Xplore

Project Info

Team Members


6 members with unpublished profiles.

Project Description


This tool

  • connects people to their community and environment according on their lifestyle needs and values.

  • ensures a diverse society is accommodated for in the ACT by linking people to their community hubs.

  • progresses the society by innovating with new technology, leading to a brighter, better and more connected future of tomorrow.

2 important benefits of this magical tool:

  • One: will help users make informed life choices; and

  • Two: will help government make evidence -based policies and plan for the future based on data collected on users.


Data Story


The Xplore tool uses the multiple data sources available on the ACT Government Open Data Portal (https://www.data.act.gov.au/) as its underlying data. This includes the geolocation data of schools, hospitals, libraries, public transport routes, recreation facilities and projected population growth time series by suburb. The data was cleaned and transformed into a usable format using Power Query and stored as a Microsoft Access database. You can find the complete list of datasets we used and analysed here: https://github.com/Hjacer/Govhack19-Xplore

Xplore uses cutting edge technology such as geospatial visualisation and machine learning algorithms to better visualise and predict population trend to better help the individual end user and ACT government to plan for their future. The tool not only visualises statistics such as number of schools and hospitals, predicted population growth rate by suburb, but also makes recommendations for the user. The tool works by taking user inputs such as age, gender and suburb they want to move into, and uses the built-in machine learning model to forecast population growth. In production, the recommendation system will also calculate the ten year lifestyle, housing affordability and employment outlook scores using public facilitates data, housing datasets and employment datasets for the suburb the user entered. It will then compare these scores with other ACT suburbs and recommend the best suburb (highest score) for the user to move into in the future.

The ACT government could also use the data we collect through the system, such as user demographics, housing and employment data to better plan for the city in the areas of population, education, community and job opportunities in the future.


Evidence of Work

Video

Team DataSets

ACT Population Projection

Description of Use used for data visualisation on map and used for population prediction using machine learning algorithm

Data Set

Challenges

ATO for individuals

How can ATO and other Australian public data be used to help the community fill employment opportunities?

Go to Challenge | 27 teams have entered this challenge.

Canberra 2029 – First Hackers: Inclusive; Progressive; Connected

How do we use data from the past to predict a better future for Canberra? How do we best support the diversity of our community? Optimise the way we travel and transport goods throughout our city? Predict the jobs of the future – and the skills needed for them? Connect our citizens with their environment?

Go to Challenge | 10 teams have entered this challenge.

🌟 Canberra 2029 – Inclusive; Progressive; Connected

How do we use data from the past to predict a better future for Canberra? How do we best support the diversity of our community? Optimise the way we travel and transport goods throughout our city? Predict the jobs of the future – and the skills needed for them? Connect our citizens with their environment?

Go to Challenge | 21 teams have entered this challenge.

Australia’s Future Employment

Choose one of the following questions to address: 1. How can recent and future changes in the labour market help prepare young people for job opportunities? 2. What can we learn from case studies of regional labour markets? For example, what does rapid change in the industries or occupations within a region tell us about the needs of employers/workers in other regional labour markets

Go to Challenge | 38 teams have entered this challenge.