Product Capabilities

Data Profiling

Understand what is in your data without any data preparation, giving you complete data distributions with a full view of the content and structure of the data
  • Data Distribution at a Glance

    See the distribution of numerical and categorical data for every column in your data set
  • High and Low Frequency Values

    See the most and least frequently occurring in a data set
  • Predictive Metadata

    Downloadable and API accessible level of connected strength for each column, representing data quality

Identify Outliers and Surprising Data Points

Find outlying or unexpected data values in your data as well as the SQL queries to find them in your source data
  • See the Outliers in Your Data

    Understand what constitutes an outlier (both numerical and categorical) and which values fall into those ranges
  • Quantify the "Dirtiness" in Your Data

    See how many of the data values are outliers and how close the data is to maximum "dirtiness"
  • Find the Outliers in Your Data

    Use the automatically generated SQL queries to find the outlying data points, either for cleaning or additional investigation

Use Case Generation

Find use cases within your data by discovering the key predictors and connectors within a data set
  • Organizes your Outcomes by Connected Strength

    Outcomes are ranked by how well they correlate with the entire data set
  • Reveals Key Drivers for Each Outcome

    Ranked list of every column that correlates with any outcome of interest
  • Measures the Potential Quality of Each Use Case

    Suggests the final value in pursuing each use case with the information present

Persistent Data Monitoring

Automatically monitor all data silos within an enterprise for quality and health
  • Recurring Outlier Detection

    Instantly be alerted when your data begins to feature high amounts of outliers, pointing to issues in data collection
  • Ensure Data Integrity

    See how the structure of your data changes over time by monitoring the connection patterns within each column
  • Get a Leading Indicator of Data Changes

    By scanning your data at the source, you have an early indicator of changes in your data