The number of Google searches for this term just set a record and investors are noticing


Fast food has been on a roll as of late. The rate of Google searches for for the term “hamburger” is at all time highs, and investors in fast food stocks are enjoying tasty returns. Burger chains such as Red Robin (RRGB) and Jack in the Box (JACK) have more than tripled since 2011, with similar returns for more chicken-centric stocks like Popeye’s (PLKI) and Buffalo Wild Wings (BWLD).

We wanted to take a deeper look at the relationship between historical search trends and stock prices. Previously, we saw some evidence that the volatility of Tesla Motors share price was cointegrated with the volume of Google searches for the term “tsla”. We have also looked at how search traffic can be used to value a stock after it’s IPO.

For each stock symbol in our list of quick service restaurants, we extracted a historical time series of search volume with gtrends using the company’s name as the target search term.  Then we compared the correlation structures of each dataset:


From a price standpoint, this sector forms a tight cluster around its leader: JACK. Correlations between search volumes presents a more nuanced picture, with PNRA forming the center of the biggest cluster. We used two methods to visualize the structure, Heatmaps above and Minimum Spanning Trees below:


Overall, search volumes had a high correlation with their corresponding stock price levels. Just like the overall trend in searches for hamburgers, rising search volume represents a positive fundamental pressure on the chain’s stock price.

The volatility of log daily returns is presented a more complicated relationship with historical search volume. In some cases we found similar findings like we did in TSLA, while in others the relationship was firmly negative. These findings make us inclined to do a broader investigation of these correlations, expanding into a universe of stocks like the Nasdaq 100 or S&P 500 to get a more complete picture. This study was different in that we used the company name as the target search term instead of its ticker symbol.

Want to experiment with this data? You can learn to download historical search trends with the gtrends class yourself by reading our forthcoming eBook, Intro to Social Data for Traders, which is available for pre-order now. The release date is only a week away on February 26th, 2015 so pre-order now to make sure your get your copy as soon as it’s released.

price_level_cor price_vol_cor

Categories: Python, Quantitative Trading, R

6 replies »

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s