OUR PRESENTATION VIDEO
This presentation video is part of our pitch submission for the 2021 GovHack competition.
PROOF OF CONCEPT IDEA 1
We wanted to demonstrate that we could import the Australian Skills Classification dataset and graphically display roles where the points were clustered with relative similarity of roles.
​
We also wanted to demonstrate classification of natural language user descriptions as inputs in order to classify into the ANZSCO job codes.
​
In this example the title 'Medical Sales Representative' did not exist in the ANZSCO job codes, but the model was able to classify it from the description and map it to it's closest neighboring roles. In this case the model found similarities to pharmacy sales assistants and retail pharmacists.
​
Users can interact with the map and zoom in and out to get more detail.
Screenshot of proof 1
DATA
We used the National Skills Commission Skills Classifications dataset which has a text description component for each of the titles and the ANZCO Codes.
​
We used the Natural Language ToolKit (NLTK) and Term Frequency–Inverse Document Frequency (TF-IDF) to take in the ANZCO titles and descriptions, break it down into keywords and create the model.
​
When the user inputs their text descriptions, we can repeat the process to match that to the closest ANZCO description of a role or title. By doing so we can classify them against the existing codes and find where they sit on the model, which we can display in a graphical format.
Dataset showing title and description against codes
PROOF OF CONCEPT IDEA 2
We wanted to allow the user to be able to see their relative position against the map of jobs and explore their future roles and do some career planning.
​
The map shows the relationships between their perceived skill level and those of other roles on the x-axis, with the logarithmic representation of the current job vacancies on the y-axis.
Using this the user can see how many more points of retraining are required to attain another role, and how in demand that role currently was.
​
In order to access this feature you are required to look at the left hand menu, select 'What do you want to do next?' and select your closest ANZSCO title which will plot you in red on the graph. You can then zoom and hover over another role to see the difference in skills points displayed on the graph underneath.
Current role in red, on the skills map of all roles.
Graph of core competencies between two roles
DATA
This program uses another component of the National Skills Commission Skills Classifications dataset, which classifies roles against 10 core competencies and scores them on relative proficiency level. This allows us to use this as features to map out the roles and display the relative re-training required along the x-axis of the map.
The y-axis is a logarithmic output of the Labour Market Information Portal Job Vacancies Data and uses the ANZSCO_Code as a key to match with the x-axis data. This allows us to plot the job map to the user, and the graph below shows the difference between core competencies of the two roles.
​
The Labour Market Information Portal Job Vacancies Data set counts online job advertisements on Seek, CareerOne and Australian Jobsearch and catalogues them against state/territories.
​
​
X-axis dataset showing proficiency ratings against codes
IVI dataset showing ANZCO Codes against job vacancies for y-axis
PROOF OF CONCEPT IDEA 3
We wanted to incorporate the ABS API portal to be able to show insights regarding the roles the user would look into. In this case we worked with the IT Specialist role pulling in the data, and then linking it up with the keys provided by the mentors in the slack channel.
​
We used this to display a heatmap of of IT Specialists by industry and size of company.
API Raw Data
Keys to the Dataset
Heatmap displaying insights obtained from dataset.