The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

Data-Driven Sourcing of Candidates for Recruitment

Submitted by Devashish Sood (@devssh) on Monday, 15 April 2019

Session type: Full talk of 40 mins

Abstract

We cover how we are using social media data to source candidates and details on how we manage the data-pipeline, trained the models, built the webapp, handled data-security and GDPR and Legal. Our project manages a huge amount(~1TB) of data but is used by a small amount of users.

Outline

Data pipeline
Models
WebApp - minor overview
Data Security
GDPR and Legal

Requirements

No requirements.

Speaker bio

I have been working as a Data Scientist and Engineer for the last 2 years and I started off as an Application Developer writing software. I have an online specialization in Data Science from the University of Michigan, a specialization in Deep Learning in Tensorflow/Keras, Numpy from Andrew Ng and Deeplearning.ai and a specialization in Scala-Spark from EPFL.

Links

Slides

https://docs.google.com/presentation/d/1KbmFQXFJE8C1Q8OuZa2-Ny_LEBmH9LN2pNEYr_r2RQ8/edit?usp=sharing

Comments

  • Zainab Bawa (@zainabbawa) Reviewer 5 months ago

    The slides simply describe the technology stack. They don’t contain details of the architecture, why the tech stack was used, and why the decision to use this stack versus other options. The GDPR part of the slides are primarily descriptions, without implementation details and the challenges encountered during implementation.

    • Zainab Bawa (@zainabbawa) Reviewer 5 months ago

      In the current form, the proposal is a no-go. If you decide to convert this into a case study, you have to show the implementation in-depth and go into explaining why you did what you did, not just the how.

Login with Twitter or Google to leave a comment