8 October 2018
It will be a familiar challenge to many data scientists and data analysts: you have built a predictive model to tackle a business problem and (you think) it is fantastic. And you want to prove it to your rather less technical colleagues in the business. But when you try and do that, with your ROC curves, your AUC measures and your hit rates, you mainly just see glazed-over expressions and it isn’t hitting home. Are we even speaking the same language?
With R and Python it is possible to make really good predictive models. To help you explain these models and to ensure the address the questions popping up in your business colleagues’ heads, Jurriaan Nagelkerke (data science and advanced analytics consultant at Cmotions) and Pieter Marcus (data scientist at De Persgroep Nederland) have put together an R package and Python module. The package and module have the same function and enable you to discuss the strengths of your predictive model for your business, with reference to various different programming languages, using four graphs (the cumulative lift plot, the cumulative gains plot, the response plot and the cumulative response plot). An example of this is given below with thie cumulative gains plot.
To introduce modelplotr and modelplotpy, we have written two articles:
We have also published the articles on modelplot.github.io.
In these articles we explain the graphs and what business questions they answer. We show how you install it and take a concrete example to then illustrate its functionalities.
We hope that modelplot[R/py] will help data scientists and data analysts to get the most out of their predictive models for the business. Do you have any questions/comments/suggestions? If so, please do let us know! You can do so via GitHub or by sending us an e-mail.
Do you want to know more about this subject? Please contact Jurriaan Nagelkerke using the details below
7 September 2022
We don’t know if you’ve heard already, but there is yet another crisis on our horizon:... read more
21 February 2022
Plan your calendar free and make sure you have plenty of party clothes in your closet,... read more
15 September 2021
Project-Friday At Cmotions, we love a challenge. Especially those that make us both think and have... read more