Andrew Cantino
    About Me Experience Freebie Finder Experiments Technical Research Blog Contact
© , by Andrew Cantino.

About Andrew

I am a web technology consultant based in San Francisco, CA. Through my company, Iteration Labs, LLC, I specialize in helping organizations to leverage emerging web technologies such as Ruby on Rails, machine learning / artificial intelligence, cloud computing, and structured web crawling.

My recent projects include SelectorGadget and Parselets.com, two tools for better structured data extraction on the web. I have also created a database of public parks, a popular online free stuff site, and have worked on some casual research projects.

Please contact me to discuss my work and how I can collaborate with you.

Experience

I am currently consulting with a couple of companies through Pivotal Labs, a Ruby on Rails consulting company in San Francisco. I also maintain relationships with a few other clients.

Until Oct. 2008, I worked as a software engineer at CastTV, Inc., a video search startup, where I built both backend and frontend systems in Ruby, Ruby on Rails, and JavaScript. Before that, I spent a summer working on Gmail at Google with JavaScript and Java.

I have 12+ years of online entrepreneurial development experience and have built profitable websites that leverage aggregated content, web scraping, and user input. I currently work with Ruby, Ruby on Rails, Perl, MySQL, JavaScript, and HTML/CSS and have experience in Java and unix administration.

My academic background is in physics and computer science, with Masters level research in artificial intelligence, stochastic optimization, and machine learning in web applications. I also enjoy exploring emergent phenomena in both nature and computer science.

Freebie Finder

AbsurdlyCool Freebie Finder
Freebie Finder is an automated free stuff aggregator, receiving 4,000-6,000 visitors a day. Combining input from multiple sources, it automatically collects freebies from across the web while filtering out scams and referral pyramids. The software also attempts to predict freebies' categories and countries and then utilizes user input to refine these predictions. Freebie Finder is built upon open source software, including Perl, MySQL, Apache, and Lynx.

Technical Projects

  • Educational Physics Simulations - I've written three Java applets to help teach physics concepts. Please explore damped, driven harmonic oscillators, coupled harmonic oscillators and Hilbert Space, and waves on a beaded string. Discussions are underway to include these applets with an upcoming physics textbook.
  • Perl, SQL, and Web Publishing Security - If you would like to learn more about topics in advanced web publishing and web security, check out this course that I developed and taught in 2005. (Please note that some topics may now be out of date.)
  • Computer Graphics - A portfolio from two computer graphics classes that a friend and I took in 2004. All of the images were generated by code that we developed from scratch.
  • SEdit - A simple, online, open source text editor that I wrote a few years ago.
For additional technical background please see my research experience.

Demos & Experiments

  • CSSEvolve - CSSEvolve lets you play with many properties of a web site, including the site's color scheme, fonts, borders, and more. CSSEvolve works through a process of simulated natural selection in which you select site features that you like and refine them through multiple generations.
  • Flexible Address Parser - An advanced parsing script that can handle US mailing addresses in many formats.
  • Adaptive Rock-Paper-Scissors - Can you beat this Rock-Paper-Scissors AI that I wrote?
  • Ant Harvesting Simulation in Second Life - I created a simulation of emergent ant harvesting behavior in the online world of Second Life.
  • MadLib BrainStormer - Generates silly ideas.
  • LiveJournal Widgets: LJ Geekalizer and LJ Grade Level Analyzer.

Research Experience

  • At Georgia Tech, I researched automated, personalized, adaptive tour guides in a museum setting using TTD-MDPs, a technique for generating a distribution of trajectories through a Markov Decision Process. We found that simulated tour guides reduced museum congestion while honoring museum visitors' preferences and autonomy.
    David L. Roberts, Andrew S. Cantino, and Charles L. Isbell. Player Autonomy versus Designer Intent: A Case Study of Interactive Tour Guides. In Proceedings of the Third Conference and Artificial Intelligence for Interactive Digital Entertainment (AIIDE-07), Palo Alto, California, 2007.
    Andrew Cantino, David L. Roberts, and Charles L. Isbell. Autonomous Nondeterministic Tour Guides: Improving Quality of Experience with TTD-MDPs. In Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-07), Honolulu, Hawai'i, 2007.
    Andrew Cantino, David L. Roberts, and Charles L. Isbell. Autonomous Nondeterministic Tour Guides: Improving Quality of Experience with TTD-MDPs. Technical report GIT-IIC-07-02, College of Computing, Georgia Institute of Technology. 2007.
  • For my Masters research project, I researched motion control of high degree-of-freedom manipulators, like octopus arms and elephant trunks, for animation and robotics. I explored local search and optimization in a real-world domain where random restarts, a standard technique, are unavailable.
  • In Fall 2006, I developed a remotely hosted interface tool in JavaScript, Perl, and MySQL that analyzes both historical traffic flow through a website and a visitor's cursor motion in order to estimate a probability distribution over page links. High likelihood subsequent links are either enlarged or pre-selected, thus improving their Fitts' Law properties.
  • During the summers of 2004 and 2005, I developed Java-based online physics pedagogy tools to aid in undergraduate education. I wrote full-featured numerical physics simulator to allow students real-time, hands-on experience with physical phenomena in an integrated environment and researched the effectiveness of these tools in a classroom setting. Find links to the applets here.
  • During summer, 2003, I developed a low-cost, distributed data-processing cluster to look for radio pulsar signals. I independently developed and deployed parallel-processing software to coordinate signal analysis and distribute 600 GB of raw radio telescope data. I set up and administered the Linux computing cluster and wrote software to gather timing data for cluster efficiency analysis.
    A. Cantino, F. Crawford, S. Dhital, J. Dougherty, & R. Sherman. A Low Cost Distributed Computing Approach to Pulsar Searches, Eleventh SIAM Conference on Parallel Processing for Scientific Computing, San Francisco, California, February 24-27, 2004.

Contact Andrew