This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
I am trying to connect predictive models to a lift chart to view the ROC curve. I have tried a logistic regression, decision tree, and random forest model. Each time, I arrive at the same error message: "Target variable must be a factor". I am new to Alteryx, as well as to many things R related, so I'm assuming this is just something simple I am unaware of. Does anybody have any suggestions on what the problem may be, or any more general tips about using the Lift Chart Tool?
As mentioned by Peter, I would go over the Samples and Documentation just to see if any questions you're curious about could be answered there.
In terms of your error, I would need the workflow and data to see what exactly what's throwing it, but it looks like it's concerning your target variable. I would check that your Decision Tree, Forest Model, and Logistic Regression's are all using a BINOMIAL target variable. And then make sure your Target Level in your Lift Chart is properly pointing to one of these options (Ideally, the one for the desired response). Additionally, double check your data for your target variable field to make sure that there are no typos, etc. which would create a multinomial model, which the Lift Chart doesn't support.