These discussions might give you further insights and also contain links to some workflows. Maybe the Rossmann Kaggle case comes quite close to your question. Prediction of future sales are always a challenge since you will have to put into data the drivers that would influence your future sales like holidays and moving holidays (like easter), marketing campaigns and so on.
I would like to point you to a few resources where they tried to predict future sales at a german retail chain on Kaggle. Maybe you might get some useful insights.
One thing to consider might be special things like (regional) holidays or events like easter that will not be at the same date every year, and the holidays might not only affect the day itself but the days before and after. You might want to take that into account.
Trying to predict future sales on Kaggle
Interview with winner
I…
There is an example of the prediction of the number of customers to a restaurant using the powerful h2o.ai nodes of KNIME. Maybe you can adapt that:
And also as @HansS mentioned there are lots of nodes and example around. Below are a few links about models for numeric targets that might be helpful. Also you might check out specific time series themes (I do not have a collection of links about that right now).
I can think of a few examples that might show you the possible directions
This site has an introduction to model building with KNIME and uses an example that could be similar to your question:
Concerning the predictions you want you will have to think about how to set up the analysis and prediction. Would you make a prediction for every single product and dealer and what role does the time play in your analysis. Sales within a month or a week.
Then the quality of a model will very much de…
@ScottF provided us with simple workflow that shows how you would set up a regression model and do an evaluation using the RMSE ( Root-mean-square deviation) => the lower the better. The KNIME numeric scorer node has you covered there.
You could switch out the type of model used:
We had a discussion about that here:
And also further information about ways to determine the quality of a model (mostly 1/0 but check out the link).
I have to see if I have an example with a regression targe…
Typically you would use the Scorer nodes. Then there are a few entries dealing with numeric targets, you might want to check them.
Regression models (numeric Target)
predict how many future visitors a restaurant will receive (with H2O.ai)
3 Likes