Application and Comparative Assessment of Data Mining and Time Series Forecasting Models to Indian Coal Mining Production and Employment Parameters

Abstract

Forecasting is designed to help decision making and planning before the actual event occurs. The main purpose
of the application of time series forecasting models to Indian mining data is to get insight into the wide-ranging
principles and methodologies for forecasting various parameters as well as current trends and future perspectives.
This paper highlights the application of some major methods of time series forecasting such as the Autoregressive
Integrated Moving Average (ARIMA) method, Regression method, Fuzzy Time Series method, Group Method of
Data Handling (GMDH Model), and Neural Networks. Based on a series of comparative analyses depending upon
the capabilities and limitations of each model, the perspective of the multi-model based forecasting approach is
presented.