Question from a novice about traffic prediction

LeoLeo Member Posts: 4 Contributor I
edited November 2018 in Help

Hi all,

As stated in the subject, i'm just starting to learn how to use RapidMiner and I wish to predict the amount of traffic (number of cars) passing a point at certain times of the day, having the history (or data) for the past one year.

I have tried using the Neural Net operator in rapidminer with "vehicle_count" as the label (or target) but the predicted "count" when i apply the model is way off the mark.

What am i missing? Please, any help would be very much appreciated.





  • Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn

    Leo, welcome to the community!  Without seeing your dataset, it's hard to give a specific diagnosis of poor model fit, but one starting question is how have you structured your data in order to create attributes as potential predictors for the model?  Assuming you have your actual traffic volume as the label, specifically how have you structured your date/time stamp attributes?  It will probably be useful to use the "Date to Numerical" operator multiple times, in order to create attributes that correspond to day of week, time of day, etc., which will then be available as model inputs.


    I hope this is helpful!





    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
Sign In or Register to comment.