“I had the great privilege of working with Harman for over a year at LinkedIn, spanning two different product teams. Harman is a detail-oriented and rigorous data scientist who excels at extracting valuable insights from complex datasets and consistently presents them in a digestible and impactful way to help his cross-functional partners make decisions. Harman's standout qualities include his proactiveness and insightful thinking. Upon joining a new team halfway through our partnership, he played a pivotal role in helping redefine our product strategy. His dedication to fostering seamless cross-functional partnerships and unwavering attention to detail made him an invaluable asset to our team. I wholeheartedly recommend Harman and know that his future teams will benefit from his dedication, talent, and collaborative spirit.”
About
Contributions
Activity
-
I love diving down random rabbit holes. My current rabbit hole is around the Marriage Penalty/Bonus. I am looking at the different breakdowns of…
I love diving down random rabbit holes. My current rabbit hole is around the Marriage Penalty/Bonus. I am looking at the different breakdowns of…
Liked by Harman S.
-
Land your dream AI Data Scientist role even if you don't have domain experience. 360° tech interview prep strategy taught by FAANG+ Data Scientists.
Land your dream AI Data Scientist role even if you don't have domain experience. 360° tech interview prep strategy taught by FAANG+ Data Scientists.
Liked by Harman S.
-
We’ve all heard of technical debt but love this concept of management debt. Definitely want to explore this a bit more.
We’ve all heard of technical debt but love this concept of management debt. Definitely want to explore this a bit more.
Liked by Harman S.
Experience & Education
Licenses & Certifications
Courses
-
Applied Machine Learning
-
-
Applied Natural Language Processing
-
-
Data Mining and Analytics
-
-
Deconstructing Data Science
-
-
Fundamentals of Business
-
-
Haas@Work
-
-
Information Law and Policy
-
-
Information Organization and Retrieval
-
-
Lean Agile Product Management
-
-
Machine Learning in Education
-
-
Managing in Information Intensive Companies
-
-
Presentation Design for Analytical Communication
-
-
Quantitative Research Methods for The Study of Information Systems and Management
-
-
Social and Organizational Issues of Information
-
-
Where Business Meets Technology
-
Projects
-
Predicting Medication Change and Hospital Readmissions in Diabetic Patients
-
American hospitals spent over $41 billion on diabetic patients who got readmitted within 30 days of discharge. Being able to determine factors that lead to higher readmission in such patients, and correspondingly being able to predict which patients will get readmitted can help hospitals save millions of dollars while improving quality of care.
We used data mining techniques such as feature engineering, data balancing and interactions, along with robust machine learning models to…American hospitals spent over $41 billion on diabetic patients who got readmitted within 30 days of discharge. Being able to determine factors that lead to higher readmission in such patients, and correspondingly being able to predict which patients will get readmitted can help hospitals save millions of dollars while improving quality of care.
We used data mining techniques such as feature engineering, data balancing and interactions, along with robust machine learning models to predict medication change and hospital readmission in diabetic patients, and interpret these models to devise corrective measures for hospitals.
Other creatorsSee project -
Deconstructing the 2016 U.S. Presidential Elections Using Tweet Analysis
-
Do people tweet the same way as they vote? With this primary goal in mind, we performed sentiment analysis using Natural Language Processing and Machine Learning on a set of 50,000 tweets to identify the correlation between the tweets and voting behaviors of the voters.
This involved coming up with a subject-based tweet sentiment analyzer that predicted the U.S. presidential election results by state, with an accuracy of 89%. Given any tweet as an input, the web-interface for the…Do people tweet the same way as they vote? With this primary goal in mind, we performed sentiment analysis using Natural Language Processing and Machine Learning on a set of 50,000 tweets to identify the correlation between the tweets and voting behaviors of the voters.
This involved coming up with a subject-based tweet sentiment analyzer that predicted the U.S. presidential election results by state, with an accuracy of 89%. Given any tweet as an input, the web-interface for the analyzer accurately predicted whether the Tweet was Pro-Hillary or Pro-Trump.
As an extension to the analyzer, we also came up with a visualization of what each of the states within the U.S. was talking about, based on the tweets.Other creators -
Predicting Dropouts in MOOCs using RNNs and Ensemble Methods
-
MOOCs have become one of the most popular means of online education in the past few years. However, the biggest problem being faced by MOOC vendors is the significantly high rate of student dropouts.
Having an understanding of which students are going to drop out allows for interventions to be implemented. Moreover, of we can interpret the results of MOOC dropouts, we can improve the ability to tailor the interventions to the respective students who will be most helped by…MOOCs have become one of the most popular means of online education in the past few years. However, the biggest problem being faced by MOOC vendors is the significantly high rate of student dropouts.
Having an understanding of which students are going to drop out allows for interventions to be implemented. Moreover, of we can interpret the results of MOOC dropouts, we can improve the ability to tailor the interventions to the respective students who will be most helped by them.
Motivated by this, the project involved the use of machine learning techniques such as Recurrent Neural Networks and Ensemble Methods to predict a student's likelihood to drop out of a MOOC on a weekly basis, based on his activities and interaction within the MOOC.Other creators -
RPACKETLOSS - A Novel Method for Measuring Packet Loss Episodes in Networks
-
Developed an application to measure packet loss episodes accurately with end-to-end probes in a network. This involved testing the capability of standard Poisson- modulated end-to-end measurements and presenting a more efficient method of packet loss measurement using a self-designed algorithm, that improved the measurement accuracy by approximately 20%.
-
File System Simulation
-
Developed an application in C that provides a transparent and convenient way of performing the basic file operations, irrespective of the operating system used.
-
Image Steganography
-
Designed the algorithm for an Image Steganography application (developed in C#) that provides data security by encrypting data files into bitmap image files and subsequently decrypting them, using the encryption-decryption algorithm.
-
Virtual DOS
-
Developed a platform independent application that simulates the DOS environment, while ensuring minimum system requirements.
Test Scores
-
GMAT
Score: 740
-
TOEFL
Score: 112
Recommendations received
7 people have recommended Harman
Join now to viewOther similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Harman S. in United States
-
Harman S.
-
Harman S.
-
Harman S
Family Nurse Practitioner at Winona State University
-
Harman S
Student at University of California, Berkeley
-
Harman S
I beekeeper
9 others named Harman S. in United States are on LinkedIn
See others named Harman S.