In this paper, they are using Canadian debit card dataset. I am not sure where to get such a dataset.


My broad question is what kind of indicator can I use that indicates real-time economic activity of the people? Something that indicates how much people are buying on an hourly basis for an example. I am willing to look at unconventional datasets or willing to scrape information from scratch.

I thought about using Amazon review timestamps for example, but I know want to when people are buying something. Specially over the United States or smaller.


The projects developed by Alberto Cavallo and Roberto Rigobon could be a source of inspiation.

The Billion Prices Project is an academic initiative that uses prices collected from hundreds of online retailers around the world on a daily basis to conduct economic research. This page shows their most recent research leveraging high-frequency price data, as well as the US daily inflation index (updated monthly).

Here are the datasets on Online Micro Price Data, Global Retailers Data...

| improve this answer | |
  • $\begingroup$ Can you elaborate on why do you wish a sub-daily frequency? $\endgroup$ – emeryville Jan 19 '17 at 19:50
  • $\begingroup$ I don't work in the field of economics. But I have a very high resolution rainfall dataset (in temporal resolution of minutes). I wanted to do some "fun" analysis to see if people buy more when it rains outside. More time spent outdoors = more time spent shopping. Hence, I was looking for any dataset that would correlate with shopping behavior or economic activity like credit card transaction data. $\endgroup$ – maximusdooku Jan 19 '17 at 19:52
  • $\begingroup$ In econ, aggregating your data at the day level (and merging with the Billion Prices Project data) would still be called high frequency data ;-)! Note that the correlation could be reversed, when it rains outside I stay home. $\endgroup$ – emeryville Jan 19 '17 at 20:05
  • $\begingroup$ With online retailing, this trend may have reversed, right? Earlier not going out meant not shopping. Today, it might be the opposite. Thank you for the insight. $\endgroup$ – maximusdooku Jan 19 '17 at 20:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.