The Data Mining Forum                             open-source data mining software data science journal data mining conferences high utility mining workshop
This forum is about data mining, data science and big data: algorithms, source code, datasets, implementations, optimizations, etc. You are welcome to post call for papers, data mining job ads, link to source code of data mining algorithms or anything else related to data mining. The forum is hosted by P. Fournier-Viger. No registration is required to use this forum!.  
Beginner Exploring Data Mining - Data set analysis
Posted by: ccmd00d
Date: May 30, 2019 09:25AM

Hi All,

I recently found this website / forum and it contains an mind blowing amount of information about data mining. I have a specific dataset containing the information below. Generally speaking an athlete does a series of training workouts defined as "workout type" and then participates in a event which either has a "postive" or "negative" result.

I would like to analyze the sequential patterns of training workouts which have the best result / outcome in an event.

a - workout type 1
b - workout type 2
c - workout type 3
.. - workout n

e - event 1 positive results
f - event 1 negative results
g - event 2 positive results
h - event 2 negative results
.. - event n positive/negative results

sequence examples

0 - {a,a,b,b,e}
1 - {a,b,c,f}
2 - {a,a,c,f}
3 - {b,a,a,e}
4 - {a,b,a,f,a,b,a,g}
......

The sequence will always end in a event, there could be multiple workouts/events in a pattern.

Q: What type of pattern recognition model can review the data set and indicate which patterns generally have the best results.

Q: The above doesn't take into consideration the timing between workouts and events (e.g. 7 days between workouts, or 14 days) How could that be layered on, does this change the model used?

Thanks for all who take a look at the above!



Edited 1 time(s). Last edit at 05/30/2019 09:25AM by ccmd00d.

Options: ReplyQuote
Re: Beginner Exploring Data Mining - Data set analysis
Date: June 10, 2019 06:03AM

Hi,

That is a very interesting topic. If you want, you can send me an e-mail to philfv8 AT yahoo.com

I can share some ideas with you about this and perhaps some unpublished paper that would be relevant for this.

Best regards,

Philippe

Options: ReplyQuote


This forum is powered by Phorum and provided by P. Fournier-Viger (© 2012).
Terms of use.