Dataset Information

Web search queries can predict stock market volumes.

ABSTRACT: We live in a computerized and networked society where many of our actions leave a digital trace and affect other people's actions. This has lead to the emergence of a new data-driven research field: mathematical methods of computer science, statistical physics and sociometry provide insights on a wide range of disciplines ranging from social science to human mobility. A recent important discovery is that search engine traffic (i.e., the number of requests submitted by users to search engines on the www) can be used to track and, in some cases, to anticipate the dynamics of social phenomena. Successful examples include unemployment levels, car and home sales, and epidemics spreading. Few recent works applied this approach to stock prices and market sentiment. However, it remains unclear if trends in financial markets can be anticipated by the collective wisdom of on-line users on the web. Here we show that daily trading volumes of stocks traded in NASDAQ-100 are correlated with daily volumes of queries related to the same stocks. In particular, query volumes anticipate in many cases peaks of trading by one day or more. Our analysis is carried out on a unique dataset of queries, submitted to an important web search engine, which enable us to investigate also the user behavior. We show that the query volume dynamics emerges from the collective but seemingly uncoordinated activity of many users. These findings contribute to the debate on the identification of early warnings of financial systemic risk, based on the activity of users of the www.

SUBMITTER: Bordino I

PROVIDER: S-EPMC3400625 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Web search queries can predict stock market volumes.

Bordino Ilaria I Battiston Stefano S Caldarelli Guido G Cristelli Matthieu M Ukkonen Antti A Weber Ingmar I

PloS one 20120719 7

We live in a computerized and networked society where many of our actions leave a digital trace and affect other people's actions. This has lead to the emergence of a new data-driven research field: mathematical methods of computer science, statistical physics and sociometry provide insights on a wide range of disciplines ranging from social science to human mobility. A recent important discovery is that search engine traffic (i.e., the number of requests submitted by users to search engines on ...[more]

PMID: 22829871

Similar Datasets

Project description:BackgroundReal-time air pollution monitoring is a valuable tool for public health and environmental surveillance. In recent years, there has been a dramatic increase in air pollution forecasting and monitoring research using artificial neural networks. Most prior work relied on modeling pollutant concentrations collected from ground-based monitors and meteorological data for long-term forecasting of outdoor ozone (O3), oxides of nitrogen, and fine particulate matter (PM2.5). Given that traditional, highly sophisticated air quality monitors are expensive and not universally available, these models cannot adequately serve those not living near pollutant monitoring sites. Furthermore, because prior models were built based on physical measurement data collected from sensors, they may not be suitable for predicting the public health effects of pollution exposure.ObjectiveThis study aimed to develop and validate models to nowcast the observed pollution levels using web search data, which are publicly available in near real time from major search engines.MethodsWe developed novel machine learning-based models using both traditional supervised classification methods and state-of-the-art deep learning methods to detect elevated air pollution levels at the US city level by using generally available meteorological data and aggregate web-based search volume data derived from Google Trends. We validated the performance of these methods by predicting 3 critical air pollutants (O3, nitrogen dioxide, and PM2.5) across 10 major US metropolitan statistical areas in 2017 and 2018. We also explore different variations of the long short-term memory model and propose a novel search term dictionary learner-long short-term memory model to learn sequential patterns across multiple search terms for prediction.ResultsThe top-performing model was a deep neural sequence model long short-term memory, using meteorological and web search data, and reached an accuracy of 0.82 (F1-score 0.51) for O3, 0.74 (F1-score 0.41) for nitrogen dioxide, and 0.85 (F1-score 0.27) for PM2.5, when used for detecting elevated pollution levels. Compared with using only meteorological data, the proposed method achieved superior accuracy by incorporating web search data.ConclusionsThe results show that incorporating web search data with meteorological data improves the nowcasting performance for all 3 pollutants and suggest promising novel applications for tracking global physical phenomena using web search data.

Project description:BackgroundInternet search query trends have been shown to correlate with incidence trends for select infectious diseases and countries. Herein, the first use of Google search queries for malaria surveillance is investigated. The research focuses on Thailand where real-time malaria surveillance is crucial as malaria is re-emerging and developing resistance to pharmaceuticals in the region.MethodsOfficial Thai malaria case data was acquired from the World Health Organization (WHO) from 2005 to 2009. Using Google correlate, an openly available online tool, and by surveying Thai physicians, search queries potentially related to malaria prevalence were identified. Four linear regression models were built from different sub-sets of malaria-related queries to be used in future predictions. The models' accuracies were evaluated by their ability to predict the malaria outbreak in 2009, their correlation with the entire available malaria case data, and by Akaike information criterion (AIC).ResultsEach model captured the bulk of the variability in officially reported malaria incidence. Correlation in the validation set ranged from 0.75 to 0.92 and AIC values ranged from 808 to 586 for the models. While models using malaria-related and general health terms were successful, one model using only microscopy-related terms obtained equally high correlations to malaria case data trends. The model built strictly of queries provided by Thai physicians was the only one that consistently captured the well-documented second seasonal malaria peak in Thailand.ConclusionsModels built from Google search queries were able to adequately estimate malaria activity trends in Thailand, from 2005-2010, according to official malaria case counts reported by WHO. While presenting their own limitations, these search queries may be valid real-time indicators of malaria incidence in the population, as correlations were on par with those of related studies for other infectious diseases. Additionally, this methodology provides a cost-effective description of malaria prevalence that can act as a complement to traditional public health surveillance. This and future studies will continue to identify ways to leverage web-based data to improve public health.

Dataset Information

Web search queries can predict stock market volumes.

Publications

Web search queries can predict stock market volumes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets