Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques

Forecasting Rice Production in West Bengal State in India: Statistical vs. Computational Intelligence Techniques

Arindam Chaudhuri (Faculty of Post Graduate Studies and Research, Computer Engineering and Technology, Marwadi Education Foundation Group of Institutions, Rajkot, Gujarat, India)
DOI: 10.4018/ijaeis.2013100104

Abstract

Forecasting rice production is a challenging problem in agricultural statistics. The inherent difficulty lies in demand and supply affected by many uncertain factors viz. economic policies, agricultural factors, credit measures, foreign trade etc. which interact in a complex manner. Since last few decades, Statistical techniques are used for developing predictive models to estimate required parameters. Determination of nature of rice production time series data is difficult, expensive, time consuming and involves tedious tests. In this paper, we use Interval Type Fuzzy Auto Regressive Integrated Moving Average (ITnARIMA), Adaptive Neuro Fuzzy Inference System (ANFIS) and Modified Regularized Least Squares Fuzzy Support Vector Regression (MRLSFSVR) for prediction of Productivity Index percent (PI %) of rice production time series data and compare it with traditional Statistical tool of Multiple Regression. The accuracies of ITnARIMA and ANFIS techniques are evaluated as relatively similar. It is found that ANFIS exhibits high performance than ITnARIMA, MRLSFSVR and Multiple Regression for predicting PI %. The performance comparison shows that Computational Intelligence paradigm is a promising tool for minimizing uncertainties in rice production data. Further Computational Intelligence techniques also minimize potential inconsistency of correlations.
Article Preview

Introduction

Forecasting (Armstrong, 2001; Box, 2008; Brockwell & Davis, 2009; Chen, 2002; Lund, Brockwell & Davis, 2002) has been a topic of research actively pursued by decision scientists. It is an integral decision making element in real life systems. It is highly utilized in predicting different economic and business trends for improved decisions. The inherent challenge involves in accuracy of predicting the candidate data (Chatfield, 2000; Delurgio, 1998). The central aspect of improving prediction accuracy is to have good and efficient forecasting techniques. The problem has initially been handled using different Statistical techniques. However, after the emergence of Computational Intelligence techniques such as Artificial Neural Network (ANN), Fuzzy Sets, Evolutionary Algorithms, Rough Sets etc. (Altun & Gelen, 2004; Benardos & Vosniakos, 2007; Chaudhuri & De, 2009; Dash, Behera & Lee, 2008; Jang & Tsai, 1995; Kosko, 2008; Simpson, 1990; Zadeh, 1994; Zhang & Min, 2005; Zimmermann, 2001) as alternative techniques to conventional Statistical techniques with better performance have paved the road for increased usage of these techniques in areas of time series forecasting. The forecasters have relied upon various types of Intelligent Systems to make crucial decisions. Several Information Systems have been developed in recent years for modeling expertise, decision support and complicated automation tasks.

Every time series data is characterized by a unique cycle. Despite its apparent uniqueness from conditions that lead to boom times to triggers that result in reversals, historical narratives (Brockwell & Davis, 2009; Lund, Brockwell & Davis, 2002) suggest that most cycles display common features. Boom times are associated with periods of credit expansion and persistent increases in asset prices often followed by rapid reversals. These commonalities confirmed by different empirical work (Bordo, Eichengreen, Klingebiel & Martinez-Peria, 2001) suggest that developments in credit and asset markets of individual countries provide an early warning indicator of vulnerability in system that would be useful in assessing current situation and in discussions of possible policy actions. In light of this it is somewhat surprising that the empirical work in this area is scarce. Whatever reasons there may be at general level, the problem in doing this type of analysis for developed countries is compounded by scarcity of events that would qualify as a situation of crises resulting in stress. These situations are usually accompanied by an increased degree of perceived risk thus widening distribution of probable losses and uncertainty i.e. decreased confidence in shape of distribution.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 10: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 9: 4 Issues (2018): 3 Released, 1 Forthcoming
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 2 Issues (2012)
Volume 2: 2 Issues (2011)
Volume 1: 2 Issues (2010)
View Complete Journal Contents Listing