Lityx Product News

Current Version

LityxIQ 5.0.4

What’s New & Improved

  • The DeepNet neural net algorithm is now available to all users in Beta testing. Please provide feedback on your use of the algorithm in your machine learning models.
  • Additional catching and attempted fixing of import errors, and provision of detailed information on the data line causing any import errors.
  • Variable names can now contain up to 128 characters (from 100).
  • Imported datasets provided with more than 128 characters in a variable name will be automatically reduced to the first 128 characters to become legal.

Feature Requests

We love to hear your suggestions. Please share with us any feature requests or updates that would make LityxIQ work even harder for you:

Previous Version

LityxIQ 5.0.3

What’s New & Improved

Previous Versions

LityxIQ 5.0.2

What’s New & Improved

* Please do a SHIFT-CTRL-R refresh in your browser to take advantage of the ROC curve analysis functionality.

LityxIQ 5.0.1

What’s New & Improved

  • Automated Insights are now available.  For any dataset in LityxIQ, simply select up to five variables for which to generate automated insights each time the data is refreshed.  Automated Insights include a ranking of which other variables are important predictors of the target, and provide an easy-to-understand multivariate segmentation for each of the selected targets. Click here to get started.
  • The export dataset option allows the selection of an escape character for use in the export file.

LityxIQ 5.0

What’s New & Improved

  • AI visualization tool that enables easy-to-build representations of machine learning data and processes
  • Support for larger datasets and the ability to build models easily with point-and-click tools
  • New decision optimization tools
  • Google BigQuery and Amazon DynamoDB are now available as data sources
  • Variable importance scores and other pre-processing information about machine learning model runs is now available for all algorithms
  • Dataset metadata is now computed in parallel to dataset execution being finalized.  This provides much-improved execution times for certain large datasets.
  • Database schedules now allow for hourly jobs

LityxIQ 4.2.10

What’s New

  • Addition of Percentile-Discrete function for new field aggregations
  • Alpha version of Process Flow management released to limited users
  • Preview excel files in the preview pane within raw data source settings
  • Support site is now integrated into the UI, with help available from every dialog and the main menu
  • Increased functionality when performing aggregations allows for both cross aggregation variables and individual level variables to be used in the same aggregation
  • Dataset libraries can be fully copied into new libraries
  • Multiple datasets can be selected at once when defining the incoming datasets for a View— through manually selecting them, or by specifying a dataset name pattern to match
  • Datasets can now use themselves as input allowing for a very simple method for creating an automatic, cumulatively updating dataset

What’s Improved

  • Improved handling for ranking and distribution functions
  • Queue processing will now happen 25-50% faster
  • Cross-joins (full Cartesian product of two datasets) is now naturally executed when no join keys are selected
  • Improved functionality related to using configuration variables to automatically execute datasets
  • Batch loading of external files now operates more easily upon first starting the process

LityxIQ 4.0

What’s New

  • LityxIQ is now based on a highly scalable backend data warehouse supporting massively parallel query execution, and is fully encrypted at rest and on the fly by default
  • LityxIQ includes connectivity to more external database and data warehouse sources, including Amazon Redshift, SQL Server/Azure, Snowflake, Salesforce, and others, with more being added on a regular basis
  • LityxIQ now includes an API for real-time scoring that can be called from other business applications. Please ask if you are interested in additional details on getting started with it
  • Ability to perform “Quick Insights” on a dataset
  • Join indicator variable
  • Aggregation – option to summarize by individual variable levels
  • Dataset or variable attribute referencing with configuration variables
  • QC rules within Finalize area
  • Ability to have a “public” project accessible by anyone
  • Detailed output from every executed scenario is automatically saved into datasets accessible from the Data Manager

What’s Improved

  • Dataset summary statistics now include quartiles
  • Datasets can be optimized in the Finalize area by selecting sorting variables. This optimizes them when used as input into other dataset creation
  • Creating and solving constrained optimization scenarios is now even easier
  • The backend MIP and LP solver has been upgraded for increased speed of scenario execution
  • Information about datasets (and models and other objects) now updates instantaneously in the on-screen list when execution finishes

Get Started
with Lityx