Hello There

I am Harish.
I am a machine learning researcher.


Master's candidate in Computer Science with over 2 years experience in developing machine learning solutions. Authored 'What Makes a Research Article Newsworthy?' which is now ranked in the top 25% of all research tracked by Altmetric. I have a very strong knowledge of machine learning algorithms, tools and best practices.


I am a graduate student at the Northern Illinois University where I also work as a Research Assistant at the DATA Lab. In my thesis, I have proposed novel ways to assess societal impact of research using machine learning and natural language processing. I have also devloped tools that allow people with no coding experience to use the machine learning models I built to assess research outputs. I am also simultaneously working as a Machine Learning Intern at Sema to help automate maintenance of legacy software systems or as the CEO says, "we're building code that fixes code". I look forward to making more such contributions to teams around the world working on exciting projects.

I've Got Some skills.

  • 90%
  • 85%
  • 70%
  • 95%
  • 75%
  • 90%

My Work Experience

January 2018 - Present


Machine Learning Intern

Use Machine Learning techniques to automate maintenance of legacy software systems.

May 2015 - June 2015

Vizag Steel Plant

Developer Intern

Developed an Android application for the IT department.

August 2016 - May 2018


Research Assistant

Analyzed social media and other online content to solve unique real world problems.


August 2016 - May 2018

MS in Computer Science

Northern Illinois University

Concentration: 1. Machine Learning 2. Databases | GPA: 4.0

August 2012 - May 2016

B.Tech in Computer Science and Engineering

GITAM University

GPA: 8.9 out of 10


Assessing Public Understanding of Research

Python, R

Used Natural Language Processing to analyze scientific text and content posted by public online to study public understanding of science.

What Makes Research Newsworthy?


Built Machine Learning Models to predict if a research paper is likely to attract attention of news outlets.

Predicting Reseaerch that will be cited in Public Policy Documents


Built classifiers and regression models to predict if a scholarly paper is likely to be cited by public policy documents.


Author image

There has been tremendous growth in research being published every year. Yet, only a small part of it receives press coverage. In this study, classifiers were built that predicted the newsworthiness of research articles based on the attention they received on online platforms.

Author image

Scientific publications are increasingly being cited in policy documents. Suct citations are a critical indicator of the significance of the research output. In this study, classification models were built that predict if a particular research work is likely to be cited in a public policy based on the attention it received online.

Predicting Research that will be Cited in Policy Documents
Author image

An initial evaluation of altmetrics and their relationship with public policy citations was done. Various methods to use altmetrics were examined and evaluated for their potential usefulness.

Exploring Features for Predicting Policy Citations

Hours of Coursework Completed


Cups of Coffee




Hours of Hands-on Experience


Feel free to drop a message if you're looking for an awesome data scientist/machine learning engineer, or if you want to discuss Game of Thrones, Sherlock and Doctor Who.


(224) 800 7076