At Freshworks, we receive more than 1000 applications every week. This leads to a lot of applications for our Talent Acquisition teams to process, which can be difficult. Conventionally, candidate screening at Freshworks has involved a manual review of the candidate’s resume/portfolio which cannot be scaled for smaller HR teams. We experimented with making this process smoother by implementing an automated pipeline that uses data science to score a candidate based on their skills, experience and how suitable they are for the job they have applied for, using thousands of previously processed candidates.

• The recruitment pipeline at Freshworks
• Common roadblocks in hiring and how Data Science can eliminate them
• Building Candidate Scoring models
  • Data sources and Enrichment
  • Picking the right features for scoring candidates
  • Evaluating the Candidate scoring models
  • Identifying features that differentiate good candidates
• How candidate scoring models accelerate hiring
  • Candidate conversion rates
  • Average turnaround time
• AI solutions for the HR in areas other than hiring
  • Targetted training modules
  • Predicting attrition

As a part of the Data Science team, I work on analysing textual content in deal pipelines and building AI models to boost sales. I enjoy applying AI to solve practical problems.

• github.com/py-ranoid
• linkedin.com/in/vishalg8897