Government Services Challenge
How might we better understand citizens' transaction preference and behaviours to make Queensland Government services easier to use?
Go to Challenge | 9 teams have entered this challenge.
The Hellish kangaroos
The Australian Taxation Office has opened around to 500 help centers across Australia, where accredited community volunteers can provide assistance for individuals. These centers, of great help to the community, are often hard to find, even requiring a phone call to locate them. For these reasons, opening a new Tax Help center is a strategic decision, that can be supported by various AI or machine learning approaches.
Among the various factors that have to be taken into account when opening a new help center, for clarity and simplicity, we mainly focused on the following ones:
- The population: When opening a help center, we want to be able to reach as many people as possible.
- The income: Some people are more likely to be expecting a tax return, and may require assistance. Therefore it would make sense to favor the low-income areas.
Based on the processing of the data available to us and our predictions, our web application allows us to visualise in an interactive way the past and upcoming situation across Australia and support decision when opening new Tax Help centers.
The dataset is much richer than what we focused on, and with enough time and computational power, there is a potential for relevant analysis of previous help center openings, as well as accurate predictions for the future.
The Medicare levy surcharge, population by age, wages, gifts or donations, or HELP assessment are just some of the variables that can help to be more accurate.
Description of Use We used the dataset to estimate the location of postcodes. The official postcode location dataset is not open-data!
Description of Use Our results are based on the attributes that were the most meaningful for us, and for the scope of this project.
Go to Challenge | 9 teams have entered this challenge.
Go to Challenge | 21 teams have entered this challenge.