Discovering Insights with Boundless Analytics
Uncover valuable insights using Boundless Analytics, a powerful tool developed at Rutgers University. Explore distributions, plots, cubes, slices, and more to find unique patterns in your data for further exploration.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
BOUNDLESSANALYTICS PREDISCOVERY FINDING NEEDLES IN HAYSTACK OF DATA
BACKGROUND Boundless analytics was developed at Rutgers under direction of Tomasz Imielinski, with support NSF CCF-0939370 (subcontract with NSF CSol STC) It has debuted as an educational tool in data literacy class Data 101 at Rutgers in spring of 2021 150 students have used it in preliminary data exploration in spring 2021 semester.
CUBES SLICES - CONJUNCTS MOVIE DATA SET (IMDB from Kaggle) Slice: Genre = Comedy & Country = UK Slice: Rating = R & Country = US Slice: Country = France and Genre = Action and Rating = PG Exponential number of slices potentially even with minimum support
PLOT ZERO AND SLICE PLOTS Take, for example, a histogram of IMDB scores HIST(IMDB) Plot Zero: p0=HIST(IMDB) over entire data set of movies Slice Plot: pS = HIST(IMDB) over a slice Country = France and Genre = Action and Rating = PG Order by DISTANCE d(pS,p0) in ascending order: from most distant first
PRE-DISCOVERY WITH BOUNDLESS ANALYTICS For each plot type: Finding slice plots which are as different from the plot zero Such plots are good LEADS for further exploration
