Forecasting Crude Palm Oil Prices Using Fuzzy Rule-Based Time Series Method

Abstract

Oil palm can be reflected as the main contributor to capital investment, technology, foreign workers' employment, and knowledge management. There are risks and uncertainties arising from instability of crude palm oil (CPO) prices. Therefore, this research develops a new CPO price forecasting method using weighted subsethood-based algorithm in order to generate fuzzy rules of forecasting. The concept of fuzzy rule-based systems was embedded in fuzzy time series application to generate fuzzy IF-THEN rules. This paper aims to enhance the efficacy of time-series forecasting, which would in turn increase the accuracy of the predictions. The CPO prices data set was used for validation purposes. The accuracy of forecasting of the proposed method was compared with previous methods. The numerical results are comparable with the previous methods. The outcomes of the proposed method have shown an increase in the accuracies of the CPO price forecasts. As such, the above-mentioned method can be utilized for the creation of a new set of fuzzy rules to better predict CPO prices.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 31 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.