Timeseries pattern detection problem
\n \t
\n
<\/BR>
\n
\n \t
\n
<\/BR><\/p>\n
I’ve never dealt with any time series data – please help me understand if I’m reinventing the wheel or on the right track.<\/p>\n
I’m building a little hobby app, which is a habit tracker of sorts. The idea is that it lets the user record things they’ve done, on a daily basis, like “brush teeth”, “walk the dog”, “go for a run”, “meet with friends” etc, and then tracks the frequency of those and helps do certain things more or less often.<\/p>\n
Now I want to add a feature that would suggest some cadence for each individual habit based on past data – e.g. “2 times a day”, “once a week”, “every Tuesday and Thursday”, “once a month”, etc.<\/p>\n
My first thought here is to create some number of parametrized “templates” and then infer parameters and rank them via MLE, and suggest the top one(s).<\/p>\n
Is this how that’s commonly done? Is there a standard name for this, or even some standard method\/implementation I could use?<\/p>\n<\/p><\/div>\n
submitted by \/u\/ilyanekhay <\/a>
[link]<\/a><\/span> [comments]<\/a><\/span>\n<\/div>\n