Powered by the Northstar engine developed at MIT and Brown University
Einblick is based on 6 years of research done at Massachusetts Institute of Technology (MIT) and Brown University as part of the DARPA Data Driven Discovery of Models (D3M) program and several NSF grants.
Key Features
The fastest engine:
The most natural interface
The first Visual Data Computing interface that enables playful interaction with data and supports desktops, large interactive whiteboards, and tablets and features real-time collaborative editing.

Visual Data Computing combines the best aspects of workflow engines, BI tools, programming environments, and collaborative tools.




Optimization
What-if
Progressive Computation Engine
The first progressive computation engine
All interactions take under a second regardless of the data size and results are then continuously refined in the background.
The Effects of Interactive Latency on Exploratory Visual Analysis. IEEE Trans. Vis. Comput. Graph. 20(12): 2122 2131 2014

The smartest assistants
Our award-winning smart assistants help to automatically find statistically significant insights and build models in sub-seconds rather than hours. It enables everyone to do tasks only data scientists can do now.
Cloud-enabled
Einblick can be deployed in the public or private cloud. We also allow airgap installation for the most critical applications.
Adding data can be as easy as dropping a file or you can connect easily connect to your favorite data sources with a click of a button. No need for expensive loading and data preparation steps. Einblick's progressive sampling engine takes care of the rest.
Based on years of cutting-edge research
Einblick is powered by the Northstar engine, which was originally developed by MIT and Brown University over 6 years of research. The results have been published in various top-tier systems, machine-learning, and human-computer interactions conferences and journals
Democratizing Data Science through Interactive Curation of ML Pipelines
SIGMOD2019
Northstar: An Interactive Data Science System
PVLDB 11(12): 2150-2164 (2018)
Towards Quantifying Uncertainty in Data Analysis & Exploration
IEEE Data Eng. Bull.41(3): 15-27 (2018)
Towards Interactive Curation & Automatic Tuning of ML Pipelines
DEEM@SIGMOD 2018: 1:1-1:4
Estimating the Impact of Unknown Unknowns on Aggregate Query Results.
ACM Trans. Database Syst. 43(1): 3:1-3:37 (2018)
Investigating the Effect of the Multiple Comparisons Problem in Visual Analysis
CHI2018: 479
Revisiting Reuse for Approximate Query Processing
PVLDB 10(10): 1142-1153 (2017)
How Progressive Visualizations Affect Exploratory Analysis
IEEE Trans. Vis. Comput. Graph. 23(8): 1977-1987 (2017)
Toward Sustainable Insights, or Why Polygamy is Bad for You
CIDR 2017
What you see is not what you get!: Detecting Simpson's Paradoxes during Data Exploration
HILDA@SIGMOD 2017: 2:1-2:5
Approximate Query Processing for Interactive Data Science
SIGMOD Conference 2017: 525
Controlling False Discoveries During Interactive Data Exploration
SIGMOD Conference 2017: 527-540
Towards a Benchmark for Interactive Data Exploration
IEEE Data Eng. Bull. 39(4): 50-61 (2016)
VisTrees: fast indexes for interactive data exploration
HILDA@SIGMOD2016: 5
The case for interactive data exploration accelerators (IDEAs)
HILDA@SIGMOD 2016: 11
Vizdom: Interactive Analytics through Pen and Touch
PVLDB 8(12): 2024-2027 (2015)
Automating model search for large scale machine learning
SoCC 2015: 368-380
PanoramicData: Data Analysis through Pen & Touch
IEEE Trans. Vis. Comput. Graph. 20(12): 2112-2121 (2014)
MLbase: A Distributed Machine-learning System
CIDR 2013