All projects
CompletedAI / ML · Full Stack · Cloud & DevOps

SmartSkin

Skincare Compatibility System

SmartSkin connects an ML-assisted compatibility workflow to a practical web interface. It analyses product ingredients and a user's skin type, predicts suitability, and presents the result in a form designed to support routine decisions.

Project field / smartskin

Context

The problem space.

Skincare labels are dense and product suitability is personal. SmartSkin explores how a structured compatibility model can make those choices easier to reason about.

Confirmed work

What the evidence supports.

  • A Python-based machine-learning workflow predicts product suitability and compatibility.
  • A React interface exposes the analysis and supports personalized routine visualization.
  • The frontend and backend communicate through a REST API.
  • The application was containerized with Docker and used for Kubernetes-based local deployment experimentation.
PythonMachine LearningReactREST APIsDockerKubernetesGit

Related work

Keep exploring.

All projects
PNProject / 01

AI / ML

Personalized News Recommendation System

Semantic news discovery shaped around the reader

Completed

A news recommendation pipeline using text embeddings, topic clustering, preferences and semantic similarity.

  • Python
  • NLP
  • Sentence Transformers
  • Web Scraping
Case notes
View project
NTProject / 02

AI / ML · Research

NeuroTrace

Explainable deep learning for brain-tumor segmentation

Completed

A 3D medical-image segmentation framework combining Attention U-Net with GNN-driven attention, explainability and uncertainty estimation.

  • 3D Deep Learning
  • Medical Image Segmentation
  • Graph Neural Networks
  • Grad-CAM
Case notes
View project
HRProject / 03

Full Stack

House Rental Application

A concise full-stack rental workflow

Completed

A Java and SQL application for working through the core data flows of a house-rental experience.

  • Java
  • SQL
  • Java Applet
Case notes
View project