A comparative study of neural-network & fuzzy time series forecasting techniques - Case study: Marine fish production forecasting

Abstract

<span style="mso-ansi-language:EN;mso-fareast-language: EN-IN" lang="EN">Various forecasting methods have been developed on the basis of fuzzy time series data, but accuracy has been matter of concern in these forecasts. Historical data of marine fish production of India have been taken to implement the model; as such time series data obtained through sample survey are likely to be imprecise. Fuzzy sets theory of¹ and fuzzy time series models introduced by^2-5, were applied in this study.<span style="mso-bidi-font-size:9.0pt;font-family:Arial;mso-ansi-language:EN; mso-fareast-language:EN-IN" lang="EN"> <span style="mso-ansi-language: EN;mso-fareast-language:EN-IN" lang="EN">The forecast to marine fish production have also been obtained by developing an Artificial Neural Network (ANN) model using Back propagation algorithm. It is aimed to find the marine fish production forecast for a lead year by using different fuzzy time series models and back propagation algorithm for the forecast. Forecasted marine fish production, obtained through these techniques, has been compared and their performance has been examined. Present infers that ANN produces more accurate results in comparison of fuzzy time series methods.

</span></span></span>