Manas Bansal
Business Analyst at OYO Vacation Homes
Delhi, India
Summary
🤩
Rockstar🎓
Top SchoolManas Bansal is a business analyst and former content writer with 11 years of professional experience blending technical acumen and communication skills. Trained as an electronics and communications engineer from Thapar Institute, he brings hands-on experience in SEO, web content, and C programming alongside data-focused contributions to notable open-source projects like Snorkel—where he improved weak supervision tooling, BERT feature pipelines, and model evaluation. At OYO Vacation Homes he applies analytical rigor to product and operations while his student leadership roles reflect a knack for coordinating vocational programs and events. Comfortable bridging technical and non-technical stakeholders, he combines code-level data science experience with a marketer’s eye for content and discoverability.
11 years of coding experience
1 year of employment as a software developer
B.E, Electronic and Communications Engineering Technology/Technician, 9.22, B.E, Electronic and Communications Engineering Technology/Technician, 9.22 at Thapar Institute of Engineering & Technologyclass 12 th, 95 %, class 12 th, 95 % at Swami Vivekanand Public School , yamunanagar
Github Skills (22)
python10
data-science10
snorkel10
pandas10
machine-learning10
numpy10
natural-language-processing10
nlp10
basics9
testing9
learn-ruby-on-rails9
labeling9
unit-testing9
pytest9
user-manual9
Programming languages (3)
Github contributions (5)
snorkel-team/snorkel-tutorials
Jul 2019 - Jan 2020
A collection of tutorials for Snorkel
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:36 commits, 71 PRs, 175 pushes in 5 months
Contributions summary:Manas contributed to the development of tutorials for Snorkel, a framework for programmatically building and managing training data. They implemented features for using BERT (Bidirectional Encoder Representations from Transformers) embeddings. The user added code to process and use BERT features to train a logistic regression model and improve the accuracy of the model.
snorkel
snorkel-team/snorkel
Jul 2019 - Feb 2021
A system for quickly generating training data with weak supervision
Role in this project:Data Scientist
Data ScientistContributions:11 commits, 33 PRs, 55 pushes in 1 year 7 months
Contributions summary:Manas primarily contributed to improving the functionality and robustness of the Snorkel library, focusing on data analysis and model evaluation. They implemented a function to filter unlabeled examples, enhanced error analysis by handling 2D predictions, and corrected a bug in the ROC AUC calculation. Additionally, they made changes related to data augmentation and type annotations, showing a focus on code quality and reliability.
training-dataweak-supervisionmachine-learningailabeling
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.