Back

Methods for pulling long term daily data from Google Trends?

Hello QuantConnect community!

   I was wondering if anyone had any recommendations for me for how I might go about pulling daily trend data from Google as it is made available. Is it even a worthwhile project? I am very keen on figuring out how to automate my data collection with this as the alternative is a very slow manual process. I will be normalizing the data from 2004 onward for a variety of search terms but obviously would prefer to do this using a Python program instead. 

Thanks for any help as always and let me know if you have any questions on my intentions!

Update Backtest







0

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Hi Sam,

Google Trends has been attempted by many but then not used I believe because it imposes a look ahead bias due to the way it scales the historical relative search values. I'm not sure it translates well over time to a strategy. This was the primary reason it never became a custom data source in QuantConnect. 

Maybe it's different now its been a few years? 

Best
Jared

1

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


I read alot of those comments - I guess it doesn't work even with 'pytrends' data normalization? I was going to do it myself, translating monthly 0-100 trends into daily data since 2004, but if many others likely more skilled than I have failed, I guess I'll leave this alone for now :(

Thanks though!

0

Update Backtest





0

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Loading...

This discussion is closed