ALGO LOG
MS Data Science · UMD · GPA 3.78

Ajaykumar
Balakannan

>

Building systems that learn, adapt, and reveal hidden patterns — from large-scale anomaly detection pipelines to real-time forecasting models. Grounded in electrical engineering, fluent in modern data science.

Live K-Means · click canvas to resetinitialising…
Gradient descent · loss surfacewaiting…
Logistic classifier · live trainingwaiting…
3.78
GPA @ UMD
2nd
National Hackathon
15M+
Records Processed
10+
Yrs Survey Data
Experience

Work History



May – Aug 2025
Canaria Inc.
New York, NY
Data Science Intern
  • Built v0 statistical models and v1 unsupervised PyCaret pipelines (Isolation Forest, KNN, HBOS, OCSVM) on 15M+ records, containerized with Docker — improving anomaly detection accuracy by 35%.
  • Designed CI/CD workflows with GitHub Actions and Docker for reproducible, real-time ML model deployment and monitoring.
  • Developed Grafana dashboards and Python signal processing pipelines, reducing monitoring time by 25%.
PyCaretIsolation ForestDockerGrafanaCI/CD
Sep 2024 – May 2025
Counseling Center, UMD
College Park, MD
Graduate Data Analyst
  • Led SQL ETL workflows (Informatica) and Tableau dashboards — improving counselor scheduling efficiency by 25%.
  • Applied hypothesis testing and sentiment analysis on 10+ years of survey data; findings helped secure increased budgets for two consecutive quarters.
SQL · InformaticaTableauSentiment AnalysisPython
Skills

Technical Stack



Core Proficiency
Python · NumPy · Pandas · Sklearn92%
ML / Anomaly Detection88%
SQL · Data Engineering85%
Visualization · Tableau · Grafana80%
Cloud · Docker · CI/CD75%
Deep Learning · NLP78%
Machine Learning
Isolation ForestHBOSRandom ForestXGBoostARIMASVMYOLOv5KNN
Programming & Data
PythonRSQLMATLABPandasNumPyPyCaret
Engineering & Cloud
DockerApache SparkAWSAzureGit/CI-CDPostgresClickHouse
Visualization
TableauPower BIGrafanaQlik SenseExcel (Pivot)
Embedded & Signal
ArduinoARM CortexDSPIoT8051
Projects

Selected Work



01 — COMPUTER VISION
Agricultural Animal Intrusion Detection

YOLOv5 + CNN ensemble with hardware-integrated microcontroller pipeline. Automated deterrents (sirens, ultrasonic) for real-world precision agriculture.

YOLOv5CNNArduinoIoT
🏆 2nd Place · National Hackathon · BIOGECKO Published
02 — TIME SERIES
Bitcoin Price Forecasting Pipeline

End-to-end ARIMA + XGBoost forecasting with automated ingestion, validation, and Qlik Sense dashboards for real-time volatility insights.

ARIMAXGBoostQlik SenseSQL
03 — RISK ASSESSMENT
Space Debris Risk Assessment via ML

ML-driven orbital debris collision risk pipeline with multi-platform dashboards in Tableau, Qlik Sense, and Jupyter for real-time visibility.

XGBoostTableauJupyterPython
Education

Academic Background



Master's in Data Science
University of Maryland
Expected May 2026 · Maryland, MD
GPA: 3.78 / 4.0
NLP · Machine Learning · Big Data Systems · Deep Learning
B.Tech — Electrical & Electronics Engineering
Sri Krishna College of Engineering & Technology
Aug 2020 – May 2024 · Coimbatore, India
CGPA: 8.4 / 10.0
Microcontrollers · Power System Analysis · Python · ML in Energy Systems
Let's Build
Together.

Open to full-time roles, internships, and research in data science, ML engineering, and analytics.