AI/ML engineering student building practical machine learning systems across telecom, healthcare, digital twins, and explainable model pipelines.
Predicts handover timing using prediction, trend smoothing, and volatility control to reduce unstable decisions in 5G mobility scenarios.
Python / Stability scoring / 5G handover logic Nokia Top 3Telecom QoS risk model with SHAP-based root cause insight, built for proactive SLA violation detection and fast operational triage.
Python / SHAP / QoS logs / Flask DeployedDecision-tree cardiovascular risk model built without ML libraries, showing fundamentals, preprocessing, evaluation, and clinical data interpretation.
Python / Custom decision tree / Flask / Data vizA Flask-based AutoML workflow that selects models, applies model-specific preprocessing, tunes hyperparameters, and produces SHAP-style explanations for transparent decision support.
Python / AutoML / Explainability / Model selectionA small simulation environment for testing how traffic load, latency targets, and bandwidth limits affect network-slice decisions before moving toward ML-based optimization.
Python / Network slicing / QoS metrics / SimulationOpen to ML internships, applied AI work, research collaborations, and backend/frontend project roles.
Python
Machine Learning
Deep Learning
Flask
HTML
CSS
JavaScript
Data Visualization
MySQL/PostgreSQL
Git
GitHub
Notion
Jupyter
VS Code
Ditto
Docker
Kubernetes
You can expand and visit the cards to access some of the live project deployments.
Click the deployed project cards to see live demos of these models in action.
My journey in machine learning began with building a decision-tree–based cardiovascular risk predictor, demonstrating interpretable AI on clinical datasets. Later, I developed a service-license agreement violation predictor that earned a top 3 finish at Nokia Campus Connect 2025, tackling QoS risk proactively for 5G/6G networks. Currently, I’m architecting an AutoML pipeline that automates preprocessing, feature engineering, and model explainability, aimed at scalable, transparent ML workflows.
I’m always open to collaborating on impactful projects, discussing new opportunities, or simply exchanging ideas around AI, machine learning, and technology for good. Feel free to reach out through the following channels:
Alternatively, you can fill out the form below, and I’ll get back to you as soon as possible.
