for the payment companies, the financial and technology sectors, and the general stock market. However, the impact of cyberattacks on cryptocurrencies has been decreasing over time, while the impact on payment companies and the financial sector has been increasing. Moreover, gold prices have shown a positive response to these cyberattacks. These results underscore the need for enhanced cybersecurity measures in the fintech sector and may inform both policymakers and market participants.

Impact of the Russia-Ukraine Conflict on International Staple Agrifood Trade Networks.

The Russia-Ukraine conflict is a growing concern worldwide and poses serious threats to regional and global food security. Using monthly trade data for maize, rice, and wheat from 2016/1 to 2023/12, this paper constructs three international crop trade networks and an aggregate international food trade network. We aim to examine the structural changes following the occurrence of the Russia-Ukraine conflict. We find significant shifts in the number of edges, average in-degree, density, and efficiency in the third quarter of 2022, particularly in the international wheat trade network. Additionally, we have shown that political reasons have caused more pronounced changes in the trade connections between the economies of the North Atlantic Treaty Organization and Russia than with Ukraine. This paper could provide insights into the negative impact of geopolitical conflicts on the global food system and encourage a series of effective strategies to mitigate the negative impact of the conflict on global food trade.

Risk Preference and Asset Allocation Strategy Analysis in Financial Market

In the financial market, risk appetite is the key factor of investors decision-making, which determines investors acceptance of risk and investment behavior. The importance of risk appetite is that it affects asset allocation, investment strategy selection, and risk management. In financial markets, risk appetite is measured by psychological tests and questionnaires, analysis of historical trading data, and consideration of an investor s life cycle. The adjustment of asset allocation strategy needs to be reviewed and adjusted regularly to respond to market changes and adopt corresponding coping mechanisms when investors risk appetite changes.

Skew–Brownian processes for estimating the volatility of crude oil Brent

To predict the volatility of crude oil Brent price, we propose a novel econometric model 11The numerical results presented in this manuscript were reproduced by the Editor-in-Chief on 30 June 2024. where the explanatory variables are a combination of macroeconomic variables (i.e. price pressure), trade data (freight shipment index), and market sentiment (gold volatility). The model is proposed in two alternative variants: first, we assume Gaussian distributed quantities; alternatively, we consider the potential presence of skewness and adopt a Skew–Brownian process. We show that the suggested approach outperforms the selected baseline model as well as other models proposed in the literature, especially when turbulent periods occur.

Matching comparative advantages to special economic zones for sustainable industrialization

African countries are consistently trying to leverage industrialization to advance their economic development. Despite possessing favorable factors such as abundant natural resources, a surplus of low-cost labor, and an increasing number of established Special Economic Zones (SEZs), African countries are yet to fully maximize their potential and achieve sustainable and inclusive industrialization. This study explores the comparative advantages of African countries to determine the types of SEZs that can effectively accelerate industrialization. By leveraging the unique strengths and resources of each country, customized strategies for SEZs can be developed to attract investments, promote technological advancements, and foster sustainable economic growth. The research utilizes the Revealed Comparative Advantage (RCA) matrix, which is grounded in Ricardian trade theory, examining trade data spanning from 2011 to 2021 to evaluate the competitive export capabilities of various countries. The findings consistently reveal that the selected countries (Ghana, Ethiopia, and South Africa) possess a significant and consistent comparative advantage in natural and agricultural resources compared to other sectors. Establishing SEZs that focus on these sectors can generate substantial socio-economic impacts, including attracting investments, creating employment opportunities, enhancing export capacities, stimulating economic growth, fostering linkages, facilitating skills and technology transfer, promoting spillover effects, encouraging specialization, developing infrastructure, and supporting value addition in agribusinesses. The result of this study will contribute to policy discussions and aid decision-making processes for policymakers, investors, and development practitioners in their efforts to advance industrial development across Africa.

Optimizing Emergency Responses on Water Transport Accidents in Metropolitan Lagos

The study analyzed agricultural product trade data to ascertain the extent of involvement of ECOWAS in community trade between 2013 and 2017. The extent to which members fulfilled the regional trade co-operation policy objective of expanding the volume of intra-community trade is gauged by computed trade indices. Each index measures intra-community trade as a share of total trade, and takes values between 0 and 1. The value is 0, if trade is truly intra-community carried out by all or most members; and 1, if trade is inter-regional, most trade being carried out by few community members. Value of annual index were influenced by cases of none, under or over reporting by member nations. Analysis revealed that intra-community trade occurred more in animal than food products, while vegetable products accounted for less. It is recommended that ECOWAS member nations should seek and utilizing foreign direct investment in development of agricultural sector to improve value chain in addition to increasing and sustaining intra-community trade volume. Besides, reports of intra-community exports and imports of agricultural products should be accurate, and no member should import from other regions where sub-community members are suppliers. Keywords: Agricultural Product Sub-sections, ECOWAS, Intra-Community Trade, Extent. DOI : 10.7176/DCS/9-1-08

The Revealed Comparative Advantage of Agri-Food Industries in Selected Countries in the Central and Eastern Europe: Gross-Versus Value-Added Trade Flows

The aim of the article is to interrogate comparative advantage of agrarian and food processing sectors in the context of the agri-food global value chains in particular countries in the Central and Eastern Europe using gross trade and value-added trade data from TiVA database. The Normalized revealed comparative advantage index (NRCA) was applied to analyze comparative (dis)advantage of agrarian and food processing sectors from 1995 to 2020. The article contributes twofold: First, NRCA pairs of indices calculated using gross trade and value-added trade data are mostly consistent. The analysis identifies for what areas and countries there is a discrepancy; second, it reveals comparative advantage of agrarian and food processing sectors in each country separately. It indicates different trajectories of development among countries in the Central and Eastern Europe. These results are complementary to the results of studies that evaluated comparative advantages on the product basis.

Unlocking Africa’s development potential: insights from the perspective of global hierarchy and competition

Science and technology have had great leaps since World War II. However, many African countries have remained very poor. To understand this issue, we employ a new metric, the revealed comparative wealth (RCW), to critically assess economic development in all African countries. The yearly ranking of RCW for all the countries in the world reveals a global hierarchy with many African countries moving to the lower end of the hierarchy, indicating worsened relative underdevelopment in Africa. Analysis of the temporal variations of RCW reveals a salient mechanism for the underdevelopment in Africa — over 30 African countries have their RCW strongly negatively correlated with advanced economies. One main factor contributing to this phenomenon, inferred from international trade data analysis, is the partition of labor and differences in industrial structure — most African countries are at the very bottom of the various value chains, including only providing raw materials to the better-developed countries. The inferior positions in the global hierarchy for the African nations are found to be partly instigated by colonialism and enhanced by neo-colonialism. To unlock Africa’s development potential, African nations must diversify their economic activity, unleash people’s creativity about economic development, and make the best efforts to accumulate capital to make further development possible. A prerequisite for achieving the last is to use foreign capital and cooperate with multinational corporations more wisely, including securing better deals with profit allocation resulting from foreign investment.

Research on Hedging Ratio of Stock Index Futures to ETF Fund

Exchange Traded Funds (ETF) can largely avoid non-systematic risk, but investors often cannot avoid systemic risk, and the hedging function of stock index futures can do this. Therefore, hedging ETF with stock index futures has become a good investment strategy. Based on the trading data of the China Securities Index (CSI) 300 stock index futures and CSI 300 Exchange-Traded Fund (ETF), this paper analyzes the optimal hedging ratio of CSI 300 stock index futures by Ordinary Least Squares (OLS) and dynamic Error Correction Model - Generalized Autoregressive Conditional Heteroskedasticity (ECM-GARCH) model and compares the hedging performance predicted by the model to avoid the systematic risk of ETF. The results show that the hedging effect of the dynamic hedging model is better than that of the static model, and the ability to avoid systemic risk is also better. The predictions of both models show that stock index futures hedge ETFs very well. The dynamic model is more able to reduce the heteroscedasticity of the transaction data.

Influence of Quality Education on FDI Inflows in Subs-Saharan Africa: A Theoretical and Empirical Research

The non-traditional influences of Foreign Direct Investment (FDI) are increasingly gaining attention in international business studies; however, the empirical evidence of these influences is still scant. Using human capital theory within the context of the national competitive framework, the study reported in this paper considers the progress towards achieving Quality education as a likely influence of FDI inflows in Sub-Saharan Africa (SSA). The paper employs a panel data research design and conducts fixed effects estimations. The analysis categorizes FDI flows into global FDI, FDI from developed countries, and FDI from developing countries to SSA. Thus, the paper is centred around three research questions: (1) How does progress toward quality education influence global FDI inflows? (2) How does progress towards quality education influence FDI inflows from developed and (3) from developing countries? The analysis mainly utilizes a bespoke dataset from the United Nations Conference on Trade and Development (UNCTAD) and data from trustworthy databases such as UNCTADSTAT and the World Development Indicators (WDI). The results support the claim of the increasing importance of non-traditional influences of FDI flow. Quality Education significantly influenced FDI inflows from the globe and developing countries to SSA. This research provides further evidence that the national competitive framework can thoroughly explain the factors that have different significant powers in influencing FDI flows to SSA from developed and developing countries. The study is highly policy-relevant because it examines the effects of the degree of attainment of specific UN Sustainable Development Goals (quality education) on inward FDI performance. It, therefore, shows the benefits of SSA countries investing in the SDGs for the policy goal of attracting more considerable amounts of inward FDI.

Establish an US Interagency Wildlife Trade Data System to meet scientific and policy goals

Establish an US Interagency Wildlife Trade Data System to meet scientific and policy goals