Sign up for our newsletter and get the latest big data news and analysis.

Domino Data Lab Platform Enhancements Improve Productivity of Data Science Teams Across the Entire Model Lifecycle

Domino Data Lab , provider of a leading open data science platform, announced new capabilities to further empower model-driven organizations to institute data science as an enterprise-wide discipline.
Updated with three new breakthrough capabilities — Data sets, Experiment Manager, and Activity Feed — Domino helps data science teams accelerate development and delivery of high-impact models through increased collaboration, reproducibility, and reusability across their organizations.

Today’s data science teams are not well equipped to collaborate and iterate on the work necessary to develop models that power their businesses and missions. Productivity suffers without a single view to track, organize, and asses experiments at various levels of detail, as iterations take longer and critical inputs like data are not clearly cataloged and versioned.
Additionally, data scientists spend 80 percent of their time wrangling data with data preparation, data engineering, and feature extraction tasks, robbing organizations of time and effort that could be spent on higher value research.

Domino provides a data science platform to rapidly develop, deliver and manage models. New enhancements to the platform announced today include:

  • Data sets: Data science teams lack the capability to find, share, efficiently consume and track the data used to develop models. Domino Datasets provide a high-performance, revisioned data store that enables data scientists to track, share, and reuse large file-based data resources so teams can iterate on research faster and accelerate model development.
  • Experiment Manager: Throughout the model development process, data scientists and data science leaders lack a single system of record to track, organize, and manage computational experiments, leading to duplication of work, lost insights and slower iteration cycles. The Experiment Manager is tailored to allow data scientists to organize,
    track, and visualize their experiments as they evolve over the course of their research.
  • Activity Feed – Without a record of activity, data science leaders struggle to optimize workloads, review past work, and manage change. The new Activity Feed provides data science leaders with context to understand changes in a project, including new experiment results, file changes, and discussion points. The Activity Feed facilitates quick review of the actions performed by team members, including who performed the action, what the action was, and when it was performed for more efficient workload review and change management.

“The Datasets feature has saved us a lot of time,” said Luiz Scheinkman, principal software engineer at machine intelligence company Numenta. “It used to take hours to process data, so we’d run those processes overnight. With Domino Data sets, we can preprocess the data and attach the preprocessed data to an experiment in 21 minutes. This means we can iterate, see our results, and make continuous improvements throughout the day — it makes a huge difference in expediting the whole model development process.”

“For too long, data science teams haven’t had software and systems that fit their unique workflows,” said Nick Elprin, CEO of Domino. “At Domino, we are laser focused on providing a platform that maximizes the creativity and productivity of data science teams. With Data sets, Experiment Manager and Activity Feed, we’re continuing to deliver capabilities that help organizations become model-driven.”

Sign up for the free insideBIGDATA newsletter.

Leave a Comment

*

Resource Links: