Predictive data mining on Average Global Temperature using variants of ARIMA models

Author

Babu, Narendra ; Reddy, B. Eswara

Author_Institution

Dept. of Comput. Sci., JNTU, Anantapur, India

fYear

2012

fDate

30-31 March 2012

Firstpage

256

Lastpage

260

Abstract

This paper analyzes and predicts the Average Global Temperature time series data. Three different variants of ARIMA models: Basic ARIMA, Trend based ARIMA and Wavelet based ARIMA have been used to predict the average global temperature. Out of all the three linear models, it has been observed that Trend based ARIMA method outperforms basic ARIMA method and Wavelet based ARIMA method outperforms Trend based ARIMA method. MAPE (Mean Absolute Percentage Error), MaxAPE (Maximum Absolute Percentage Error) and MAE (Mean Absolute Error) have been used as a performance measures to compare between the models.

Keywords

atmospheric temperature; autoregressive moving average processes; data analysis; data mining; geophysics computing; time series; wavelet transforms; ARIMA model variant; Basic ARIMA; MAE; MAPE; MaxAPE; Trend based ARIMA; average global temperature; linear model; maximum absolute percentage error; mean absolute error; mean absolute percentage error; performance measure; predictive data mining; time series data analysis; wavelet based ARIMA; Data models; Forecasting; Measurement uncertainty; Predictive models; Temperature distribution; Temperature measurement; Time series analysis; Average global temperature; Predictive data mining; Time series forecasting; Trend-based ARIMA; Wavelet-based ARIMA;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Engineering, Science and Management (ICAESM), 2012 International Conference on

Conference_Location

Nagapattinam, Tamil Nadu

Print_ISBN

978-1-4673-0213-5

Type

conf

Filename

6215607