Hardik Singh

Python | SQL | Tableau | Financial Markets | CFA L1 Aspirant

Nagpur, Maharashtra, India

About

Recent graduate from IIT KGP experienced in data analytics using python, seeking opportunities in Analytst, Finance, Development and Project Management.

Experience

  • Associate Analyst at RZR
    Jan 2026 - Present · 7 mos

  • Research Analyst at Chamber for Indo Russo Technology Collaboration
    Jul 2024 - Feb 2025 · 8 mos

    • Revamped SQL queries, enhancing data retrieval efficiency by 35% and managed successful data migration for 20+ projects. • Processed satellite data to forecast seasonal agricultural output, integrating results into commodity index movement predictions. • Performed agri-sector financial and investment analysis, developing a pitch deck that secured INR 50 lakh funding from investors.

  • Research Intern - Data Analyst ( Economics Department ) at Indian Institute of Technology Kharagpur
    Jun 2024 - Jul 2024 · 2 mos

    • Utilized pooled panel data for 37 countries & 2 years, aligning HS and ISIC codes with concordance tables for sectoral benchmarking. • Built a dataset of 25 manufacturing sectors with RCA indices, and firm-level controls, enabling financial modeling. • Applied fractional logit model to analyze how comparative advantage influences export intensity, producing quantitative insights. • Produced reproducible outputs, sector-level insights, and cross-country findings, supporting export and policy analysis in trade.

  • Research Intern - Data Analyst ( Centre of Excellence in Artificial intelligence ) at Centre for Artificial Intelligence, IIT Kharagpur
    Apr 2024 - Jul 2024 · 4 mos

    • Predicted the groundwater salinity of whole India based on 9 years of data • Preprocessed multivariate groundwater datasets (2013–2022) using advanced imputation, outlier detection, and feature scaling techniques and applied GIS-based spatial modeling and temporal trend analyses to map salinity risk zones with an accuracy of 90% in hotspot identification • Engineered predictive models using Random Forest and Gradient Boosting for salinity estimation, achieving mean absolute error reduction of 15% through k-fold cross-validation, and derived feature importance through statistical correlations • Developed LSTM and GRU architectures to capture spatiotemporal dependencies in groundwater salinity data, enabling high-accuracy trend forecasting and actionable insights for resource management