About Me
I am a data science professional with a passion for addressing complex global challenges. Originally from a small village near Pokhara, Nepal—a city renowned for its natural beauty and cultural heritage—I pursued undergraduate and graduate studies in economics, laying the foundation for a career dedicated to impactful problem-solving. I began my professional journey with a startup in India, working on cutting-edge applications of AI and machine learning. While this experience honed my technical skills, it also deepened my desire to apply these capabilities to a larger purpose. This drive led me to shift my focus to the public sector, where I could use data science, AI, and research to tackle pressing global issues. After nearly six years in data analytics, I moved to the United States to earn a master’s degree in public policy. Today, as a consultant with the World Bank, I combine my expertise in data analysis, machine learning, business intelligence, and geospatial analysis to contribute to solutions for challenges like climate change, sustainable development, and leveraging technology for social good. Outside of work, I am an avid soccer fan, having competed in—and occasionally won—several tournaments. Cooking, especially Indian cuisine, is one of my favorite pastimes, and I enjoy exploring diverse topics such as politics, philosophy, and religion. Music is another source of inspiration; I am a big fan and practice the guitar whenever time allows.
Skills
Technical
Statistical Analysis, Machine Learning, Natural Language Processing(NLP),Visualization, Geo-spatial analysis.
Programming
R, Python (Pandas, NumPy, scikit-learn, NLTK, Beautiful Soup), ArcGIS Pro/QGIS, SQL, Tableau, Excel, Stata.
Languages
English (Fluent), Nepali (Native), Hindi (Fluent), Spanish (A1)
Portfolio
Data Science Projects
Fraudulent Claims detection
About: Improved fraud detection models for an insurance company in the US, by utilizing text analytics using the claim notes. Used Natural Language Processing (NLP) techniques such as topic modeling, named-entity extraction to identify key features which were used in machine learning models such as XgBoost, Random Forest models. Significant improvement in capturing the fraudulent cases against traditional methods.
Skills: Topic Modeling, Word Vectorization, Python, PySpark, Databricks
Contact Me
Email: [email protected]
Phone: (412) 909-7272