Search results

1 – 1 of 1
Book part
Publication date: 22 July 2021

Hsiu-Chen Fan Chiang, Pei-Xuan Jiang and Chia-Chien Chang

We empirically investigate the forecasting ability of USD-INR exchange rate volatility models by considering Google Trends data. Within a multiple regression framework, we use…

Abstract

We empirically investigate the forecasting ability of USD-INR exchange rate volatility models by considering Google Trends data. Within a multiple regression framework, we use historical volatility and liquidity measures to build our benchmark volatility model (Chandra & Thenmozhi, 2014). Moreover, we extend Bulut (2018) to incorporate indexes for 15 keywords (price-related, income-related, and liquidity-related) from Google Trends data into our benchmark volatility model to evaluate the forecasting ability of the models. Our results indicate that Google Trends data can improve volatility prediction and that among the groups of keywords that we consider, the price-related keywords have the best forecasting ability. Incorporating data on searches for “prices” into the model produces the highest reduction in the forecasting error: a 22.75% decrease compared to the level in the benchmark model. Hence, these empirical findings indicate that Google Trends data contain information that influences exchange rate movements.

Details

Advances in Pacific Basin Business, Economics and Finance
Type: Book
ISBN: 978-1-80043-870-5

Keywords

Access

Year

Content type

Book part (1)
1 – 1 of 1