Google Trends data is messy. It’s normalised, it’s abstracted and it’s aggregated to a very coarse layer. In this talk we’ll discuss how to turn Google Trends snapshot into large datasets you can actually use to compare terms across countries in a meaningful way by using a chaining methodology and borrowing tech from the world of Finance. In this talk the attendees will learn how to generalise the concept of an ETF from finance to google trends data, how to handle normalised data to behave in a more real world way and in doing so learn how viewing a problem from a different angle, or taking knowledge from different domains, can unlock new innovative data science techniques.
Technical Level: Technical practitioner