Back to Community
Exogenous event data?

I'm looking for feedback about how one would derive value from a web service that provides information about non-market/external events (holidays, weather, disease, road construction, power outages). The idea is to have each event associated with a given geography (tornado in Tulsa will have no direct impact in NYC, its level of severity/importance and time period. I suspect this will have most (all?) interest in retail equities or where geographic location matters.

Some sources already exist (GDELT, weather), but I'm proposing to aggregate and make the service technically easier to integrate.

Would it be useful to identify (say) and correlate an unexpected drop in foot traffic at retailers might be attributable to a major event (eg rock concert), is it simply nice to know but doesn't move the needle?

I have more questions and will gladly be more specific in what I'm proposing, but don't want to dump too much info up front!

Thanks for reading (and commenting!)

2 responses

For your reference, some prior (and public) work on foot traffic: https://medium.com/foursquare-direct/foursquare-predicts-chipotle-s-q1-sales-down-nearly-30-foot-traffic-reveals-the-start-of-a-mixed-78515b2389af#.crtcrspwc

Generally, I'd say yes this type of data is very promising. However, it really depends on the details of the data and how it maps to a single stock, an industry, or something that cuts a cross section through the market. I'd love to hear more specifics!

Disclaimer

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 Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian 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.

Yep, I'm familiar with much of the alt data world, including foot traffic. What I'm proposing could be used to identify anomalous behavior in spending patterns. When you have expected pattern of activity (foot traffic, sales by day/hour, etc....) and your plot falls outside of expected bounds, does the analyst think it's a data issue or something else? If it can be explained by (say) a snowstorm, parade, bomb threat, etc...I understand one would say "great," but does it become insight that is essential in developing a trading strategy for (in this case) retail equities?