AI and Data Visualization: the Beauty and the Brains
Last updated:
3:29pm Jan 28, 2019

Synopsis

Visualizing data helps us explore structure and relationships in data, and it provides a basis for communicating information. Machine Learning can be used to systematically comb through data and quantitatively identify patterns. Combining Al and ML with visual analytics can be especially powerful. Starting with AI / ML, we can reduce high dimensional data to important variables for visualization. Starting with visualizations and visual analytics, it’s possible to identify patterns that can subsequently be tested with rigorous ML methods. Further, AI can be used inside a visual analytics environment to suggest data shaping, variables to explore, and patterns in the underlying data.

AI and Data Visualization: the Beauty and the Brains is a series of roadshows where we present case studies and examples to explore this combination of AI and visual analytics methods with reference to TIBCO Spotfire®, TIBCO Spotfire Data Science, TIBCO Statistica® and data science environments such as R and Python.
Sign up to attend and learn about: 

  • How AI can drive BI and visual analytics for rapid insights and data discovery
  • Recent advances in AI and Machine Learning, with visual analytics
  • TIBCO Connected Intelligence, and the ability to sense, learn, and act on your data with Spotfire, Spotfire Data Science, Statistica and TIBCO StreamBase®.

Cities and dates

Past 'the Beauty and the Brain' Meetups:

  • Los Angeles, CA Jan 18, 2018
  • Denver, CO Jan 23, 2018
  • Phoenix, AZ Jan 24, 2018
  • Palo Alto, CA Jan 25 2018
  • Falls Church, VA Jan 25 2018
  • Houston TX, Feb 20, 2018
  • Chicago IL, Feb 21, 2018
  • New York, NY Feb 22, 2018
  • Atlanta, GA Feb 27, 2018
  • Toronto, ON Feb 27, 2018
  • Mexico City, Mexico, Mar 22, 2018
  • New York, NY, April 24, 2018
  • London, United Kingdom, May 10, 2018

Registration information for your city on TIBCO's meetup page.

View this roadshow's introductory webinar.

Demo Showcase

SpotCoffee trade fund optimization

Summary

This is an example of an analytics app for the CPG and retail industry. The overall business objectives are to increase revenue from product sales and reduce the cost of operations. A demand planner and trade marketing analyst use the app to perform forecasting, trade promotion analysis, what-if analysis for marketing campaigns and supply chain distribution planning. It features an interactive visual analytics dashboard driven by an embedded AI engine in TIBCO Spotfire.

Video

 

Best offer and cross-sell recommendations

Summary

A retailer wants to increase revenue and delight its customers with a relevant offer at the same time. Its marketing analyst runs a promotion on selected products and uses predictive analytics to find best offers and cross-sell opportunities. She then operationalizes the decisions made by the predictive model by deploying it to runtime to make product offers. This example features visual analytics and predictive modeling with an in-built R engine in TIBCO Spotfire. Product offer decisions are made live in TIBCO StreamBase and monitored in a live dashboard.

Video

Analyzing flight delays

Summary

This example is for airlines and airports that want to improve operations and traveler experience. A data scientist analyzes historical flight delays and builds models to predict potential flight delays in future so that an airline or airport may take pre-emptive actions. It features TIBCO Statistica, a workbench for data scientists, where they can perform operations on historical data and use a comprehensive set of statistics, analytics and machine learning algorithms to build models. Interactive visual analytics in TIBCO Spotfire helps the data scientist understand the data and the models in the modeling process.

Video

Parking citations in San Francisco

Summary

This project is a collaboration between Tipping Point, the San Francisco Office of Financial Justice and TIBCO. It aimed to discover insights on the impact of parking citations on low income drivers in San Francisco. The team discovered that older cars, which are assumed to be driven by lower-income drivers, are associated with citations of higher amounts. As a result of the findings, the team made recommendations to the Office of Financial Justice for policy review.

Due to the volume of data analyzed, the initial analysis was performed on a Big Data platform. Business analysts, data engineers and data scientists collaborated and shared findings in TIBCO Spotfire Data Science, a collaborative data science platform for data preparation and analytics at scale. Data supporting the findings was then summarized and presented in an interactive TIBCO Spotfire dashboard to a business audience.

Video

Resources

Explore the team's findings for this project.

Analyze some data!

Ready to do some analysis? Download a Spotfire Trial and visit one of these open data sites to find some data to work with!