Accurate price forecasting for agricultural commodities can have significant decisionmaking implications for suppliers, especially those of biofuels, where the agriculture and energy sectors intersect. Environmental pressures and high oil prices affect demand for biofuels and have reignited the discussion about effects on food prices. Suppliers in the sugar-alcohol sector need to decide the ideal proportion of ethanol and sugar to optimise their financial strategy. Prices can be affected by exogenous factors, such as exchange rates and interest rates, as well as non-observable variables like the convenience yield, which is related to supply shortages. The literature generally uses two approaches: artificial neural networks (ANNs), which are recognised as being in the forefront of exogenous-variable analysis, and stochastic models such as the Kalman filter, which is able to account for non-observable variables. This article proposes a hybrid model for forecasting the prices of agricultural commodities that is built upon both approaches and is applied to forecast the price of sugar. The Kalman filter considers the structure of the stochastic process that describes the evolution of prices. Neural networks allow variables that can impact asset prices in an indirect, nonlinear way, what cannot be incorporated easily into traditional econometric models.

No abstract

Resumo: Nos últimos 20 anos tem ocorrido um interesse crescente no comportamento do preço de commodities devido a mudanças no padrão da demanda mundial e o crescimento dos mercados futuros de commodities como instrumento para gestão de portfólios na indústria. A fim de reduzir risco e assegurar preços, os agentes de mercado empregam diferentes estratégias de hedging baseadas no em mercados futuros, sendo imprescindível o uso de modelos de previsão. Neste contexto, o objetivo deste artigo é construir um modelo de previsão para preços à vista de commodities agrícolas com base em um modelo hierárquico. Um primeiro modelo de espaço de estados é ajustado de forma a identificar tendências das séries. Os resultados obtidos são então corrigidos através de redes neurais. Para analisar o comportamento do modelo foram consideradas commodities: soja, álcool e açúcar. Os resultados sugerem que o modelo pode ser uma ferramenta útil para entender os mercados e para previsão de preços de curto prazo.Palavras Chave: Commodities agrícolas. Mercados Futuros. Redes Neurais. Modelos híbridos. Previsão.Abstract: Last two decades have seen a considerable interest in commodities price behavior as a result of demand pattern changes and the growth of commodities futures markets as a tool to portfolio management in industry. In order to reduce risk and assure prices, agents use different hedging strategies based on futures markets. In this sense forecast models are essential. This paper proposes a mathematical model to agricultural commodity prices forecasting. A hierarchical model is presented. A state space model is considered to identify trends or to describe the structure of the stochastic process. This model is adjusted through a neural network. To analyze the model three commodities were considered: soybeans, alcohol and sugar. The results suggest that this model can be a useful tool to understand markets and to short term forecast.

No abstract

The creation of successful products is linked with the ability to reach longings and desires of costumers. Several factors compose these desires and a group of factors have a special characteristic, this group embraces reliability, maintainability and safety. The management of these three factors carries in a deep look of the entire product's life cycle and not only in design, manufacture or in functional test phase.The following work intend discuss an implementation of a management system for reliability, maintainability and safety in companies that develop products seeking profit and keeping intense attention to rules from concurrent engineering. Finally will be presented an implementation case of one of most important tool for the management system, the system FRACAS, "Failure Reporting, Analysis and Corrective Action System", that organizes and standardizes the data collection, making some analysis possible and creating basis for the decision making process.During the development of all this discussion a broad number of subjects will be pointed, like product's life cycle, designs, projects, quality, information systems, data base technology e obviously reliability, maintainability and safety.The case will start from a preexistent product that already have available field data, following to construction of an information system capable to collect, organize, filter and pre-analyze the information.The main goal of this work is to orientate companies that develop products that demand huge engineering efforts in optimization of making decisions process, showing some options to control their operations, their IV programs and projects, concerning reliability, maintainability, availability and safety.