Neural Networks Versus Time Series Models For Forecasting Commodity Prices

This paper applies a recurrent neural network (RNN) method to forecast cotton and oil prices. We show how these new tools from machine learning, particularly Long-Short Term Memory (LSTM) models, complement traditional methods. Our results show that machine learning methods fit reasonably well with the data but do not outperform systematically classical methods such as Autoregressive Integrated Moving Average (ARIMA) or the naïve models in terms of out of sample forecasts. However, averaging the forecasts from the two type of models provide better results compared to either method. Compared to the ARIMA and the LSTM, the Root Mean Squared Error (RMSE) of the average forecast was 0.21 and 21.49 percent lower, respectively, for cotton. For oil, the forecast averaging does not provide improvements in terms of RMSE. We suggest using a forecast averaging method and extending our analysis to a wide range of commodity prices.

The aim of this publication is to identify and apply suitable methods for analysing and predicting the time series of gold prices, together with acquainting the reader with the history and characteristics of the methods and with the time series issues in general. Both statistical and econometric methods, and especially artificial intelligence methods, are used in the case studies. The publication presents both traditional and innovative methods on the theoretical level, always accompanied by a case study, i.e. their specific use in practice. Furthermore, a comprehensive comparative analysis of the individual methods is provided. The book is intended for readers from the ranks of academic staff, students of universities of economics, but also the scientists and practitioners dealing with the time series prediction. From the point of view of practical application, it could provide useful information for speculators and traders on financial markets, especially the commodity markets.

Readers will find, in this highly relevant and groundbreaking book, research ranging from applications in financial markets and business administration to various economics problems. Not only are empirical studies utilizing various CI algorithms presented, but so also are theoretical models based on computational methods. In addition to direct applications of computational intelligence, readers can also observe how these methods are combined with conventional analytical methods such as statistical and econometric models to yield preferred results.

From the author of the bestselling "Analysis of Time Series," Time-Series Forecasting offers a comprehensive, up-to-date review of forecasting methods. It provides a summary of time-series modelling procedures, followed by a brief catalogue of many different time-series forecasting methods, ranging from ad-hoc methods through ARIMA and state-space

Natural Computing is the field of research that investigates both human-designed computing inspired by nature and computing taking place in nature, i.e., it investigates models and computational techniques inspired by nature and also it investigates phenomena taking place in nature in terms of information processing. Examples of the first strand of research covered by the handbook include neural computation inspired by the functioning of the brain; evolutionary computation inspired by Darwinian evolution of species; cellular automata inspired by intercellular communication; swarm intelligence inspired by the behavior of groups of organisms; artificial immune systems inspired by the natural immune system; artificial life systems inspired by the properties of natural life in general; membrane computing inspired by the compartmentalized ways in which cells process information; and amorphous computing inspired by morphogenesis. Other examples of natural-computing paradigms are molecular computing and quantum computing, where the goal is to replace traditional electronic hardware, e.g., by bioware in molecular computing. In molecular computing, data are encoded as biomolecules and then molecular biology tools are used to transform the data, thus performing computations. In quantum computing, one exploits quantum-mechanical phenomena to perform computations and secure communications more efficiently than classical physics and, hence, traditional hardware allows. The second strand of research covered by the handbook, computation taking place in nature, is represented by investigations into, among others, the computational nature of self-assembly, which lies at the core of nanoscience, the computational nature of developmental processes, the computational nature of biochemical reactions, the computational nature of bacterial communication, the computational nature of brain processes, and the systems biology approach to bionetworks where cellular processes are treated in terms of communication and interaction, and, hence, in terms of computation. We are now witnessing exciting interaction between computer science and the natural sciences. While the natural sciences are rapidly absorbing notions, techniques and methodologies intrinsic to information processing, computer science is adapting and extending its traditional notion of computation, and computational techniques, to account for computation taking place in nature around us. Natural Computing is an important catalyst for this two-way interaction, and this handbook is a major record of this important development.

Master's Thesis from the year 2019 in the subject Computer Science - Miscellaneous, University of Gondar (Atse Tewodros Cumpas), course: Information technology, language: English, abstract: Agricultural price predictions are an integral component of trade and policy analysis. As the prices of agricultural commodities directly influence the real income of farmers and it also affects the national foreign currency generate. Sesame is highly produced in some tropical and subtropical rain forest Ethiopia region. The thesis is to build a model that can predict market prices of sesame commodity. Based on the complexity of sesame price prediction; the predicting models used for crop are linear regression, support vector machine and neural network models to predict a future price. A data have been taken from the ECX website (www.ecx.com.et) in the interval of January 2013 to March 2019. The total numbers of records selected to the experiments are 5,327 daily prices are used for proposed models. The experimental result had evaluated by RMSE, MSE and CC metrics. We follow six phase CRISP-DM process model for sesame price prediction. The process phase are, business understanding, data understanding, data preparation, modeling, evaluating and deployment.

Comprehensive introduction to the neural network models currently under intensive study for computational applications. It also provides coverage of neural network applications in a variety of problems of both theoretical and practical interest.

Artificial neural networks provide a new approach to commodity forecasting that does not require algorithm or rule development. Neural networks have been deemed successful in applications involving optimization, classification, identification, pattern recognition and time series forecasting. With the advent of user friendly, commercially available software packages that work in a spreadsheet environment, such as Neural Works Predict by NeuralWare, more people can take advantage of the power of artificial neural networks. This thesis provides an introduction to neural networks, and reviews two recent studies of forecasting commodities prices. This study also develops a neural network model using Neural Works Predict that forecasts jet fuel prices for the Defense Fuel Supply Center (DFSC). In addition, the results developed are compared to the output of an econometric regression model, specifically, the Department of Energy's Short-Term Integrated Forecasting System (STWS) model. The Predict artificial neural network model produced more accurate results and reduced the contribution of outliers more effectively than the STIFS model, thus producing a more robust model.