Tourism Jobs Challenge
How might we determine the future tourism job needs for Queensland?
Go to Challenge | 7 teams have entered this challenge.
Error 417: Expectation Failed
This project aims to connect people seeking a career change with current job opportunities in Queensland’s Tourism industry. We’ve created a website with unique algorithms which search job descriptions based on skills and locations to match them with local council and rural business opportunities.
This is a great way of finding the right people with the right skills for the right jobs in a way which supports rural Queensland communities and new or growing businesses.
Primary link: https://govhack2.herokuapp.com
Alternative link: https://myapp-ftwwqfgsix.now.sh/search
The first dataset we investigated when we began this project was the 'Deloitte Access Economics – Australian Tourism Labour Force Report 2015 -2020'. This report informed our entire approach to this project as it made us aware of the prevalence of skills misalignment in the tourism industry. A lack of skills or lack of appropriate skills was highlighted throughout the report as a key issue for tourism industry employers. This problem influenced our idea to have a skills-based job search platform for Tourism which allows job seekers to find opportunities that best align with their skill set.
Through further investigation into this report as well as those provided on the Tourism Research Australia website, we found that our engine should also account for the differing requirements and capacities of each Region of Queensland. In order to do this we used the Tourism Research Australia 'Regional Tourism Satellite Accounts' for Queensland to inform our Search engine ranking algorithm. This algorithm ranked which jobs would appear in which order for every search according to the 'number of skills matched' to the job description and the 'Regional Weighting' figure. The regional weighting figure defined the potential change in tourism employment for this region into the future (e.g. will the region have growth in it's tourism employment over the next few years or a reduction). To determine the region weighting we used the Year-on-Year change value (%) in tourism employment for each region of Queensland from the 2015-16 period. This value was used as it was available for the same time period for each region of Queensland (allowing for comparison between regions). We acknowledge that this figure, as it only pertains to the 2015-16 period, is not ideal for a predictive model. In future iterations we would request ABS data, for the Tourism industry specifically, to ascertain a more accurate predictive figure.
In future iterations of the project, we would like to create a full database of job names, tags and skill requirements from public job listings using web crawlers. We can then use dynamic models and machine learning to generate relationships between these elements based on their strength of connection. This way we will have a constantly-shifting, computer-maintained database of skill and job mappings for our search that can reflect the constantly shifting job demands of the real world.
Description of Use We used the Tourism employment data within this dataset to create the Townsville Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Southern Queensland Country Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Whitsundays Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Outback Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use The report provided important context for the projected future skill and labour shortage in the tourism industry, and is the key impetus for our decision to focus on this project. Unfortunately the figures in the report do not have adequate regional breakdown for our needs, but we can probably obtain more detailed projection data if we request from Deloitte.
Description of Use We used the Tourism employment data within this dataset to create the Mackay Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Tropical North Queensland weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Southern Great Barrier Reef Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Sunshine Coast Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Gold Coast Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Fraser Coast Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use We used the Tourism employment data within this dataset to create the Brisbane Regional weighting value for our search engine ranking algorithm. The main value we used was the Year-on-Year change (%) value for the 2015-16 period, which was used to predict growth or decline in tourism employment in this region of Queensland.
Description of Use For the proof-of-concept, text data from publicly available job listing websites are extracted and manually processed to create some sample skills and job listings for the website as function showcase.
Go to Challenge | 7 teams have entered this challenge.
Eligibility: Must use at least one Sunshine Coast region data set.
Go to Challenge | 14 teams have entered this challenge.
Go to Challenge | 27 teams have entered this challenge.
Eligibility: Must use at least one Sunshine Coast region data set.
Go to Challenge | 11 teams have entered this challenge.
Go to Challenge | 13 teams have entered this challenge.