I have a dataset consisting of close to 15,000 entries, each entry consisting of -1150 potential input variables (most of which are generally empty) and 10 target variables. The input for each entry is an ordered subset of said 1150 potential input variables, so any value given denotes the position within this subset. (Example: Let's say A, B, C and D are input variables. If we have CAD and no B, C would say 1, A 2, D 3, and B would be empty.) My hope is that a good correlation between input and target can be found.
I'd like you to work with Python and Keras. Alternatively, please let me know which technology you'd like to employ.
The truth is that I don't actually *know* whether or not a decent correlation can be established, but I'd like you to try and see how good it'll get. I tried myself, but my knowledge in this field is rather limited at best, and I wasn't successful. This also means that there are no clear criteria for accepance - I'll accept any code which looks reasonable. The flipside is that I see no reason for this to be a lengthy project at all if you know what you're doing, so be mindful of this when bidding.
Thank you!
About the recuiterMember since Mar 14, 2020 Shashi Narsimhu
from Bekes, Hungary