Knime Shopping Cart Prediction [closed]

Question

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.

---

Questions asking us to recommend or find a tool, library or favorite off-site resource are off-topic for Stack Overflow as they tend to attract opinionated answers and spam. Instead, describe the problem and what has been done so far to solve it.

Closed 9 years ago.

Improve this question

I am new at Knime and I have a doubt about the GroupBy node.

I have a data set representing a Shopping Cart, with the following columns

• Session Number (integer)
• CustomerID (String)
• Start Hour
• Duration
• ClickedProducts
• AgeAddress
• LastOrder
• Payments
• CustomerScore
• Order

where Order (Char meaning Y=purchase or N = nonpurchase)

I saw in my data set that Session Number can have more than one row, so I used the GroupBy node and grouped by SessionID, but when I see the resulting table, I only see the column I have chosen.

I would like some advice about if I have to aggregate new columns with another node.

Thank you

Answer 1

What exactly is your question? If there is any KNIME example similar to this problem? I don't know any.

The grouping and the prediction can of course be done in KNIME. Use the GroupBy node to group by CustonerID and Session. Values of other fields can be aggregated in various ways. Then use the Partitioning node to partition your data into training and test set. Then use a learner e.g. the Decision Tree Learner node to train a model on the training data. Use the Decision Tree Predictor to use the trained model to predict the test data. Finally use the Scorer node to calculate accuracy and other quality measures. Of course you can also do cross validation in KNIME to score your models.

Hope this helps.