RapidMiner Review

Extensive features, Turbo Prep, Auto ML, good GUI and good stability

What is our primary use case?

We primarily use the solution for training and deploying various supervised and unsupervised models in the area of financial crime management.

How has it helped my organization?

It enables banks to quickly try and experiment multiple algorithms on same data set without the worry to have full time data scientists working. Focus shifts to data procurement, feature engineering and model validation rather than to worry about coding the same in other languages.

What is most valuable?

The GUI capabilities of the solution are excellent. Their Auto ML model provides for even non-coder data scientists to deploy a model.

The features the solution offers are quite extensive. We haven't had a chance to utilize all of them yet. The solution is constantly evolving to continue to be cutting edge.

What needs improvement?

The biggest problem, not from a platform process, but from an avoidance process, is when you work in a heavily regulated BFSI environment, like banking and finance. Whenever you make a decision or there is an output, you need to bill it as an avoidance to the investigator or to the bank audit team.

If you made decisions within this machine learning model, you need to explain why you did so. It would better if you could explain your decision in terms of delivery.  However, this is an issue with all ML platforms. Many companies are working heavily in this area to help figure out how to make it more explainable to the business team or the regulator.

For how long have I used the solution?

I've been using the solution for about 3 years.

What do I think about the stability of the solution?

The stability of the solution is good. We haven't faced any bugs or glitches. However, it does depend on the data model you are working on. So far, for example, we haven't modeled a big data site, so I'm not sure what stability would be affected in a case like that.

What do I think about the scalability of the solution?

In terms of scaling, it depends on the model you are deploying. When you build a model in a batch, scale is not an issue, because you can run it for hours or days to train the model. Currently, our company works within banks where we process around 10-20,000,000 transactions per day on a single site in the bank. 

You need to balance everything. In a real-time system, like the way we are operating, where we have a high case of having to send a response in less than one second, we need to have a balance. There are various ways we make sure, according to the deployment model, that we can respond within that one-second timeframe.

 Typically the kinds of people using the solution are data scientists and data analysts.

How are customer service and technical support?

In terms of technical support, whenever we face issues, the first place we go to are online forums or the solution's blogs. Typically, we can find an answer to our issues there. If there are issues that need to be fixed, they do offer extensions where you can write your own Python or R program to address them.

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

Before using this solution, we were mostly working on a native R and Python-based platform. It was more of an open-source tool. This is the first commercial tool we have used.

How was the initial setup?

In terms of the initial setup, you don't need to install the solution because it's a desktop version. It's the server of the deployment model which is a bit more complex. However, a desktop version is a standalone application and it's pretty straightforward. 

Unless you have some preliminary understanding of how machine learning models work, you will not be able to use the tool. It's not just with RapidMiner, it's on any tool. You have to check the parameters for every algorithm and you need to understand how algorithms work. Even with the excellent GUI and auto model capabilities, you'll still need the have a decent level of data science or machine learning knowledge.

What about the implementation team?

We have an in-house team of data engineers, data analysts, subject matter experts, data scientists and ML engineers who collaborate with bank's IT and business team to deliver the solution. This is handled by dedicated team working under Professional consulting group.

What was our ROI?

This is confidential as banks do not usually share this information. However, given the ML platform with auto model capability, I can say ROI would easily exceed at least 90%. This again depends on how many models are trained and deployed on a regular basis.

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

Within the company, we have about seven user licenses. When it comes to clients, they typically only have one license, which is more than enough for their use.

Which other solutions did I evaluate?

We did evaluate a few others like IBM SPSS. But Rapidminer is very user friendly and has a robust rating on various leading portal like KDnuggets. 

What other advice do I have?

We're in the banking and finance space, so mostly our clients use the on-premises deployment model. As part of compliance, it's required that data should not go out of the bank's boundaries or firewall.

This solution is a great tool for users that are experimenting and is an alternative to doing the coding and everything themselves. It's perfect for those who want to focus more on data analysis rather than spending days coding everything. Users can go pretty far because of the solution's Auto ML capability which cuts down on coding. It allows for great productivity.

I'd rate the solution eight out of ten.

Which deployment model are you using for this solution?


If public cloud, private cloud, or hybrid cloud, which cloud provider do you use?

Amazon Web Services (AWS)
**Disclosure: My company has a business relationship with this vendor other than being a customer: Partner
More RapidMiner reviews from users
...who compared it with SAS Enterprise Miner
Learn what your peers think about RapidMiner. Get advice and tips from experienced pros sharing their opinions. Updated: January 2021.
455,536 professionals have used our research since 2012.
Add a Comment