Author: augerdevops

blog image

Monitoring Machine Learning Accuracy in the Enterprise

Machine learning tools and practices continue to develop at a dizzying pace. The industry has moved on from running Python tools on the data scientist’s local laptop to hosted services from all the major cloud vendors that inexpensively build accurate enough models with many popular algorithms, both traditional (such random forest, support vector machine and

Read More
blog image

Monitoring Machine Learning Accuracy

The biggest problem in machine learning model accuracy is that all models degrade. They perform well initially but as the real world changes the models no longer capture the underlying structure. Both concept drift (the meaning and universe of values of the target dependent value being predicted) and data drift (the universe of values for

Read More
blog image

Putting “Automating AutoML” to Work

In my last post I discussed why we at Auger believe that AI will eat software. Enterprises will move beyond just solving their biggest problems with painstakingly built predictive models that teams of data scientists spend months on. Instead every enterprise application can build predictive models wherever they have access to data. Such predictive models can replace hand-coded rule of

Read More
blog image

Building Explainable Models with Auger.AI

For some of you it’s not just the accuracy of the predictive model that is important, but how explainable it is. In this webinar, Vladislav shows how to limit your search to the most interpretable algorithms. He also shows how to use the Auger.AI user interface to provide more information on what drives the model

Read More
blog image

AI Is Eating Software: How Second Generation AutoML Will Replace Software Development from the Inside Out

I just returned from a few weeks in Europe speaking at various AI and ML conferences. Notwithstanding our many posts on the topic, I actually don’t like to give talks about why Auger.AI is the best AutoML product. Instead what I have been talking about is where I see all of this innovation in AutoML heading. “First generation” Automated Machine Learning was focused on the

Read More
blog image

Auger.AI Cloud Launches!

We are very excited to announce the launch of Auger.AI Cloud!  Auger.AI Cloud is a fully hosted service eliminating the additional costs of paying for your own Amazon Web Services account. Only pay for what you use: choose the level of worker hours, storage, and numbers of users that you need to run your prediction

Read More
blog image

Auger Outperforms Competitors: The Google Update

Shortly after Microsoft released the AutoML product a few months ago, we published a comparison of Auger.AI versus Azure’s accuracy on Microsoft’s own chosen datasets. Specifically, in their paper behind their AutoML approach, Microsoft chose 89 OpenML datasets. As Azure did, we then compared that accuracy against H20 and TPOT as well. The results showed Auger with 4.5%

Read More
blog image

Timeseries Analysis with Auger.AI

Read More
blog image

Integrating Auger.AI Into Your Data Science Pipeline and Applications

AutoML is one of the most robust areas of innovation in applied machine learning. New products in this space from the likes of Google and new AI-focused startups are appearing constantly, all of which promise to make machine learning accessible to the masses without the need for trained data scientists. At its base, AutoML involves

Read More
blog image

Best Practices in Machine Learning Prediction

In this webinar, Vladyslav Khizhanov, discusses how to build optimal machine learning-based prediction models with our Auger.AI Automated Machine Learning Service. The following topics are covered in the discussion: Sizing your instances based on data size Choosing algorithms (i.e. restricting search) based on data dimensionality (rows and columns) and data distribution (edited) Restricting search based

Read More