Skip to content
View joshndala's full-sized avatar

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Highlights

  • Pro

Block or report joshndala

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
joshndala/README.md

Hello, I'm Josh 👋

🎓 Computer Science graduate from the University of British Columbia

💻 Software Developer and Data Scientist

🤖 Passionate about Machine Learning, AI, and Data Analysis

🌐 Full-stack web development enthusiast

💼 Professional Experience

Web Developer @ TRIUMPH College Consulting

Aug 2024 - Dec 2024 | Toronto, ON, Canada (Remote)

Built a comprehensive full-stack platform for a US-based educational consulting startup, enabling streamlined college application support for international students.

Tech Stack: Next.js, Tailwind CSS
Key Features: Dynamic content management, student progress showcase, consultation scheduling

AI & Backend Developer @ UBC for Learnification

May 2024 - Aug 2024 | Kelowna, BC, Canada

Led full-stack development of an AI-powered assignment grading system for an ed-tech startup, achieving 75% faster grading speeds and 20% improved user satisfaction.

Tech Stack: Express.js, Node.js, React, Material-UI, MySQL, Phi-3 LLM, Ollama
DevOps: Docker, GitHub Actions, Mocha/Chai, Jest

🚀 Featured Projects

Project Timeline Key Technologies Description Links
Web Intent Classification System Oct 2024 - Present React, Python, Flask, AWS Bedrock, Llama 3 A full-stack web application that analyzes website content and generates contextual questions to classify visitor intent. Features AWS DynamoDB for efficient data retrieval and data analysis. View Project
Automated Fake News Detection Jan 2024 - Apr 2024 Python, TensorFlow, BERT, LSTM Processed 43,000+ examples, achieving 99% accuracy on news datasets and 73% on Bangladeshi tweets. Conducted comprehensive sentiment analysis. View Project
Smartphone Price Prediction Oct 2024 Python, XGBoost, Random Forest End-to-end ML pipeline with 96.5% prediction accuracy, processing 1,500+ entries with optimized ETL. Improved baseline accuracy by 4.5%. View Project
Cyclistic Bike-Share Analysis Aug 2023 - Oct 2023 R, RStudio, Tableau Analyzed 2.9 million data entries to derive strategic marketing insights for bike-sharing service. View Project
ForumRank Website Jan 2023 - Apr 2023 PHP, MySQL, AJAX Custom discussion platform with real-time search, interactive filtering, and responsive design. -
Public Library System Sept 2022 - Dec 2022 Java, JavaFX, MySQL Comprehensive library management system integrating Google Books, TVMaze, and JokeAPI. View Project

💼 Skills

Python Java R JavaScript React Node.js Express.js MySQL TensorFlow HTML5 CSS3 Docker Git

🛠 Tools & Platforms

  • Amazon Web Services
  • Google Cloud Platform
  • Docker
  • Google Colab
  • Jupyter Notebooks
  • Tableau
  • RStudio
  • Scikit-Learn
  • Matplotlib & Seaborn

🌱 I'm currently learning

  • Advanced Machine Learning techniques
    • Currently pursuing IBM's Machine Learning Professional Certificate
    • Deep dive into various model types and their applications
    • Recent focus on regularization techniques to prevent overfitting
  • Natural Language Processing
  • Cloud computing platforms
  • Data visualization tools

📫 How to reach me

LinkedIn Email GitHub

Pinned Loading

  1. web-visitor-classifier web-visitor-classifier Public

    A full-stack app that analyzes website content and generates multiple-choice questions to classify visitor intent. Built with React/Material UI frontend, Flask backend with AWS Bedrock (Llama 3) fo…

    Python

  2. fake-news-detection fake-news-detection Public

    Exploring deep learning models (LSTM, RNN, BERT) for the detection of fake news. A study on how efficiently they are able to differentiate between fake news and actual news.

    Jupyter Notebook

  3. phone-classification phone-classification Public

    A machine learning project analyzing 1,500+ smartphones to predict prices based on technical specifications. Using feature engineering and multiple ML models (Linear Regression, Random Forest, and …

    Jupyter Notebook

  4. Cyclistic-Case-Study Cyclistic-Case-Study Public

    A thorough data analysis of Chicago bike-share startup Cyclistic, evaluating the differences in service usage between annual subscribers and casual users, along with suggestions for a fresh approac…

    R