Data Science Project Lead
May 2023 – Present | New York, US
- Led the development of a publicly operational Carbon Compass tool for 'NYC Local Law 97,' championing energy efficiency in compliant buildings. Spearheaded end-to-end project management, ensuring seamless execution from ideation to deployment.• Led the development of a publicly operational Carbon Compass tool for 'NYC Local Law 97,' championing energy efficiency in compliant buildings. Spearheaded end-to-end project management, ensuring seamless execution from ideation to deployment.
- Designed and deployed Tableau Dashboard merging energy benchmarking and mortgage lien holder data, providing comprehensive data visualizations of largest financiers of NYC’s LL97 carbon emissions to promote sustainable finance.
- Integrated financial analytics to identify sustainable investment trends among key financiers of NYC’s LL97 carbon emissions.
Graduate Student Researcher
June – Dec 2023 | New York, US
- Led a cancer research initiative, employing Large Language Models and Named Entity Recognition (NER) to automate gene annotation in research articles. Streamlined the updation process of OncoKB database by accelerating gene annotation tasks through the development of a BioMed-BERT-powered model, mitigating manual efforts and reducing time-intensive processes.
- Engineered an end-to-end pipeline that fetches new research from PubMed, performs predictions, labels diverse genes, and seamlessly updates the OncoKB database, ensuring a continuous and precise flow of annotated genetic information.
Data Science Intern
June – Dec 2023 | Florida, US
- Trained an ensemble machine learning model (XGBoost and SVM) to predict ticket tiers with 94% accuracy, securing lucrative partnerships with multiple prestigious sports venues and directly generating $100K in revenue through ticket sales.
- Streamlined categorization by performing unsupervised machine learning on ticket sales data, implementing BIRCH and K-Means clustering algorithms to create 5 tiers hence enabling efficient analysis.
- Formulated dynamic pricing problem as price forecasting problem and developed custom analytical explainable models that generated insights to help the pricing team, reduced the price approval time by 15 minutes.
- Built a reinforcement learning model using off-policy evaluation to dynamically price tickets, tested prices using A/B testing.
- Collaborated with the strategy analyst team to enhance clustering algorithms, boosting model accuracy and reliability, and developed a business solutions dashboard to convey technical insights to non-technical stakeholders through data storytelling.
Machine Learning Intern
Jan – April 2022 | Pune, India
- Accelerated manual classification of cells in histopathological images, resulting in 80% increase in efficiency, by building Image Segmentation Models to detect and count different types of cells.
- Enhanced accuracy by 15% and expedited preprocessing with 40% increase in speed to 3 seconds by streamlining pipeline to incorporate Deep Learning model for keyword extraction on text, post speech-to-text conversion.
- Engineered pipeline to perform face-matching post-enhancement of government IDs and portrait photos using GANs.
Data Science Intern
Aug 2021 – Mar 2022 | Netherlands (Remote)
- Improved accuracy of model by 20%, as measured by its ability to classify colors based on reflection values, by implementing ensemble of Random Forest and Light Gradient Boosting Models using Scikit-Learn.
- Simplified color recipe-generating process by building Machine Learning models to generate color recipes using solid colors.
- Rationalized relating colors and toners by analyzing large-scale color recipe datasets and performing ETL processes.
Junior Data Science Associate
April – July 2020 | Mumbai, India
- Led development of text-cleaning pipeline, reducing processing time by 40% to 7 seconds and expediting integration of data.
- Implemented a baseline recommendation system using sentiment analysis for a client's social media application, leading to an increase in user retention time by 3 minutes as validated through A/B testing.
- Conducted and facilitated knowledge transfer by hosting a tutoring session for 11 full-time staff members.
Data Analyst Intern
April – June 2020 | Mumbai, India
- Maximized supply chain efficiency of Covid-19 vaccines by designing and publishing a collaborative dashboard using Tableau and Dash, used AWS to extract key metrics. Presented it to the Andhra Pradesh government as a proposal.
- Analyzed historical data and market trends to predict need of essential supplies at hyper-granular level in India (ad hoc queries).
- Managed SQL database (over 40 tables with 100,000 rows) for COVID-19 Project, integrated by mobile and web applications.