Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Devarsh Shah, a data-driven Quantitative Research enthusiast currently advancing my MSc in Finance with a focus on financial mathematics at Ulm University. I enjoy turning complex market data into actionable investment insights using Python, ML, and robust analytics. During my internships, I built end-to-end investment analysis tools, automated reporting pipelines, and ML-powered decision frameworks at the intersection of finance and technology. I thrive in cross-functional teams and am eager to apply these skills to challenging problems in data science and software development.…I am Devarsh Shah, a data-driven Quantitative Research enthusiast currently advancing my MSc in Finance with a focus on financial mathematics at Ulm University. I enjoy turning complex market data into actionable investment insights using Python, ML, and robust analytics. During my internships, I built end-to-end investment analysis tools, automated reporting pipelines, and ML-powered decision frameworks at the intersection of finance and technology. I thrive in cross-functional teams and am eager to apply these skills to challenging problems in data science and software development.

Devarsh Shah

Data Scientist, AI Engineer, AI Developer, +2





I am Devarsh Shah, a data-driven Quantitative Research enthusiast currently advancing my MSc in Finance with a focus on financial mathematics at Ulm University. I enjoy turning complex market data into actionable investment insights using Python, ML, and robust analytics. During my internships, I built end-to-end investment analysis tools, automated reporting pipelines, and ML-powered decision frameworks at the intersection of finance and technology. I thrive in cross-functional teams and am eager to apply these skills to challenging problems in data science and software development.…I am Devarsh Shah, a data-driven Quantitative Research enthusiast currently advancing my MSc in Finance with a focus on financial mathematics at Ulm University. I enjoy turning complex market data into actionable investment insights using Python, ML, and robust analytics. During my internships, I built end-to-end investment analysis tools, automated reporting pipelines, and ML-powered decision frameworks at the intersection of finance and technology. I thrive in cross-functional teams and am eager to apply these skills to challenging problems in data science and software development.

Available to hire

I am Devarsh Shah, a data-driven Quantitative Research enthusiast currently advancing my MSc in Finance with a focus on financial mathematics at Ulm University. I enjoy turning complex market data into actionable investment insights using Python, ML, and robust analytics.

During my internships, I built end-to-end investment analysis tools, automated reporting pipelines, and ML-powered decision frameworks at the intersection of finance and technology. I thrive in cross-functional teams and am eager to apply these skills to challenging problems in data science and software development.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

German

Beginner

Work Experience

Quantitative Research Intern at Tipson’s Financial Services

June 1, 2025 - June 1, 2025

Developed a full-stack investment analysis and recommendation system using Python, MySQL, and Streamlit, integrating Q-learning and clustering models to segment investors and optimize bond recommendations. Automated daily deal bill generation and report creation pipelines, reducing manual reporting time. Built web scraping tools for NSDL, NSE, and BSE to extract market and bond data, enabling competitor trade tracking and price analysis. Designed a portfolio analytics dashboard in Power BI using R scripts and SQL queries, providing real-time insights into trade performance and market positioning.

Machine Learning Intern at Metis Intel lisystems Pvt Ltd

December 1, 2024 - December 1, 2024

Developed a machine learning model using satellite and agricultural big data to predict crop outcomes and optimize loan approval decisions for agribusiness financing. Built a predictive framework combining real-time market data, crop yield trends, and credit scoring metrics to improve decision-making for NBFCs and rural lenders. Created a farmer-specific data processing pipeline to classify farms by size, soil type, and weather patterns, enabling targeted financial risk assessment and resource allocation.