Commodity price analysis by using logic mining

Abstract

Developing a data mining model for commodities price plays an important role in future investments and decisions for related companies. Viewed from this perspective, this paper proposes a logic mining model for accurately showcase the behavior of the commodities' price from 2009 until 2018. This model utilizes 2 Satisfiability Reverse Analysis Method (2SATRA) integrated with Hopfield Neural Network (HNN). HNN is a single layered neural network that can be divided into learning and retrieval phase. In this case, the retrieved neuron state from HNN is an important component in 2SATRA. The inputs of the proposed model were realized by using the real commodities such as Palm oil, Latex, Gold, Crude Petroleum, Timber, Black & White Pepper and Cocoa Bean. This model discusses the implication of the 2SATRA model within the context of the discipline as well as practical application.