International Prize: Machine Learning Hack

Supported By: 
Google

We are in the age of machine learning! From IBM's awesome Watson "Machine Learning as a Service", to Google's DeepDream and TensorFlow, and Facebook’s M. The past year has seen the release of many great machine learning tools and software libraries that are enabling machine learning to spread beyond the academic sphere into the hands of mere mortal programmer and analysts. We know government has some great 'big' datasets that might feed a machine learning problem - be that purely a measure of a dataset’s size, longitudinal data spanning decades, or de-identified unit record level data.

Think about a wicked problem that you could apply machine learning to, have a look at the data that's available, and get creative. You might uncover some new insight for policy makers and make Australia a better place, or maybe you'll just make an app for identifying Australian wildlife from a photo. Let's find out!

 

Eligibility Criteria

all Australian and New Zealand teams are eligible. Must use at least two Official GovHack Datasets. Open Government data must be used.

Anaconda Don't

Team Name: 
Anaconda Don't

​​​​​​​The Water Corporation is the principal supplier of drinking water to the Perth metropolitan area as well as the rest of Western Australia. For some of these towns, the water is supplied through a vast network of above ground pipes. These pipes require regular inspections and maintenance to make sure that the precious cargo it is carrying isn’t leaking out and wasted.

 

Mantis Labs

Team Name: 
Mantis Labs

Problems Identified:

We have examined the overall problem of data security which is a growing concern globally. We have applied our focus for the GovHack event toward the Government Health sector which can be a vulnerable area of concern. Our findings lead us to the particular issue of "ransomeware" that highlights this problem to be a growing concern whereby 4000 attacks occur daily across the world in the health sector alone of which Australia would be included.

The Working Solution:

ABS and opengov db

Team Name: 
Will

A video is inappropriate. Essentially I am scraping large volumes of open data from government and public sources, centralising and identifying regular expressions from random samples of data points from across each table and row, alongside selected pattern recognition statastical tools (clustering table data together for initial matching, anf fluctuating glanularity based on a decision framework) to produce decision making trees for the linking of relationships between large quantities of datasets in a logarithmic fashion, without having to process every individual data point.

GO MO GO

Team Name: 
GOMOGO

Meet Charlie, an executive for a multinational company with two kids and a dog. He loves fine dining but enjoys horseback riding with his kids on weekends. He was recently relocated to Melbourne on a new assignment from Brisbane. Becuase he was needed at his new job on short notice, he left his family behind in Brisbane and has been looking for a place to live. For now, he's living in a hotel room provided by his company - but has two weeks to find a new place to live. He misses his family terribly, and is eager to settle down to his new life in Melbourne with his entire family.