Breaking timeseries data into sessions
Edit: Since writing this I've found lots of ways to simplify this solution, for instance making use of the lag function in MS SQL, or MySQL solutions using variables, but I'll leave this here anyway! Problem: You have a lot of data about users interacting with your site, with a UserID and timestamp for each transaction. [...]
willycs40 Uncategorized
Optimising with Simulated Annealing
Tasked with optimising a complicated system, I went down the route of heuristic optimisation and ended up creating a simulated annealing algorithm in R. I don't want to go into too much detail about how the model works, because that has been done well enough elsewhere, but essentially it is a smart way of searching through all [...]
willycs40 Uncategorized Simulated Annealing