IBM SPSS Modeler Review

Automated modelling, classification, or clustering are very useful. Customer support is hard to contact.


What is our primary use case?

Primary use case is feature engineering on a pre-prepared data set and mostly doing predictive modeling. Used on desktop. If it comes to ETL and data prep the tool is a waste of time...

How has it helped my organization?

  • Pretty much the automated modeling process helps us to get going so quickly.
  • A lot of jobs that are stuck in Excel due to the huge numbers of rows are tackled pretty quickly.

What is most valuable?

  • Automated data cleansing, transformations and imputation of missing data.
  • Some basic form of feature engineering for classification models, automated binning, etc. This really quickens the model development process.
  • Automated modelling, classification, or clustering are very useful as well.

What needs improvement?

  • Formula writing is not straightforward for an Excel user. Totally new set of functions, and it takes time to learn and teach.
  • Automating procedures: Writing macros is not easy and difficult to learn.
  • It is not integrated with Qlik, Tableau, and Power BI. Unfortunately…
  • Expensive to deploy solutions. You need to buy an extra deployment unit.

For how long have I used the solution?

Three to five years.

What do I think about the stability of the solution?

With some specific encoding, it simply does not work. I installed the English version on a Turkish Windows locale and SPSS Modeler literally halted. No fixes. You have to change locale and install from scratch.

What do I think about the scalability of the solution?

The server is not cheap and not scalable enough.

How is customer service and technical support?

Hard to contact and get any benefit.

Which solutions did we use previously?

I used SAS Enterprise Guide and Enterprise Miner. Compared to those, SPSS Modeler is easier to learn and utilize. 

when compared to Alteryx, Alteryx is a much more userfriendly tool to use. I switched to Alteryx because it can do ETL on big data, has extensive abilities in spatial analytics.

How was the initial setup?

Setup is a little problematic for desktop. A nightmare for server.

What about the implementation team?

Used a vendor team, and it sucked. Nobody on IBM side really cared. It is a big company "Big Blue", and you are always a miniature customer.

What was our ROI?

It got us a good amount of money with quick and efficient modeling.

It earns its money before the year-end.

What's my experience with pricing, setup cost, and licensing?

When you are close to end of quarter, IBM and its partners can get you 60% to 70% discounts, so literally wait for the last day of the quarter for the best prices if you don't want to get robbed by IBM. 

we switched to Alteryx because price performance advantages and great community and support.

Which other solutions did I evaluate?

I checked out RapidMiner, which is a good alternative. However, SPSS Modeler is more capable and automated. 

What other advice do I have?

Do not dive into the server directly. It is very hefty for just doing calculations that can already be done by SQL Server R or Oracle or teradata at hand... Maximize the utilization of the desktop tool first.

It is not a BI tool. It is pure analytics. It does not do reporting as well. And you unfortunately cannot publish your results to Qlik, Tableau, or Power BI.

this was another reason we switched to Alteryx.

Disclosure: I am a real user, and this review is based on my own experience and opinions.
1 visitor found this review helpful
Add a Comment
Guest
Sign Up with Email