About Me
I am a Data Science undergraduate focused on building practical data analytics skills using Python, SQL, and Power BI. I have completed multiple virtual internships and industry simulations with organizations such as Microsoft, McKinsey, Tata Group, and Shell.
I have hands-on experience converting raw data into clear, business-focused insights. I am actively seeking Data Analyst internships, project collaborations, and entry-level opportunities.
Open Source Contributions
Data Analyst – SSoC 2025
Reskill | Apr 2025 – Aug 2025 | Bhopal, India
- Contributed to open-source data analytics projects using Python and Power BI.
- Performed data cleaning, transformation, and exploratory data analysis.
- Created dashboards and analytical reports to visualize trends and insights.
Projects
1. Global Military Power & Country Analytics Dashboard
Tech Stack:Python · Web Scraping · Pandas · Data Cleaning · Power BI · DAX · Data Visualization · Dashboard Development
Global Military Power & Country Analytics Dashboard — Built a 4-page interactive Power BI dashboard during my Infosys Springboard internship for country-level analysis, comparison and coalition analysis across military, economic and demographic indicators. link
- Quick Stats — country rankings, GDP, total assets, military burden, defense budget, labour force, manpower and foreign reserves.
Compare Power — side-by-side comparison of two countries across GDP, active personnel, defense budget, budget per soldier, assets and manpower.
Coalition Builder — interactive comparison of a reference country against selected coalition countries using assets, personnel, GDP and defense-budget metrics.
Nation Overview — selected-country analysis covering GDP, population, purchasing power, land area, military personnel, assets and other country-level indicators.
2.User Journey & Funnel Analysis
User Journey & Funnel Analysis
Analyzed user journey events using PostgreSQL to evaluate the Save investment funnel, conversion rates, completion time, and user drop-offs. Built SQL queries using CTEs, window functions, aggregations, conditional logic and statistical functions to derive actionable funnel insights.
Tech StackPostgreSQL | SQL | CTEs | Window Functions | Aggregations | Data Analysis
Key Analysis
- Save Journey Funnel & step-wise conversion
- Median journey completion time
- Largest user drop-off identification
- First-event-per-user analysis
3. Real-Time Air Pollution Monitoring & Health Risk Scoring System
Data Analytics & Real-Time Monitoring Project
Developed a real-time air pollution monitoring system to collect, process and analyze air-quality data and generate health risk scores based on pollution levels. Built a data pipeline to handle incoming environmental data and developed an interactive Streamlit dashboard for monitoring trends and risk indicators.
Tech Stack:Python | Pandas | PostgreSQL | Supabase | Streamlit | Plotly | Data Cleaning | Data Pipeline | Data Visualization
Key Contributions
- Collected and processed real-time air-quality data through an automated data pipeline.
- Performed data cleaning, transformation and validation using Python.
- Stored and managed historical and real-time data using Supabase/PostgreSQL.
- Analyzed pollution indicators and generated health risk scores from processed data.
- Built interactive visualizations for monitoring pollution trends and risk levels.
- Developed a Streamlit dashboard to present real-time and historical insights.
- Worked with structured data pipelines for continuous data ingestion and analysis.
4. Dashboards
Tech Stack -Power BI
Employee Attrition & Retention Analysis
Identified key drivers of employee attrition using performance, tenure, and overtime data to support retention decisions.
Netflix Content Performance Analysis
Analyzed Netflix content trends by genre, ratings, and release year to understand content performance patterns.
Currently building projects based on real-world use cases to demonstrate practical application of skills.
Tech Stack - Power BI
Diversity & Inclusion Analytics Dashboard
Analyzed hiring, promotions, and attrition metrics across departments to evaluate workforce diversity and inclusion trends.
Flipkart Sales & Customer Insights Dashboard
Built a sales analytics dashboard to track revenue, product performance, and customer behavior using key business KPIs.
5. AI-Based Disease Prediction & Health Assistant
Team Project | Data Analyst / Data Management
Tech Stack:Python | Pandas | NumPy | Data Collection | Data Cleaning | Data Preprocessing | EDA | Data Management | Machine Learning | Streamlit
Contributed to a team-based machine learning project by collecting, organizing, managing and preparing healthcare datasets used for disease prediction models. Supported the project by ensuring data quality, consistency and usability for downstream analysis and machine learning.
My Contributions
- Collected and consolidated relevant healthcare datasets for Diabetes, Heart Disease and Parkinson’s Disease prediction.
- Organized and maintained datasets for different prediction modules.
- Performed data cleaning and preprocessing to improve dataset quality and consistency.
- Checked data for missing values, duplicates, inconsistent formats and data-quality issues.
- Prepared structured datasets for machine learning model development.
- Supported exploratory data analysis (EDA) and understanding of important features, where applicable.
- Collaborated with the ML/development team to provide analysis-ready data.
- Documented datasets, variables and data preparation steps for smoother team workflow.
Project :- Link
Deepak Avachitkar