Returning to Tides

[This article was first published on R – Win-Vector Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Fred Viole shared a great “data only” R solution to the forecasting tides problem.


The methodology comes from a finance perspective, and has some great associated notes and articles.

This gives me a chance to comment on the odd relation between prediction and profit in finance.

If there really was a trade-able item with low trade costs and the pattern of the tides: then there would be little point in predicting this security. One would already have a very profitable strategy in some variation of “buy below 2, and sell above 5” (or some variation of that based on slowly moving historic quantiles). For trading strategies we don’t so much want to predict all prices changes, but instead identify trade opportunities. A trading model at its very crudest is perhaps a time series of the symbols: “buy opportunity”, “sell opportunity”, and “no opinion”. And not a system that is required to reliably predict future prices from all time-periods. For example: if we have no net-position or holdings we can tolerate “don’t know” from a prediction algorithm.

However, I really like the “demonstrate solving a presumably easy problem” (such as tides or sunspots) before tackling a hostile one (such as equity prices).

To leave a comment for the author, please follow the link and comment on their blog: R – Win-Vector Blog. offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)