Open to Opportunities · Bengaluru

Poorani
Muthu

ML Engineer · Data Scientist · IIT (ISM) Dhanbad

I build ML systems that ship. From fraud detection achieving AUC 1.0 on 50K financial transactions to production-grade ETL pipelines, model monitoring with automated drift detection, and full-stack analytics platforms — I take problems from raw data all the way to deployed, measurable impact. 6 live production systems. 32 automated tests. Real business outcomes.

Fraud Detection
AUC 1.0
50K credit card transactions
FraudGuard · Live on Railway
Reporting Latency Cut
40%
Real-time Power BI dashboards
@ Andritz Technologies
Forecasting Accuracy
9.4%
MAPE · ForecastIQ
Retail time-series · Live
Revenue Insights Surfaced
$85M
48K+ listings · SQL ETL
Airbnb NYC Analysis
Career

Work Experience

Jun 2025 – Present
Andritz Technologies Ltd.
Bengaluru, Karnataka
Graduate Engineering Trainee — ML & Data Analytics
  • Engineered scalable end-to-end ML pipelines and statistical models in Python and SQL on manufacturing operations data, increasing resource efficiency by 15% and improving operational reliability across workflows.
  • Deployed predictive analytics models integrated with real-time Power BI dashboards with advanced DAX measures, reducing reporting latency by 40%; implemented automated data validation and integrity protocols ensuring accuracy of KPIs presented to senior leadership.
PythonSQLPower BIDAXETL PipelinesML Deployment
May 2024 – Jul 2024
SRIP IIT Gandhinagar
Gandhinagar, Gujarat
Research Intern — Control Systems & ML
  • Developed control systems for complex chemical processes using MATLAB/Simulink, integrating machine learning for system identification and performance optimisation.
  • Implemented Particle Swarm Optimization (PSO) and Response Surface Methodology to minimise control errors by 28% across nonlinear systems through convergence data analysis.
Machine LearningMATLAB/SimulinkPSO OptimizationProcess Control
Sep 2023 – Mar 2024
Nernst Energy Solutions LLP
Remote
Data Analyst
  • Applied quantitative cost-benefit modelling and vendor risk analysis on financial datasets, reducing operational risk by 20% and supporting strategic procurement decisions with data-driven recommendations.
  • Built interactive Tableau dashboards communicating ML-backed investment strategies to senior stakeholders, achieving 100% alignment on data-driven recommendations.
TableauExcelStatistical ModellingStakeholder Management
Dec 2023
Indian Oil Corporate R&D Centre
Faridabad, Haryana
Research Intern — Battery Materials
  • Synthesised sodium hexacyanoferrate cathode materials for Na-ion batteries; applied statistical analysis to correlate synthesis parameters with sodium storage capacity (150+ mAh/g) and intercalation kinetics from cyclic voltammetry datasets.
Data AnalysisMaterials ScienceStatistical Modeling
Technical

Skills & Expertise

ML & Data Science
Machine Learning Statistical Modelling Predictive Modeling A/B Testing Fraud Detection Time-Series Forecasting Customer Segmentation EDA
MLOps & Pipelines
Model Drift Detection KS Test · PSI Automated Retraining Apache Airflow PySpark ETL Design Feature Engineering Flask REST APIs
Languages & Tools
Python (Pandas, NumPy, Scikit-learn) SQL (Advanced) Power BI (DAX) Tableau Plotly.js Excel (Power Query) C++17 Java · JavaScript Git · GitHub Docker · Railway
Cloud & Platforms
Databricks Lakehouse Azure Data Factory AWS (learning) Vercel WebAssembly / Emscripten
GenAI (building)
HuggingFace Transformers LoRA / PEFT Fine-tuning RAG Pipelines LangChain Prompt Engineering ChromaDB
Soft Skills
Stakeholder Management Cross-functional Collaboration Data Storytelling Executive Reporting Client-first Mentality
Portfolio

Featured Projects

● Live 🛡️
FraudGuard — End-to-End Fraud Detection

Production ML system on 50,000 credit card transactions. Manually implemented SMOTE in NumPy, trained 3 classifiers achieving AUC 1.0, deployed as a Gunicorn-served Flask REST API with 5-page interactive frontend. Full automated build-train-serve pipeline.

50K transactions AUC 1.0 SMOTE from scratch SHAP explainability
● Live 📡
ModelWatch — ML Drift Detection & Monitoring

Production MLOps system simulating 4 drift types across 12 months on a credit scoring model. Automated detection via KS Test & PSI, AUC tracking from 0.85→0.72→0.85 post-retraining. Full model feedback loop deployed live.

4 drift types KS Test · PSI Auto-retraining Live dashboard
● Live 📈
ForecastIQ — Time Series Forecasting App

Three forecasting algorithms (Gradient Boosting, Holt-Winters, Seasonal Naïve) evaluated via walk-forward cross-validation on Rossmann retail data. Best model: MAPE 9.4%. 8-page Flask + Plotly.js dashboard with live 90-day forecast.

5,634 rows MAPE 9.4% 3 algorithms 90-day forecast
● Live 👥
SegmentIQ — Customer Segmentation Dashboard

End-to-end RFM analysis and K-Means clustering on 50,000 transactions. 7-page interactive dashboard covering segment profiles, revenue breakdown, trend analysis, and strategy recommendations. Built for executive and non-technical audiences.

50K transactions RFM + K-Means 7-page dashboard Live on Railway
● Live
AdPulse — Google Ads Analytics Platform

Full-stack ad campaign analytics platform with JWT auth, role-based access, and 8 analytics pages. Three C++17 engines compiled to WebAssembly: A/B testing (Welch t-test), keyword matching (Porter Stemmer), click fraud detection (Z-score + bot CV). 32 automated tests.

C++17 → WebAssembly 32 automated tests JWT auth React + Java Spring Boot
GitHub 🏗️
RetailSync — Legacy ETL Migration Pipeline

End-to-end migration from Informatica/SSIS flat-file ETL to PySpark. Apache Airflow DAG orchestration, automated data quality checks (Z-score, null rates, referential integrity), RFM scoring, and Parquet output replicating AWS Glue patterns.

10K ERP records PySpark + Airflow Star schema 5 quality checks
GitHub 🏙️
Airbnb NYC 2019 — Revenue Analysis

End-to-end Python ETL pipeline processing 48K+ listings into an optimised SQLite database. 12 targeted SQL queries uncovering $85M in Manhattan revenue potential and identifying high-demand neighbourhoods like Williamsburg.

48K+ listings $85M revenue insight 12 SQL queries SQLite ETL
GitHub 📉
Customer Churn & Revenue Risk Analysis

Python EDA pipeline on 7K telecom customers. Applied NVF/NCRF scoring to segment users by value and risk, identifying $12M+ revenue at risk from Month-to-Month contracts with retention strategy recommendations.

7K customers $12M+ at risk NVF/NCRF scoring Retention strategy
ML 🔬
K-Means Clustering — Income Segmentation

Applied K-Means clustering to segment individuals by annual income and spending patterns. Identified 5 distinct customer clusters with centroid analysis, comprehensive visualisations, and pattern discovery from unsupervised learning.

K-Means 5 clusters scikit-learn Centroid analysis
Academic

Education

May 2025
IIT (ISM) Dhanbad
B.Tech — Chemical Engineering
CGPA: 7.66 / 10.00
Mar 2021
Velammal Vidyalaya
12th Standard · Mel Ayannambakkam, Chennai
92%
Mar 2019
SBOA School & Junior College
10th Standard · Chennai
95%
Credentials

Certifications

📊
Google Data Analytics Certificate
Google · Coursera
🐍
Python for Data Science and AI
IBM · Coursera
🗄️
SQL for Data Science
UC Davis · Coursera
Honours

Achievements

🏆
Runner-up — Chem-e-Flow, Concetto
Led the runner-up team in Chem-e-Flow, the inter-collegiate competition at the annual tech fest Concetto, IIT Dhanbad.
💃
Bharatanatyam Arangetram
Trained in classical dance for 10+ years and completed the prestigious solo debut performance (Arangetram) on August 28, 2016.
🥇
Gold Medal — NSO 2019 (District)
Awarded the Gold Medal in the National Science Olympiad at the district level in 2019.
Let's Connect

Say Hello

Open to ML Engineer, Data Scientist, and Analytics roles where I can ship production systems that make a measurable difference. If you're building something ambitious — let's talk.