Author: Johnny Ch Lok

Publisher:

Published: 2021-04-26

Total Pages: 196

ISBN-13:

⦁Can predict consumer behavior with web search?In behavioral economy view point, it can be applied to predict why consumers buy products from internet. Recent work has demonstrated that web search volume can "predict the present", meaning that can be used to accurately track outcomes, such as unemployment levels, auto and home sales and disease prevalence in near real time. Consumers are searching what for online can also predict their collective future behavior days or even weeks in advance. For example, specifically businessmen can use search query volume to forecast the opening weekend box-office revenue for feature films, first month sales of video games and the rank of songs, finding in all case that search counts are highly predictive of future outcomes from online google research. Finally, businessmen can reexamine previous work on tracking trends and show that, perhaps surprisingly, the utility of search data relative to a simple auto regressive model is modest.Nowadays, people increasingly use the internet for news, information and research purposes. From this perspective, it is a short step to conclude that what people are researching for today is predictive of what who will do in the near future. For example, consumers may search to prepare to buy a new camera, moviegoers may search to determine the opening date of a new film, or to locate cinemas showing it and individuals planning a vacation may search from a places of interest, to find airline tickets, or to price hotel rooms. So online can aggregately count of search queries related to retail activity. Movie going or travel might be able to predict collective behavior of economic, cultural, or political interest. Determining the nature of behavior that can be predicted using search, the accuracy of such predictions and the time scale over which predictions can be usefully made are therefore all questions of interest. Researchers have focused on the observation that search " predicts the present". For example, Ettredge et al (2005) found that counts of the top 300 search terms during 2001 to 2003 year were correlated with US Bureau Of Labor statistics Unemployment Figures; Cooper (2005) et al found that search activity for specific cameras during 2001 to 2003 year correlated with their estimated incidence and Eysenbach (2006) found a high correlation between clicks on sponsored search results of flu-related keywords and epidemiolopical data from the 2004 to 2005 year Canadian flu season.Thus, motivated, I indicate one example how investigates whether search activity is a systematic leading indicator of consumer activity by forecasting. For first example, supposing to opening weekend Box-office revenue for 119 feature films released in the united States between Oct. 2008 year and Sept. 2009. For second example, supposing to first month sales of video games across all gaming platforms, e.g. Xbox, Play station etc.) for 106 games released between Sept. 2008 and Sept. 2009 year. These search data can be collected from yahoo using research rank from the current and previous weeks. Can online search also predict the near future? A finding that may apply usually to a wide range of consumer behaviors, e.g. airline travel, hotel vacancy rates and auto sales and economic indicators, e.g. real-estate prices, credit card and confidence indicators. It seems all research based predictions simply models to build on publicly available information. For movies, baseline predictions can be used a linear model that includes production budgets, the number of screens on which each movie opened and box office projections from the Hollywood Stock Exchange (HSX) ( hsx.com) on online, play money prediction market that is known to generate information prediction. For video games, many of the key indicators of revenue, including production budgets and initial available.