Aditya Kapil
Product Manager
www.linkedin.com/in/aditya-kapil | github.com/aditya1463 | candidates.intervues.club/u/aditya-kapil
SUMMARY
Product Manager candidate with a background in engineering, data analytics, and quantitative modeling. Proven track record in integrating AI APIs into reporting workflows, developing time-series forecasting models, and building KPI-focused business intelligence dashboards. Skilled in translating analytical insights into actionable product and strategy recommendations.
EXPERIENCE
Data Analyst Intern
Socteamup
Jun 2025 – Aug 2025
- Integrated the OpenAI API into internal reporting workflows to automate natural-language summaries of KPI anomalies.
- Engineered ARIMA-based forecasting models in Python to evaluate product usage patterns and delivered weekly SQL-driven reports that enhanced sprint retention.
- Designed and maintained Power BI dashboards tracking 12+ KPIs while establishing standardized data validation checks across ingestion pipelines.
EDUCATION
Netaji Subhas University of Technology (NSUT), New Delhi · B.Tech · 2026
Navyug Convent School, Najafgarh, Delhi · Class 12th, CBSE · 2022
St Mary’s Convent School, Gajraula, U.P. · Class 10th, CBSE · 2020
SKILLS
Languages and Frameworks: C++, HTML, Python, ShaderLab, SQL, Apache Spark, matplotlib, NumPy, pandas, scikit-learn
Databases: PostgreSQL
Tools: Celery, ETL Pipelines, Git, Jupyter Notebook, MS Excel, OpenAI API, Power BI, REST APIs, Tableau
PROJECTS
AI-Powered Business Intelligence Dashboard
Built a BI pipeline pulling sales, ops, and engagement data from multiple sources into Power BI dashboards tracking 15+ KPIs using ARIMA and linear regression forecasting. Constructed an end-to-end BI pipeline aggregating multi-source metrics into unified Power BI dashboards. Applied ARIMA and linear regression models to generate predictive forecasts on operational metrics.
Python, SQL, Power BI, OpenAI API, pandas
Customer Churn Prediction and Segmentation Model
Analyzed 50,000+ customer records using SQL and pandas to perform exploratory data analysis, feature engineering, and predictive churn modeling. Analyzed 50,000+ customer records via SQL and pandas to identify primary churn drivers through feature engineering. Developed and evaluated Random Forest and XGBoost classification models to segment high-risk users.
Python, scikit-learn, SQL, pandas, Power BI
AWARDS
Finalist (Top 5/120), Inter-College Risk & Analytics Case Competition, Best Quantitative Project, ECE Department, NSUT, Top 10/350+, Quant Coding Challenge (HackNSUT), JEE Mains, Top 4% (among 1.2M+ candidates)