I am a Data Scientist from India.
transforming messy, unstructured datasets into clear narratives that drive business decisions.
With a technical foundation in Computer Science and AI/ML from SRM Institute of Science & Technology, I bring an advanced algorithmic lens to traditional data analytics. I don’t just report numbers; I uncover the "why" behind the trends to help organizations navigate complex business challenges with precision.
SQL
Data Pipeline
Python
GitHub
Excel
Docker
PowerBI
Machine Learning
Python | PostgreSQL | Pandas | Scikit-learn | FastAPI | Streamlit | Power BI
An end-to-end e-commerce data pipeline built in Python. This project covers raw data ingestion, data cleaning, feature engineering, machine learning for churn and CLV, a REST API backend, a Streamlit frontend and an LLM-powered customer insights experience.
GitHub - ArpanSurin/Drivers-earning-performance-and-risk-analysis
PostgreSQL | Power BI
An interactive dashboard designed to understand DAX functions and driver revenue distribution across different cities, earning segments (active vs at risk) and also the driver count.
GitHub - ArpanSurin/Drivers-earning-performance-and-risk-analysis
Power BI | SQL Server
This project analyzes historical hotel booking data to understand revenue performance across years and compare City Hotels vs Resort Hotels. The analysis was performed using SQL Server, and insights were visualized through an interactive Power BI dashboard.
Altair: Data Science | Virtual
July 2025 - September 2025
Applied data preprocessing, visualization and model evaluation techniques using real world datasets.
Built predictive models and conducted feature engineering workflows to solve analytical problems.
Designed and executed basic pipelines on structured and unstructured data using the Altair platform
**[Certificate of completion](<https://drive.google.com/file/d/1GKVMMU45pAxeaJUNjWhJlPXvgLG-xICF/view?usp=sharing>)**
$$ \begin{aligned} Thanks~for~taking~the~time~to~visit~my~portfolio! \end{aligned} $$