About MeProjectsWritingContact

Projects

Case studies in applied ML, deep learning, and data science - each with quantified results and technical reasoning.

⭐ Featured
4 weeks → 15 min
Enterprise agentic AI · 22-agent orchestration

Agentic Audit Assistant — 22-Agent Orchestration for Regulated Audits

An enterprise agentic system that compressed regulated pre-audit preparation from four weeks to fifteen minutes. A lead orchestrator runs Plan-and-Execute across 22 specialized sub-agents with federated tool and data access, built-in observability, and conversational follow-up — validated in use by the audit team it was built for.

Multi-Agent OrchestrationPlan-and-ExecuteDatabricksAzure AI SearchPython+2
ProprietaryRead Case Study →
91.6%Accuracy · +21% over baseline

Brain Tumor Classification from MRI Scans

Clinical decision-support system achieving 91.6% accuracy on 4-class brain tumor classification - a +21.35% improvement over baseline using transfer learning with EfficientNet-B3 and a custom medical image preprocessing pipeline.

PythonPyTorchComputer VisionMedical Imaging+3
CodeRead Case Study →
200+Sensors · Real-time ML

AI-Driven Anomaly Detection — Industrial Sensor Intelligence

Built an early-warning system for industrial process failures across 200+ sensor channels, combining Isolation Forest, LSTM and Autoencoder ensembles with a Gemini-powered chat interface for operator queries. Shipped a Streamlit monitoring dashboard, a simulated real-time streaming pipeline, and automated alerting workflows, deployed to GCP with a modular Python codebase.

PythonIsolation ForestLSTM AutoencoderTime Series+4
CodeRead Case Study →
0.82 F1Entity Extraction · BioBERT

Clinical NLP NER

Automated extraction of medical entities from clinical notes - fine-tuned BioBERT achieves 0.82 F1 on disease/medication/procedure extraction, accelerating chart review and supporting clinical decision-making.

PythonNLPBioBERTSciBERT+3
CodeRead Case Study →
NLPTF-IDF · Word2Vec · Sentiment

Text Analytics on 10-K Filings

NLP-driven analysis of SEC 10-K filings in the apparel sector - extracts strategic themes using TF-IDF and Word2Vec, quantifies sentiment trends, and surfaces competitive intelligence from unstructured financial disclosures.

PythonNLPWord2VecTF-IDF+2
CodeRead Case Study →
79.1%ModelNet40 · From Scratch

PointNet 3D Classification

From-scratch PointNet implementation achieving 79.1% on ModelNet40 - learns directly from unordered 3D point clouds using permutation-invariant architecture, without voxelization or mesh conversion.

PythonPyTorchDeep LearningPointNet+3
CodeRead Case Study →
ROIKMeans Clustering · Deployed

Vancouver Airbnb Investment Intelligence Dashboard

Data-driven investment analysis tool - grades Vancouver Airbnb properties by ROI potential using KMeans clustering, maps neighborhood opportunities, and forecasts revenue. Built with real Inside Airbnb data, deployed on Streamlit.

StreamlitPythonScikit-learnPlotly+2
Demo CodeRead Case Study →
TableauInteractive Dashboard · BI

Airbnb in Vancouver Data Visualization

Interactive Tableau dashboard revealing pricing trends, neighborhood performance, and seasonal patterns in Vancouver's short-term rental market - supports investment scouting and market research with drill-down visualizations.

TableauData VisualizationBusiness Intelligence
Demo CodeRead Case Study →
Real-timeVADER NLP · Trend Analysis

YouTube Sentiment Intelligence Dashboard

Real-time sentiment analysis of YouTube comments - analyzes audience reaction at scale using NLTK VADER, with 24-hour trend visualization, auto-refresh, and AI-generated insights. Deployed on Streamlit.

YouTube APINLTK VADERStreamlitPython+1
Demo CodeRead Case Study →
GPT-4oVision + Language · Deployed

PhotoCaption-AI

AI-powered caption generator combining GPT-4o vision and language capabilities - analyzes photos and produces contextually relevant, stylized Instagram captions with user feedback tracking in PostgreSQL. Deployed on Streamlit.

OpenAI GPT-4oStreamlitPythonPostgreSQL+1
Demo CodeRead Case Study →