Data Science & Analytics Intern
I am a Data Science & Analytics Intern with hands-on experience in SQL-based data extraction, Power BI dashboard development, and Python data analysis built through a data science internship and applied analytics projects. I trained a Random Forest classifier with GridSearchCV hyperparameter tuning, achieving 93.6% accuracy, 94.5% F1-score, and 99.7% recall on churn prediction. I am currently seeking a Data Analyst role to apply strong analytical thinking, attention to details, and data visualization skills toward measurable business outcomes.
Built a 3-page Power BI dashboard on an 80K-row Flipkart e-commerce dataset, covering executive KPIs, sales & revenue performance, and seller & delivery performance for stakeholder self-service reporting. Designed DAX measures for Total Revenue, Return Rate %, Average Discount %, Average Delivery days, and Low Stock Products to monitor business health across categories, seller, and cities. Built an executive overview with revenue trend, category, and seller breakdowns plus year, category, and city slicers, and a seller-city revenue map with drill-through pages for deeper analysis.
Extended the internship model into a full analytics workflow, combining SQL-based data extraction with Python data processing to simulate an end-to-end pipeline from raw data stakeholder-ready insights. Queried relational datasets using SQL to extract customers demographics and behavioural patterns, feeding validated, cleaned outputs into the analysis pipeline. Conducted options analysis on churn drivers (payment delay, support call frequency, subscription type) via feature importance, translating technical outputs into actionable business recommendations.
Designed a multi-page Power BI dashboard with Dax measures to track and validate sales KPIs – revenue, average selling price, units sold, dealer-region performance. Built drill-through reports and slicers enabling business teams to interrogate data and filter by-region, model and time period.
Sept 2025 - Mar 2026
Performed end-to-end data extraction, transformation, and processing on 500k+ customer records, building a modular scikit-learn ColumnTransformer (imputation, scaling, encoding) to prepare data for analysis. Queried and validated structured datasets, applying quality checks (Stratified K-fold cross-validation, ROC-AUC, full metrics suite) to maintain data integrity and catch inconsistencies before deployment. Trained a Random Forest classifier with GridSearchCV hyperparameter tuning, achieving 93.6% accuracy, 94.5% F1-score, and 99.7% recall on churn prediction. Conducted structured EDA and requirement-driven feature analysis on customer behavioural data (tenure, usage frequency, support calls, payment delay) to surface business-relevant churn drivers.
June 2026
May 2026
April 2026
April 2026
March 2026
Bachelor of Engineering in Computer Science • 2021 - 2025
7.65
Higher Secondary • April 2021
81.1%
Interested in collaboration or just want to say hello? Feel free to reach out!