Follow Datanami:
December 7, 2022

dotData Feature Factory Tech Adds Feature Discovery Capabilities to Azure Synapse Analytics

SAN MATEO, Calif., Dec. 7, 2022 — dotData, a pioneer and leader of the feature discovery platform announced that its Feature Factory technology is now fully integrated with and available on Microsoft’s Azure Synapse Analytics, that is an integrated cloud-native platform for data analytics. This new integration of dotData’s Feature Factory technology with Azure Synapse Analytics allows Azure Synapse users to easily and quickly discover 100X more features, derive deeper insights, and build more accurate models.

“dotData’s Feature Factory technology impressed us from the beginning,” said Karthik Chandrasekhar, Sr. Vice President of Decision Science at Exeter Finance LLC. “Feature Factory uncovered unique, explainable, and actionable insights using our data on day one. The goal-driven nature of the feature search process in dotData ensures that the features generated are truly valuable to our business.”

dotData’s Feature Factory technology seamlessly works in the Python workflow on Azure Synapse and allows users to explore millions of features from relational, transactional, temporal, geo-locational, and text data. With Feature Factory, data science teams can leverage multi-relational tables with billions of records to build ML-ready feature tables just in hours – without the tedious, manual hypothesis-test-rework process normally associated with building flat tables for Machine Learning.

Benefits of dotData’s Feature Factory integration with Azure Synapse Analytics include:

  • All features and functionality of dotData’s award-winning automated feature discovery technology
  • Runs on Spark-Pool provisioned by Azure Synapse – maximizing the speed of feature engineering
  • Compatibility with Azure ecosystem, e.g., supplying dotData’s AI features to Azure Machine Learning, access control using Azure Active Directory, etc.
  • Installed as a library, requiring neither changes on the existing Synapse Python workflow nor moving data outside of Azure Synapse

“Developing better ML models requires great features. The combination of dotData’s Feature Factory technology with the advanced capabilities of the Azure Synapse Analytics empowers data scientists to deliver higher quality models faster,” said Ryohei Fujimaki, Ph.D., founder, and CEO of dotData. “Bringing our technology to the Azure Synapse platform was an important goal for dotData. We are very excited to be working with Azure Synapse users to build better ML applications faster.”

dotData automates feature discovery and engineering, the most manual and time-consuming step in AI and ML projects. dotData’s proprietary AI technology automatically explores the complex relationship between large enterprise data sets comprised of dozens of tables, hundreds of columns, and billions of rows of data, discovering hidden features without the need for time-consuming trial-and-error manual processes. Until now, feature discovery and engineering have relied on a 100 percent manual effort that required a high degree of manual work and a continuous back-and-forth process between domain experts and data scientists to arrive at optimal features for ML models.

With dotData Feature Factory technology, data science and data engineering teams can augment in-house feature development and can explore millions of possible feature combinations to accelerate their workflows without additional expensive development resources. From rapid prototyping to explore new use cases or data sets, dotData’s Feature Factory technology expedites the process of discovering critical patterns and building accurate ML models. dotData’s Feature Factory technology is available on Azure Synapse as a Python library that integrates directly within the Python workflow, creating a seamless experience.

About dotData

dotData’s pioneering automated feature discovery and engineering platform solves the hardest challenge of AI/ML projects. Our Feature Factory technology discovers hidden gems for empowering your business as transparent, explainable features by connecting the dots within large-scale data sets in hours, without human bias. It enables data scientists to explore 100X more features, including those you’ve yet to imagine, and arguments AI/ML projects in an agile manner to deliver business value faster. In an era of rapid change, AI-discovered insights can be a game changer for business growth and innovation across industries. The power of dotData’s platform and ability to provide game-changing insights is why Fortune 500 organizations across the globe use dotData.


Source: dotData

Datanami