Collaborating Authors

An Open Source AutoML Benchmark Machine Learning

In recent years, an active field of research has developed around automated machine learning (AutoML). Unfortunately, comparing different AutoML systems is hard and often done incorrectly. We introduce an open, ongoing, and extensible benchmark framework which follows best practices and avoids common mistakes. The framework is open-source, uses public datasets and has a website with up-to-date results. We use the framework to conduct a thorough comparison of 4 AutoML systems across 39 datasets and analyze the results.

Feedzai Unveils AutoML: Automated Machine Learning That Fights Fraud in a Fraction of the Time


By automating tasks such as feature engineering and machine learning model creation, data scientists are now able to create fraud prevention solutions as much as 50 times faster than is possible with the traditional data science workflow. Increasingly intelligent fraud attacks require teams to act faster than ever to fight evolving fraud risks on multiplying fronts. Feedzai AutoML enables teams to deliver results faster and to quickly expand to new use cases, channels, and geographies. Now, data scientists can quickly generate the most relevant features and models, and adapt more quickly to fast-evolving fraud schemes and attack vectors. Feedzai AutoML works by automating and integrating the most repetitive and time-consuming steps in the data science pipeline, freeing data scientists to perform more consequential tasks.

Crowdsourcing ML training data with the AutoML API and Firebase


Want to build an ML model but don't have enough training data? In this post I'll show you how I built an ML pipeline that gathers labeled, crowdsourced training data, uploads it to an AutoML dataset, and then trains a model. I'll be showing an image classification model using AutoML Vision in this example but the same pipeline could easily be adapted to AutoML Natural Language. Here's an overview of how it works: Want to jump to the code? The full example is available on GitHub.

dotData's AI-FastStart Program Helps BI teams Adopt AI/ML with AutoML 2.0 dotData AutoML 2.0 Solutions for Enterprise


AI-FastStart was born as a direct response to a rapidly changing BI & Analytics world. AI/ML has become a critical technology investment but most organizations still suffer from scaling AI/ML practices. The program was designed around four core principles: The right platform, education, providing fast time-to-value, and to be easy to deploy and implement. We provide the best software, host it on the best possible platform, bundle the right depth and amount of education for unlimited users, and tailor services to enable an operational first use case in as little time as feasible. Whether your BI team has no experience with AI/ML, or are full experts, dotData AI-FastStart will help them become more proficient, more successful and will ultimately provide an exceptional predictive analytics foundation for your organization for years to come.