Data Analyst · Business Analyst · AI/ML

Turning data into
decisions.

MSc in Data Science & Analytics. Nine projects across marketing, retail, fintech, and applied ML, built to find the number that changes the decision.

About

A generalist by training, a specialist by habit

I work end-to-end with data: cleaning and validating it, writing SQL and Python to analyze it, and building Tableau and Power BI dashboards that make it usable for decisions. My project work spans applied ML (churn classification, customer segmentation, anomaly detection), AI-augmented analytics (LLM-generated insights and recommendations, RAG-based chat interfaces), and business-facing analytics (marketing spend, retail pricing, fintech risk), alongside internship experience turning raw engineering and telemetry data into structured, reportable formats.

Currently looking at Data Analyst, Business Analyst, Data Science, and adjacent roles across India and the UAE, open to whichever team fits best.

MScData Science & Analytics, Jain University
BScStatistics, Sree Sankara College (MG University)
Based inBengaluru & Kochi
Projects

Nine problems, nine datasets

1.1B+ impressions analyzed

Marketing Campaign Performance Analysis

200K+ AdTech records across 6 channels, tracing 109M+ clicks back to a 14.04% average CTR.

SQLExcelTableau
View on GitHub
Window fns · RANK · CTEs

Customer Behaviour Analysis

Retail SQL analysis using window functions and CTEs, surfacing a counter-intuitive discount-effectiveness insight.

PythonSQLPower BI
View on GitHub
Random Forest + Groq LLM

AI Retail Profitability Analysis

9,977 transactions engineered into an explainable risk score, classified High-Risk vs. Not with a Random Forest model, and explained through Groq-generated recommendations and a RAG-lite Streamlit chat assistant.

PythonScikit-learnGroq LLMStreamlit
View on GitHub
0.9921 ROC-AUC

Fintech Customer Risk & Behaviour Intelligence

K-Means segmentation into 4 groups, XGBoost churn classification, and Ridge/Lasso credit-limit regression with hypothesis testing.

PythonScikit-learnXGBoost
View on GitHub
600x efficiency gap found

Cross-Channel Media Intelligence

3,051 weekly records across 26 divisions and 4 channels; Z-score flagging caught 267 anomalies and a Q4 spike to 131M vs. a ~47M average.

PythonSQLMatplotlib/Seaborn
View on GitHub
71% logistic accuracy

Behavioural Risk Analysis & Anomaly Detection

A unified pipeline combining KNN regression, logistic regression, and K-Means (K=5), engineered into anomaly scores that surfaced high-risk and high-spend segments.

PythonScikit-learn
View on GitHub
RAG · v1

AI-Powered RAG Document Q&A System

A retrieval-augmented Q&A API over documents, served through FastAPI with ChromaDB and Groq.

FastAPIDockerChromaDBGroq
View on GitHub
RAG · v2 / agentic

Agentic RAG Assistant

An upgraded assistant with LangChain 1.0, live web search, conversational memory, and dynamic file upload, with a Streamlit chat UI.

LangChainFastAPIGroq LLaMA 3.1Tavily
View on GitHub
76% accuracy

Audio Sound Classifier

ESC-50 sound classification comparing MFCC baselines against YAMNet transfer learning, deployed as a Flask app.

PyTorchYAMNetFlask
View on GitHub
Skills

Toolkit

Languages & Analysis

PythonSQLRSAS

BI & Visualization

TableauPower BIDAXAdvanced Excel

ML & AI

Scikit-learnXGBoostRandom ForestMachine LearningLangChainGroq LLM

Cloud & Data Infra

AWSBigQuerySnowflakeMongoDBDocker

Tools & Practices

GitJIRAAgileData Governance
Experience

Where the data came from

Data Analyst Intern, Techzia Solutions LLP
Bengaluru · Feb 2026 – Jul 2026
  • Analyzed a 58,862-row vehicle telemetry dataset (temporal driving actions and tracking errors across 15 columns) using Excel, Python, and Power BI to surface trends in velocity, steering, acceleration, and error metrics
  • Cleaned and structured real-world sensor data from an IoT prototype vehicle, resolving inconsistencies and preparing analysis-ready datasets for downstream reporting
  • Built Power BI visualizations and DAX measures from telemetry and tracking-error data for driving-behavior analysis, and supported a team member on IoT sensor-integration and data quality checks
Documentation Intern, Almiya Engineering Consultants Pvt Ltd
Kochi, Kerala · Jun 2025 – Jul 2025
  • Sourced, cleaned, and validated 50+ engineering project records using Python and Excel
  • Built interactive Tableau dashboards to track and communicate project progress to stakeholders
  • Maintained structured documentation artefacts aligned with project timelines
Certifications

Continued learning