IBM SPSS Modeler Reviews

I use it for my classes. One of the classes I teach is Advanced Analytics for students in the actuarial sciences area. My students are also using it for projects that they have to do as part of the process leading toward their degrees.

Before that, I was using it when I worked for IBM, as a consultant. I was doing a project for IBM in their analytics.

The main benefit is it makes things a little easier to do. If you want to solve a problem with R, for example, that's a lot more of a struggle. Essentially, R is a programming language. This package makes it more user-friendly, particularly for people who do not have a background in programming.

It's very easy to use. The drag and drop feature makes it very easy when you are building and testing streams. That's very useful.

I understand that it takes some time to incorporate some of the new algorithms that have come out in the last few months, in the literature. For example, there is an algorithm based on how ants search for food. And there are some algorithms that have now been developed to complement rules. So that's one of the things that we need to have incorporated into it.

Stability is very good.

I have no issues with scalability. It's pretty scalable. It makes pretty good use of memory. There are algorithms take a long time to run in R, and somehow they run more efficiently in Modeler. 

One of the things that I have not done in Modeler, and I'm not sure if the capability is there, is to run things in parallel. I'm pretty sure they have it but I haven't used it.

In a certain sense, I was involved in the initial setup. When I joined the university, I started to try to develop a joint agreement between IBM and the university. Because even two or three years ago, IBM was very reluctant to have universities use Modeler at no cost to the faculty or students. Now, fortunately, that has changed. Now our students can have a six-month license. That is very good. I was pushing for that when I was at IBM and then finished pushing for it when I joined the university.

Weigh the pros and cons. A lot of companies do not want to go with SPSS Modeler because of cost. What I have told some of my customers - I do some consulting as part of my job at the university - is, don't look just at the dollars and cents, look at benefits in your use case.

In terms of selecting a vendor, the most important thing to me is the availability of support.

Maybe I'm biased because I used it for a long time at IBM, but I would give it a 10 out of 10.

Building predictive models, including customer churn and lead generation.

Performance has been great. I've used it for about eight years or so, lots of flexibility. It continues to be a very flexible platform, so that it handles R and Python and other types of technology. It seems to be growing with additional open-source movement out there on different platforms.

We aren't putting that many machine-learning models into production. This is not the primary tool we use. This is more for me in terms of data exploration and knowledge discovery, that kind of thing. I really haven't done any production models in my current role. In previous roles I have.

In terms of cloud environments, it's actually a combination. Long story, but it's a combination of different things.

It's more for data, as a data repository. 

My experience so far using Modeler is good. I haven't noticed any issues with our current solution.

I don't use it for governance and security issues or for visual modeling. For data visualization we use ThoughtSpot, Tableau, Power BI. In terms of the graphic capability, those are existing platforms that have a larger user base, so it's unlikely that we'll use Modeler exclusively for data visualization.

I really can't think of anything off the top of my head because I feel like I'm under utilizing it as it is, because we're doing specific things. Two or three years ago, I would've said R and Python integration, but they've done that.

I've been using it since it was called Clementine. Every version seems to be better than the previous, but I don't think I've ever had any catastrophic failures, or any bugs that were significant enough to not have a work-around available.

The scalability was kind of limited by our ability to get other people licenses, and that was usually more of a financial constraint. It's expensive, but it's a good tool.

I haven't used tech support recently. We used IBM designates for things like training and the like, which has always been very good, but I can't really think of any issue that required any technical support.

It's a solution that was available when I entered the role. I have heard from others who were in the process of trying to start from ground-zero, and the tendency for them is to go with open-source because of the revenue model, obviously. 

I would say, if you're considering that open source-solution, definitely consider Modeler as well. Put together some kind of proposal that allows you to figure out how much time it's going to take individual people to create those models, versus being able to have an out-of-the-box solution that gets your team going more immediately.

Support is another benefit of going with Modeler over open-source. SPSS has been around for a long time. IBM acquired them, and they've added functionality and features to meet the needs of growing data science populations.

The primary use case is to augment our sales processes, to help our call center determine which customers to call, which products to push to those customers. 

Thus far it's been pretty effective. In a recent sample that I pulled, it successfully predicted two-thirds of our sales in a given week.

We're running batch, overnight, and I believe we have three machine-learning models in production at the moment.

We have separate models for our US call center and our UK call center. Each one is designed to do a customer recommendation, where it determines which customers should be ready to buy today, based on the recency of their last purchase, how frequently they purchase. And then it scores the opportunity with that customer, based on how much money they spend with us. It gives the salesmen a ranking of which customers are their biggest opportunity on that day, and they just go down that list and call them. It generates pretty good sales.

And then we have a second model that does item recommendations, based on some association modeling. The association model tells the sales rep what product that customer should be buying, based on their sales purchase history.

We're on-prem. I find the on-prem to be a pretty seamless experience, it flows directly from our data warehouse into the Analytics Server, and then we're able to deploy it back to the data warehouse for deployment into our CRM system.

The benefits are that this product makes us a more efficient sales staff. We're reducing the inefficiencies in the buying patterns of our customers, by calling them when we know they're ready to order, instead of waiting for them to call us. It makes us more effective in our calling practices as well. We're not just cold-calling anymore, we're actually calling customers we know are ready to buy.

In terms of our go-live process changing, I believe we're following some pretty standard practices there. I don't think we've changed too much, other than which servers we were using as production servers.

I think the ease of use in the user interface is the best part of it. The ability to customize some of my streams with R and Python has been very useful to me, I've automated a few things with that.

We don't use SPSS Modeler for governance or security issues.

Regarding visual modeling, it is not the biggest strength of the product, although from what I hear in the latest release it's going to be a lot stronger. I'm excited to see what they have coming down the line, because I know that's an area they've focused on the most recent release, and I'm not on the recent release yet. I haven't really been able to leverage it to make any productivity improvements with our data science or analytic teams. Most of my visualization gets done through Cognos.

Like I said, I'm really excited about the enhanced visualization that I know is coming down the pipeline. That, to me, has always been the biggest flaw in using this. It's very difficult to get good visualization.

I think mapping for geographic data would also be a really great thing to be able to use.

Also, I think it could be marketed better, actually. I think there's a lot of confusion among customers about whether they should be using SPSS Modeler, or DSX. And even some of the partners I've spoken to about it, they've given me some conflicting opinions on which one I should be using at my level of scale.

I haven't had many issues with stability. The only stability concern I ever had was just certain credentials, if the job failed multiple times it deactivated the credentials, and then became a whole process with IT to get the credentials reactivated to get the stream running again.

Scalability is infinite, because it can just spit out straight to our enterprise data warehouse, and we can use that to deploy anywhere.

 I haven't needed technical support. The product works pretty well.

I came to the World of Watson Conference in 2015, and when I saw SPSS Modeler and what it could do, I just sampled it, and it really, to me, spoke volumes about some of the inefficiencies in the way we were doing business. And, as a brand new BI practice at a company that never had one before, I was just trying to build my practice from the ground up, and I didn't want to limit it to just BI reporting, so I took on the challenge of bringing in this new software, and staking my reputation on it, and it's paying off.

The reasons we eventually chose this solution were that we were made a very good deal on the Gold package, which gave us more capability. I think without Collaboration and Deployment Services it wouldn't have been a worthwhile investment for us and it would have failed on the deployment. So that deal we got on the Gold package really sealed the deal for us.

What's most important when selecting a vendor is the proven practice of the product. Knowing that the product has had success for numerous other customers in the past for similar use cases, for similar types of customers. I think knowing that there are a variety of partners out there with expertise in the product is a very strong selling point for me. I don't like going to things where I can't get help, if I get stuck.

It was a little complex, but the person we work with, Chris Thomas, did a fantastic job walking us through it.

There were just a lot of steps and components to it. We bought the Modeler Gold package, so we had to consider CNDS, we had to consider ADM - we had a whole bunch of different components that had to get set up simultaneously. And when upgrading, we have to upgrade all of those components simultaneously in order to keep using it.

We ended up working directly with an IBM partner, but we also worked with Revelwood and LPA.

I'd give it a nine out of 10. I really think that for someone who is not the strongest programmer on the planet, but is trying to learn and trying to put together some of these basic data science projects, it's a really valuable tool, the UI is very user friendly. So, it definitely launched my journey into becoming a data scientist, and three years later I'm becoming a lot stronger with it.

In terms of advice, the right partner can make all the difference. You need somebody who you can bounce questions off of when you get stuck, because you're going to get stuck, it's just inevitable. If you haven't implemented data science and predictive modeling before, you're always going to hit a challenge that is unique to your data, or to your process, and you need somebody who can lend the weight of experience to just talk you through it.

People data, survey insights, HR analytics, nominal data, relational data, SEM modeling, logistic regression using nominal or ordinal groups.

Quickness and ease of use with the guarantee of robust modeling techniques and trustworthy accuracy.

Quick insights.

Easier coding language that is more flexible with other platforms. More server capabilities. More graphics.

Customer segmentation and churn analytics.

We get best results in customer segmentation and churn analytics and we have retained our customers. Our retention score has improved as a result of these projects.

We haven't used machine learning solutions yet.

Our business units' capabilities with SPSS Modeler is high. They no longer waste time on modeling and algorithms, meaning they are not coding any more. For example, segmentation projects now take one to three months, rather than six months to a year, as before.

In the future, SPSS and Cognos Analytics will be integrated. We will be using the two products together.

We have not yet used IBM SPSS Modeler for governance and security issues.

It would be helpful if SPSS supported open-source features, for example, embedding R or Python scripts in SPSS Modeler. We don't need that now, but in the future it may be useful.

We haven't suffered from any stability issues. It's a stable product.

We haven't had any performance problems. The product runs every data volume performantly and produces results.

We are doing our solutions in-house, but sometimes we require local support from IBM partners, but not too often. We are happy with the support the partners provide.

We have SPSS know-how in our company, and other products are not as stable as SPSS. Also, we have local support in Turkey.

Straightforward. It was not complex.

Oracle and SAP. SPSS, however, is widely known and widely used in Turkey. University students learn it, so it's easy to find professionals to work with it.

You should analyze your needs and your data, your projects. There is a lot of choice in data analytics. Which one is best depends on your needs and your budget. It depends on what you are looking to achieve.

Rapid prototyping, pre-production of models before roll out.

We put very few machine learning models in production, but we test a lot of them though. Nothing is real-time.

I can't say that our go-live has changed compared to a previously problematic base process.

We don't use IBM SPSS Modeler for governance and security issues. I can't talk about the visual modeling capability.

It's very stable, although it is not as user friendly as it could be.

I don't use it for any high performance applications.

I have not used technical support.

I'm not in the budget decisions, but IBM was chosen because of usability. It's point and click, whereas the other out-of-the box-solution, or open-source solutions, require full-on programming and a much higher skill level.

I was not involved in the initial setup.

Usually open-source solutions.

If you're hiring a data scientist, you don't need IBM SPSS Modeler. If you only have an MBA who needs to be running proofs of concept, then buy IBM SPSS Modeler.