A Critical Evaluation of Computational Methods of Forecasting Based on Fuzzy Time Series

The agricultural production is a process, which being nonlinear in nature, due to various influential parameters like weather, rainfall, diseases, disaster, area of cultivation etc., is not governed by any deterministic process. Fuzzy time series forecasting is one of the approaches for predicting the future values where neither a trend is viewed nor a pattern is followed, for example, in case of sugar, Lahi and rice production. Various forecasting methods have been developed on the basis of fuzzy time series data, but accuracy has been a mercurial factor in these forecasts. In this paper, performance analysis of different fuzzy time series (FTS) models has been carried out. The analysis is applicable to any available time series data of product. In this paper performance analysis is done on the data of Indian agro products that include sugarcane, Lahi and rice. The suitability of different FTS models have been critically examined over the production data of the three agro products. The paper establishes the applicability of FTS methods also in the agriculture industry.