2 results
Search Results
Now showing 1 - 2 of 2
Item Restricted Quantifying stock market trading behavior using Google trends: the Philippine case(2013-12) Ubaldo, Victor Cesar I.; Mendoza, Gabriel Antonio M.; Alonzo, Ruperto P.Google Trends compiles search query volume of search terms. We relate this to the financial market by hypothesizing that search query volume can be an indicator of investor uncertainty. We assume that investors search for more information in the Internet when they are most uncertain about the state of the market. Conversely, investors may search for less information when they are optimistic about the market. Thus search terms related to finance may precede decreases in stock prices, while low search query volume might precede increases in stock prices. Moreover, if search query volume can help predict the movement of stock market prices, then profits may be made. Using a hypothetical portfolio in a time range of January 2004 to August 2013, we perform a strategy consisting of weekly decisions based on whether search query volume has relatively increased or decreased: long positions are made when search volume has relatively increased, and short positions are made when search volume has relatively decreased. In an alternate strategy, we make no transaction instead of making short positions. Using search volume data from Google Trends of 89 finance-related terms and using the Philippine Stock Exchange index as a basis for transaction gains, we found that the term success best predicts the stock market. We also test for Granger causality, in which we propose ·that success Granger causes the Philippine Stock Exchange index.Item Restricted Assessing the predictive capability of google search based negative sentiment indices on Philippine inflation(2025-01) Amazona, Oliver Wendell C.; Maronilla, Yohanan Francesco S.; Domingo, Gabriel Angelo B.This study evaluates whether internet search-based sentiment indicators can improve monthly inflation forecasts in the Philippines. We construct four Negative Sentiment Indices (NSIs) using Google Trends data on inflation-related search terms, namely, “price increase and price decrease”, “price hike” and “price rollback”, “pagtaas ng presyo” and “pagbaba ng presyo”, and “inflation and deflation”. These NSIs are designed to capture public concern over rising prices. Additionally, we generate a composite index (PC1) through principal component analysis to summarize the common trend across the four NSIs. Using Autoregressive Distributed Lag (ARDL) models, we assess the forecasting power of these sentiment measures. Cointegration tests show that NSI_2 is cointegrated with monthly inflation at the 10% significance level. However, over a 12-month rolling forecast horizon for 2021, ARDL models that include these variables generally fail to outperform a simple AR(1) benchmark. In terms of RMSE and Diebold-Mariano test results, most NSI-based models yield weaker predictive performance. These findings suggest that while sentiment data may contain useful information, their forecasting value in the Philippine context remains limited. Future research could explore mixed-frequency models using weekly Google Trends data or incorporate richer sentiment sources such as social media and news analytics to improve inflation forecasting in emerging markets.