Development of tourism infrastructure is vital as the tourism
industry is contributing significantly to India's foreign
exchange earnings. This study forecasts month-wise international
tourist flows to India using univariate time-series techniques
namely Multiplicative Seasonal Autoregressive Integrated
Moving Average (MSARIMA) and Holt-Winters Multiplicative
Exponential Smoothing for seasonally unadjusted monthly
data, spanning from January 1998 to June 2007. In-sample
forecasting reveals that exponential smoothing model outperforms
Autoregressive Integrated Moving Average (ARIMA) (1, 0,
0) (1, 1, 1)12 model in terms of lower Root Mean Square
Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute
Percent Error (MAPE). Finally, both the models have been
used to forecast monthly international tourist arrivals
to India, 15 months ahead from July 2007. This will help
the government and hospitality industry for better tourism
strategic planning.
Indian tourism industry has witnessed an impressive growth
rate in recent years in line with the rapid growth in international
tourism all over the world. Due to its rich cultural and
geographical diversity, India has emerged as one of the
leading international tourist destinations. The share of
foreign tourist arrivals to India, which was just 0.37%
of the world arrivals in 2001 has gone up to 0.53% in 2006.
According to India Brand Equity Foundation (IBEF) tourism
sector contributed 5.9% of the Gross Domestic Product (GDP)
in the year 2006-07. Tourism also contributes significantly
to India's foreign exchange earnings, which grew from $6.17
bn in 2004 to an estimated $11.96 bn in 2007 (Ministry of
Tourism, Government of India). Since, tourist arrivals are
affected by the economic environment and seasonal factors
like weather, special events, etc., precise forecasting
of tourism demand is essential for tourism and hospitality
industries, so that they can undertake diverse supply measures
to meet future demand and its variations. |
