Search results

Long-term forecasts about commodity market indicators play an important role in informing policy and investment decisions by governments and market participants. Our study examines whether the accuracy of the multi-step forecasts can be improved using deep learning methods.

We first formulate a supervised learning problem and set benchmarks for forecast accuracy using traditional econometric models. We then train a set of deep neural networks and measure their performance against the benchmark.

We find that while the United States Department of Agriculture (USDA) baseline projections perform better for shorter forecast horizons, the performance of the deep neural networks improves for longer horizons. The findings may inform future revisions of the forecasting process.

This study demonstrates an application of deep learning methods to multi-horizon forecasts of agri-cultural commodities, which is a departure from the current methods used in producing these types of forecasts.

The authors explore the hypothesis that some movements in commodity prices are anticipated (news shocks) and can trigger aggregate fluctuations in small open emerging economies. This paper aims to discuss the aforementioned objective.

The authors build a multi-sector dynamic stochastic general equilibrium model with endogenous commodity production. There are five exogenous processes: a country-specific interest rate shock that responds to commodity price fluctuations, a productivity (TFP) shock for each sector and a commodity price shock. Both TFP and commodity price shocks are composed of unanticipated and anticipated components.

The authors show that news shocks to commodity prices lead to higher output, investment and consumption, and a countercyclical movement in the trade-balance-to-output ratio. The authors also show that commodity price news shocks explain about 24% of output aggregate fluctuations in the small open economy.

Given the importance of both anticipated and unanticipated commodity price shocks, policymakers should pay attention to developments in commodity markets when designing policies to attenuate the business cycles. Future research should investigate the design of optimal fiscal and monetary policies in SOE subject to news shocks in commodity prices.

This paper contributes to the knowledge of the sources of fluctuations in emerging economies highlighting the importance of a new source: news shocks in commodity prices.

This work proposes a methodology to project future freight demand for all commodity types that begin and end in each geographical region and the amount of freight that moves between all origin and destination pairs. Following the traditional four-step demand forecasting framework, the procedure corresponds to trip generation and trip distribution analysis for interregional freight demand. Using future economic growth factors from macroeconomic and input-output models, the amounts of freight production and attraction in each analysis zone are forecasted and taken as given. Subsequently, an iterative matrix balancing method is applied to determine the estimated freight shipment demand for all origin and destination zone pairs. The proposed algorithm is applied to generate predicted future freight demand within the United States from 2010-2050 in five-year increments based on the national freight demand data from 2007. Four different scenarios are proposed that consider variations in both global economic growth and environmental regulation. This study will assist transportation planners and decision makers in public and private sectors to assess how future freight delivery demand on the national scale considering various future global economic growth and environmental policy scenarios will affect various issues such as air quality and human health problems.

Agriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly wholesale price index of green grams in the Chinese market. The index covers a ten-year period, from January 1, 2010, to January 3, 2020, and has significant economic implications.

In order to address the nonlinear patterns present in the price time series, we investigate the nonlinear auto-regressive neural network as the forecast model. This modeling technique is able to combine a variety of basic nonlinear functions to approximate more complex nonlinear characteristics. Specifically, we examine prediction performance that corresponds to several configurations across data splitting ratios, hidden neuron and delay counts, and model estimation approaches.

Our model turns out to be rather simple and yields forecasts with good stability and accuracy. Relative root mean square errors throughout training, validation and testing are specifically 4.34, 4.71 and 3.98%, respectively. The results of benchmark research show that the neural network produces statistically considerably better performance when compared to other machine learning models and classic time-series econometric methods.

Utilizing our findings as independent technical price forecasts would be one use. Alternatively, policy research and fresh insights into price patterns might be achieved by combining them with other (basic) prediction outputs.

This paper aims to explore the impacts of the recent development of Korean free trade agreements (FTAs) on its seaborne trade volumes. The paper firstly estimates the changes in cargo value flows caused by Korea-EU FTA, Korea-USA FTA and Korea-ASEAN FTA using a global computable general equilibrium model named Global Trade Analysis Project (GTAP) and its most recent database - version 7 with 2004 as the base year. Then a set of systematic conversion factors transferring trade value flows to volume flows of different types of commodities is calibrated according to the United Nations COMTRADE database and is used to convert the GTAP trade value flows into volume flows. Having indentified maritime cargo flows by different commodity types, this paper attempts to draw implications for maritime logistics policy in order to facilitate the trade of Korean merchandises and to propose key competitive strategy for the maritime container transport networking and logistics service providers in the Korean logistics industry.

This study focuses on forecasting the price of the most important export crops of vegetables and fruits in Egypt from 2016 to 2030.

The study applied generalized autoregressive conditional heteroskedasticity (GARCH) model and autoregressive integrated moving average (ARIMA) model.

The results show that ARIMA (1,1,1), ARIMA (2.1,2), ARIMA (1,1,0), ARIMA (1,1,2), ARIMA (0,1,0) and ARIMA (1,1,1) are the most appropriate fitted models to evaluate the volatility of price of green beans, tomatoes, onions, oranges, grapes and strawberries, respectively. The results also revealed the presence of ARCH effect only in the case of Potatoes, hence it is suggested that the GARCH approach be used instead. The GARCH (1,1) is found to be a better model in forecasting price of potatoes.

The study of food price volatility in developing countries is essential, since a significant share of household budgets is spent on food in these economies, so forecasting agricultural prices is a substantial requirement for drawing up many economic plans in the fields of agricultural production, consumption, marketing and trade.

Forecasts of commodity prices are vital issues to market participants and policy makers. Those of corn are of no exception, considering its strategic importance. In the present study, the authors assess the forecast problem for the weekly wholesale price index of yellow corn in China during January 1, 2010–January 10, 2020 period.

The authors employ the nonlinear auto-regressive neural network as the forecast tool and evaluate forecast performance of different model settings over algorithms, delays, hidden neurons and data splitting ratios in arriving at the final model.

The final model is relatively simple and leads to accurate and stable results. Particularly, it generates relative root mean square errors of 1.05%, 1.08% and 1.03% for training, validation and testing, respectively.

Through the analysis, the study shows usefulness of the neural network technique for commodity price forecasts. The results might serve as technical forecasts on a standalone basis or be combined with other fundamental forecasts for perspectives of price trends and corresponding policy analysis.

Energy is a driving force of economic development in the modern world, while as a commodity group it holds the greatest share of the world seaborne trade. Oil, natural gas and coal are the three most important sources of energy for the European Union which, as a bloc, represents 17% of the total energy consumption. The aim of the present paper is to explore the economics and trade issues of these three major energy commodities and investigate the role of the maritime transport in the energy trade within the context of the EU-25. A number of factors are considered in order to discuss contemporary opportunities and challenges that arise in this context for the shipping business. The examination reveals the critical dependence of EU-25 energy supply on seaborne trade and the considerable reliance of the maritime transport on such commodities for the generation of shipping business within the realms of the EU-25. Among the parameters regarded as conducive to the demand of shipping services in the context of the EU energy trade are the energy demand factor, the import dependency factor, the cost effective production element, and seaborne trade related parameters while consideration is also given to environmental issues.

World trade has been increasing rapidly and much faster than world output. This study analyzes the trade structures of major dynamic East Asian countries as well as regional subgroups such as ASEAN members and Northeast Asian countries. Emphasis will be on the complementarities that would enhance integration among them through international trade. In addition, potential trade levels for each combination of East Asian countries are estimated by applying the gravity model of trade to the trade flows of21 APEC members, as a reference group. It is estimated to have significant potentiality by regional subgroup, ASEAN or Northeast Asia, and not between the two regional subgroups. However, the potential integration between East Asian countries in different regional subgroups is more significant by considering complementarities in trade compared with the results from the basic gravity model. To enhance economic cooperation between East Asian countries, expanding relationships such as inter-industry trade in natural resources trade and industrial goods between the regional subgroups needs to occur. They should also utilize complementary relationships from intra-industry trade in industrial goods such as electric and electronic equipment, related parts and accessories. And they should focus on the implementation of trade facilitation measures based on global standards.

Research based on Bangladesh–US trade data examines the Heckscher–Ohlin model and the Rybczynski hypothesis in this study.

Ordinary least square (OLS) techniques are used in this study, which relies on data from the NBER International Trade and Geography Data and the UN Comtrade Database for the years 2018 and 2008.

The research shows that trade between the United States and Bangladesh follows Heckscher–Ohlin and Rybcyzinski's trade predictions. According to the study, since labor is in plentiful supply in Bangladesh, Bangladesh's labor-based sectors have a higher US labor-to-capital import shares than US capital-based industries. As Bangladesh has not changed significantly from a labor-based country since 2008, it retains the same pattern even though the share of US unskilled labor-based sectors imported from Bangladesh decreased in 2018.

The findings of this study have a wide range of implications for both trade theory and policy debates between Bangladesh and the United States.