IBM SPSS modeler vs Python
October 06, 2021
IBM SPSS modeler vs Python
Score 7 out of 10
Vetted Review
Verified User
Modules Used
- IBM SPSS Modeler
Overall Satisfaction with IBM SPSS
IBM SPSS modded is used in building a forecasting model and a customer churn propensity model. Both were originally built 5 years ago and have been used on and off. Ideally, the same models would be easily rebuilt in Python or R but [the] modeler offers efficiencies better than other tools. This could also be because the [IBM] SPSS models were built by someone with a lot of experience [with] the tool.
Pros
- Feature selection
- PCA
- Ensemble models
Cons
- Reading how the model has been built
- Reusing with Python
- Can’t be reused with R
60% of all customers likely to churn identified by model built on modeler 95+% accuracy in forecast.
It did not have an impact since neither model [has] been used effectively.
Easier to build ensembles and also in forecasting than with Python. De trending and deseasonalizing data are far easier.
Comments
Please log in to join the conversation