The key feature is the automated model-building. It has a good UI that will let people who aren't data scientists get in there and upload datasets and actually start building models, with very little training. They don't need to have any understanding of data science. 

It also has the REST API which is used pretty extensively. It's a bit more feature-full and it is a great tool for customers who actually want to integrate ML models into their business systems, products. and workflows. This is a challenge we see with with machine-learning initiatives at a lot of companies: You hire data scientists. You give them a problem. You give them the data. You train them on what they need to do with it. And then they build a model but you can't just drop that model into your ERP. Or if you have supervisory systems, industrial systems like IoT applications, you can't just drop a model into that. Darwin and the REST API it has available abstracts all that away and makes it very easy to integrate into existing systems.

The accuracy, like anything else, is dependent on having a good data set. If you give it the right data — good, clean datasets — Darwin is as good, if not better, than anything out there. Even if, in its automated fashion, it initially returns something that may not be quite as accurate, the fact that you're able to iterate and correct the data quality issues quickly, rather than the traditional process where you work with the data scientists and you start getting results weeks or months later, enables you to iterate quickly to get to a higher level of accuracy.

Darwin's automatic assessment of the quality of those datasets does a good job. Additionally, its partner network provides industry-specific tools that integrate and work alongside Darwin, or wrap around Darwin, and provide a lot of additional capabilities. Darwin does a good job but where it doesn't, SparkCognition has a great partner network that has developed industry-specific things that solve problems that Darwin might not solve out-of-the-box.

The solution's interactive suggestions on how to address dataset issues to make the data ready for algorithmic development is interesting. It depends on the specific data set. Sometimes they're spot-on and sometimes it's a matter of the interpretation dataset. Overall, they're helpful and they definitely make the machine learning more approachable.

The model processing is valuable. However, what I find most valuable of all is the time. With the team, we could have maybe reached these numbers, but it would have taken double or triple the time to reach these numbers. So, with the Darwin tool, we are able to test our models constantly. We can go with the optimal way in minutes. That has been a game changer for us.

The tool is very powerful and has many benefits. The time reduction in the modeling testing is the most valuable thing at the moment. The time that Darwin saves for us to be constantly testing the model has been a game changer for us. We could have reached these numbers maybe with qualitative analysis, but it would definitely be with more time. With Darwin, we are reaching these numbers very quickly.

The solution tracks the health of models. We're also looking into the possibility of having alerts. So, when Darwin can find an optimal model better than what we currently use, it lets us know.

In regards to removing null values and the like, it did do so but that's a pretty basic task. I don't need an entire tool to do something like that. I can do it very quickly in Python or R.

In terms of streamlining a lot of the low-level data science work, it does a few things there.

The most valuable feature is the model-generation. With a nice dataset, Darwin gives you a nice model. That's a really nice feature because, if we're doing that ourselves, it's trial and error; we change the parameters a little and try again. We save time by just giving the dataset to Darwin and letting Darwin generate a model. We find the models it generates are good; better than we can generate.

Another feature that is really nice is that Darwin gives you a first impression of a dataset, even if the dataset is a bit dirty. Darwin can give you information about a particular column or feature where there is a lack of information. As a result, we know to do another round of manual cleaning. That's a helpful feature too.

Darwin has also increased our productivity, maybe by as much as 20 percent.

I found Darwin a simple tool. It's a really helpful. It's easy to clean data forwards and backwards when we need to analyze it and to get a quick model.

The solution’s ability to capture complex relationships over time and the resulting accuracy of its predictions is good. You can solve complex problems with it. It's easy to use. It gets good accuracy.

I find it quite simple to use. Once you are trained on the model, you can use it anyway you want. 

It was quite comfortable to use.

The thing that I find most valuable is the ability to clean the data. 

In addition, it helps us to create a model. Instead of trying things one-at-a-time, Darwin helps us to improve models and select the best one.

The solution helps with the automatic assessment of the quality of datasets, such as missing data points or incorrect data types.

I really liked how there were a lot of abilities to tweak how it was going to run: How many folds you were going to use and cross-validation. 

Also, while it wasn't super-relevant to me, I liked the data checking feature where it looks at your data and sees how viable it is for use. That's a really cool feature. Automatic assessment of the quality of datasets, to me, seems very valuable. I didn't use it too much but it looked like it worked well from the few times that I was involved in that feature. That's a great feature to have because cleaning datasets is a pain and there are often errors even after it has been cleaned. So to have another check to say, "Oh wait, there might be a problem here," is really useful.

Darwin's interactive suggestions are useful in how it could, for example, find what a more appropriate data type might be when you have it in the wrong data type. And sometimes it would tell you, "Oh, maybe you just want to drop this," especially if it was redundant or there was low variance. It's useful to see where there might be issues. I wouldn't necessarily trust it to do all of that itself. I would say it's more of a check rather than a be-all-end-all cleaning tool.

I found the interface really clean and easy to use.