What is our primary use case?
I have used Predictive Analytics for analyzing email-related data and data for healthcare products. Some of these products include:
- Water quality management
- What areas are going to be affected by bad water quality
- Pollution control
- Determining which areas are going to be polluted and with what types of pollution
What is most valuable?
The most valuable feature is its flexibility and the ability to integrate with SAS. It is easy to integrate with open-source technologies like R or Python.
I like the drag and drop interface. We can select datasets using drag and drop, for example.
We use the classification and regression functions for building models from emails.
What needs improvement?
There are not many people deploying models using this solution, which is a problem.
I have done some cross-development and have found that when I am building models with the open-source software, the accuracy is better. For categorical data, the models built by SAS Emailer are very complex compared to those built by the open-source version.
Technical support could be improved because they take too long to answer our queries.
Models that are created are a block box, and you can't see the details.
For how long have I used the solution?
We have been using this solution for one year.
What do I think about the scalability of the solution?
The scalability is good. We have more than thirty users.
How are customer service and technical support?
Technical support takes too long when we make an inquiry.
How was the initial setup?
We have four or five people who are in charge of maintaining this solution.
What other advice do I have?
For some of the things that we do, we use this solution in conjunction with SAS Forecast Studio.
This is a good solution, although the speed of the technical support needs to be improved.
I would rate this solution a seven out of ten.