
Greetings. I am Allan Ilyasov.
I'm a Graduate Student pursuing an M.S. in Data Science through an accelerated 4+1 program, after completing my B.S. in Computer Science. Currently working as a Graduate Research Assistant, I specialize in building AI-powered applications and scalable cloud infrastructure.
My expertise spans full-stack development, machine learning, and AWS cloud services. I've led the development of Codify AI, an AI-powered programming tutor, and won a hackathon for innovative AI solutions.
When I'm not coding, I'm contributing to Uncle Edik's Pickles, a startup I helped grow from a home-based operation to a national brand.
A machine learning study comparing lifestyle versus demographic factors as predictors of diabetes risk using 230K+ patient records. Analyzes which factors—such as diet, exercise, and family history—are most significant in predicting diabetes, using ensemble methods and cross-validation for robust predictions.
A modern, responsive portfolio website built with Next.js and Tailwind CSS featuring an interactive Matrix-style background, project showcases, and smooth navigation. Optimized for performance and SEO with server-side rendering and static generation.
An AI-powered programming tutor that helps students learn coding through interactive conversations without just providing pasted code. Features real-time code assistance powered by Claude 4.5 haiku via AWS Bedrock, with intelligent agentic workflows that adapt to each student's learning pace.
A comprehensive stock prediction system that analyzes and forecasts prices for AAPL, NVDA, and LYFT using multiple machine learning approaches. Combines traditional ARIMA statistical models with deep learning architectures (LSTM and GRU) to achieve highly accurate predictions across 1,458+ trading days.
A full-stack video analysis platform that enables intelligent searching and interaction with video content. Features visual search using CLIP embeddings, transcript search, and an AI chat interface powered by Gemini 2.5 Flash that can answer questions about video content with conversational memory.
Click anywhere to skip