For this hackathon, the problem statement our team selected is problem statement 3 – CSIT. Here is the problem statement: Come up with creative solutions that would help aspiring techies like yourself to achieve one or more of the following:
- Determine individual career paths in the Tech industry
- Raise awareness of the tech jobs available
- Advertise themselves and clinch the aspired jobs in the Tech Industry
Solutions can come in the form of software applications, sites, or any other feasible platforms. We will split our write up in terms of the front end, back end and the API which makes up the entirety of our website. To summarize, this web site is designed to help aspiring techies to explore their possible career paths in the tech industry based on their interests, hobbies, abilities and educational achievements. Our website also leverages machine learning algorithms in order to accurately predict and determine suitable career paths for aspiring techies in the tech industry. To start off, the frontend is our website itself, which is coded in HTML, CSS, and Nodejs languages. The frontend lets the user search their suitable career paths based on information they enter in the search bar that is related to their achievements and interests. Moreover, there is an about page that describes the website and its functionality in detail, and a contact page for users to contact the developer/owners regarding any queries relating to the website. Once the user enters the search area and submits their search query, the text that the user entered is then sent to the backend where further processing is done to determine the suitable career paths for the user, and these paths are then displayed on another page. Moreover, on this result page, the user can experience what each suitable career path feels like with demos, which allows the user to decide whether the specific career path is the one that the user wants to pursue. The crux of the demo is the provision of real world problems to the user based on their suitable career paths, and then letting them experience how it is like to actually work in that position. Finally, we use real time rendering technology to render user’s code in real time to let them feel what it is like and the actual work flow. For the backend, we have coded in python flask & pytorch for the Machine Learning Model itself, and use an API which lets us connect the frontend to the backend, and by doing this, we are able to send the text data user searched for to the Machine Learning Model, which will then run an inference on the text data it receives. Once the inference is over, the output from the machine learning model which is the suitable career paths for the user, is sent back to the front end, which is the html page, and then the results are displayed in the html format for the user to view. To elaborate more on the Machine Learning aspect of our website, it is using the latest natural language framework, BERT. This is based on a transformer, which is used to understand the user’s description of their interests, achievements and desired job, and then accordingly match them with the suitable career paths (job positions) available for the user.
Log in or sign up for Devpost to join the conversation.