Your resume has six seconds to grab the recruiter's attention. Make it count.

UWaterloo ENGHACK18 project developed initially in 24 hours, using pre-trained NLP algorithms/APIs to perform transfer learning in Jupyter Notebook to build a tailored resume screening web application.

This project won the award for "Best Use of Machine Learning" as awarded by Indico, as well as the "Wolfram Challenge" as awarded by Wolfram Research.

^{f1: Interactive features menu UI inspired by Google Cardview}

1. Job Match
   • Adjusted Word2Vec model to classify based off keywords w/ a sieve to catch blacklisted words
2. What Works & What Doesn't
   • Adjusted unsupervised neural network to cluster based on word morphology
3. Frequent Words
   • Built a tf-idf model to perform k means clustering
4. Personality Radials Classification
   • Regularized algorithm to correct for high variance/overfitting

^{f2: Personality radials identifying a high confidence for logician and architect types; displayed with Wolfram One}

Server runs on the Express framework in Node.JS with ML algorithms called upon through python-shell. The 6 pronged analysis is visualized using Wolfram One's cloud computation platform for a friendly user experience. The front end design was inspired by the interactivity of Google's Cardview template.

• Sentiment analysis to better align with company culture
• Facial recognition to identify emotion in interviews
• MongoDB to allow for multiple resumes/account
• JSON Web Tokens to form secure resume editing groups