/ResoScan

Used to filtered top resume among hundreds of resume.

Primary LanguageJupyter Notebook

ResoScan

Used ResoScan to filtered out top candidates among hundreds of candidate using their resumes.

  1. Frist of all We do vactorization so we can do NLP (Natural Language Processing) process
  2. Here we implement open-source software library "spaCy"
  3. We used TF-IDF (Term Frequency-Inverse Document Frequency) algorithm to score resume
  4. Then show top candidate score by using sorting algorithm.
  5. Using numpy, we used gensim model for word2vec
  6. We used Stack Exchange which is stack overflow's own open source data set around 77 GBs