SAS Enterprise Miner Review

Enables Statistical Modeling Of Data Using Base SAS Although Limited GUI is a drawback

What is most valuable?

It enables statistical modeling of data using Base SAS (another product from the same vendor) as the backbone. One can create visual models to see the steps involved in modelling of data.

How has it helped my organization?

Using Base SAS, one can do statistical analysis of data. However, Base SAS is completely code driven (doesn't have any GUI). This is a big limitation as statisticians, often, are not so good at programming. SAS Enterprise Miner extends GUI capability and visual appeal to Base SAS, to a good extent.

What needs improvement?

The product is still not as intuitive as one would like it to be. For example, a competing product, IBM SPSS Modeler is nearly completely GUI driven, while SAS Enterprise Miner lacks some features. Plus it is prohibitively expensive and is not available with perpetual licensing.

For how long have I used the solution?

Over seven years.

What do I think about the stability of the solution?

Not many.

What do I think about the scalability of the solution?

It gets painfully slow with raw data in excess of 50GB and one has to go for multi-socket server based licensing that gets prohibitively expensive.

How are customer service and technical support?

Email based support has a turnaround time of about 24 hours which is not good.

Which solution did I use previously and why did I switch?

We use multiple solutions simultaneously.

How was the initial setup?

Initial setup was OK. Not too complex, not too simple.

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

It has an annual licensing policy with an annual renewal of almost 35%. The initial cost (and therefore renewals) are extremely expensive. One can possibly invest that much in hardware and possibly go in for products like R that are very cheap in terms of total cost of ownership.

For clarity, R is an open source tool but with the limitation that it's an in-memory tool. When dealing with large datasets, RAM becomes an issue. R is much more flexible. So, rather that investing in a SAS license, we prefer to invest in high RAM hardware (256/512GB RAM) and use R.

Another issue with R is that native version is a single core product. Even if you have a multi-core CPU, it uses a single core. However, Microsoft R, a free version from Microsoft, does away with that limitation. There is also a multi-core (paid) version of R available through Microsoft which does away with in-memory limitation and works out to be much cheaper than SAS Enterprise Miner.

Which other solutions did I evaluate?

IBM SPSS Modeler, RapidMiner, R.

What other advice do I have?

Be sure of your needs. In most scenarios, the pricing of SAS Enterprise Miner is not justified by the value it adds.

Which version of this solution are you currently using?

**Disclosure: I am a real user, and this review is based on my own experience and opinions.
More SAS Enterprise Miner reviews from users
...who compared it with Anaconda
Find out what your peers are saying about SAS, IBM, Knime and others in Data Mining. Updated: January 2021.
456,495 professionals have used our research since 2012.
Add a Comment