Project:  Building Elements of Compassionately Analytical Resume Bots aka RBots

 

Prologue: We include the challenge problem and data from the 2015 OSU hack-a-thon. It is common knowledge that bots connect resumes to job descriptions.  And we all get frustrated since we get weeded out at word go.  You goal is to help students do a better job by analyzing the needs of the students to the demands of the labor market.  Similarly, you will help employers tune their advertisements. Even better given that AI and robots will take over the world, you will apply the salve of visual analytics and make the bots compassionately analytical.  Parsers, bi-clustering, graph drawing, parallel coordinates/sets are possible paths. The presentation of the winning team at OSU hack-a-thon is also included.

 

The Data: The local career service at Ohio State has provided us this data. Let us be local and get some cool things done. My hope is that you can give a tool that the Career services can use.  What does this repository contain? Well -

_      262 job and internship postings

_      Resume data from 91 Ohio State students

 

Please find the files here. Still, you could use any other treasure trove. But the tool needs to be demonstrated on the local Ohio State data.

 

Resources: Please find class slides here.

 

 

Deliverables: It is required you to create visualizations which allow the matching of skills to requirements.  The visualization has to be interactive. No way around it. Sorry.  It needs to deployed on at least the local data.

 

And most importantly, a user evaluation of your peers should be included. Devise a list of tasks and then deploy the tool on the list of tasks. Let you peers (about 10) score them using a binary scale. Essentially, you need to demonstrate that a matching tool is better than just poring over resumes and job descriptions.

 

In decades to come, a human will use your tool and program the Rbot so that he does not allow the recruitment of l non-human bots who will let AI rule the world.

 

Finally, yes you need to submit code, a report (with results of the user study) and any material that is required to demonstrate the project. If you cannot show in person make sure you have slide-decks/videos, links to web sites, etc. And yes you make your deposit into a Carmen dropbox.