I'm an MSIS student at Northeastern University with a passion for solving complex problems. My problem-solving and critical thinking skills were developed through the Iranian National Olympiad in Information, where I ranked among the top 70 from 11 thousand participants.

Beyond my academic achievements, I bring hands-on experience in scripting and programming languages such as C++, Java, and Python, as well as web development technologies including JavaScript and React, with a focus on areas like Machine Learning, Data Mining, Web Scraping, Software Testing, and Software Development. I've applied these skills during two years as a Junior Data Scientist and a Quality Assurance Internship.

• View my Resume

Feel free to explore my projects below and connect with me for opportunities to collaborate or discuss potential roles.

• email: faridghr.cs@gmail.com
• linkedin: linkedin.com/in/farid-ghorbanii/

• FraudDetectivePy: The goal of this project is twofold: first, to understand how an imbalanced dataset can impact the analysis and results of credit card fraud detection; and second, to evaluate the effectiveness of different classification models and techniques aimed at enhancing the accuracy and reliability of fraud detection systems.
• ProductScraper: This project scrapes product information from the Digikala e-commerce website to extract details about available laptops, such as price, model, CPU, GPU, RAM, screen size, etc. The extracted data is stored in a MySQL database using the mysql library. Additionally, the project includes a simple machine learning model built with scikit-learn for predicting laptop prices based on user input configurations.
• Data Mining HorseColic: Using data mining techniques, including data preprocessing, feature selection, model training, and evaluation, the project seeks to uncover patterns and relationships within the dataset to improve prediction accuracy.
• WirelessChurnPrediction: This project aims to predict wireless account churn and identify key features driving churn. It is a collaborative effort between data scientists to develop a machine learning model that can help maintain and grow the revenue generating base by taking proactive measures to retain customers.

• Sales Performance: Two dashboards using tableau to help stakeholders, including sales managers and executives to analyze sales performance and customers.
• Netflix Infographic: A dynamic data visualization project that explores Netflix movies across various dimensions such as country filmed, release date, genre, ratings, frequent cast members, and directors.
• Airbnb Market Insights: Tableau visualizations and data analytics project using Airbnb listings data to identify key market trends, optimal investment locations, and strategies for maximizing rental income.

• DesignPatterns-RestaurantOrdering: This project is a practical exploration of design patterns, applied to a restaurant ordering system. It demonstrates how design patterns can be used to solve real-world software design challenges, resulting in a system that is flexible, scalable, and maintainable. The project utilizes multiple design patterns, including Singleton, Factory, Builder, Strategy, Composite, Adapter, Decorator, and Observer, to create a robust and extensible solution.
• BookShare Hub: BookShare Hub is a Java Swing-based application designed to create a community-driven platform for book sharing. It allows users to lend and borrow books from each other, promoting a culture of literature sharing.

• AutoBuddy: In this project, we aim to develop a domain-specific chatbot application that utilizes a Large Language Model (LLM) for natural language understanding and processing, combined with the efficiency and scalability of a vector database for data storage and retrieval. The application will implement the Advanced Retrieval-Augmented Generation (RAG) method to enhance the chatbot's ability to provide accurate and relevant responses by integrating retrieved information with generative AI capabilities. We also fine-tune GPT-4o-mini in this project with related data to achieve optimal performance.
• Evaluate RAG Pipeline: The aim of this project is to evaluate the performance of the RAG pipeline and explore methods to enhance its metrics. This project includes a Python notebook and a report file, which document the evaluation process and present an improved version of our RAG chatbot.
• Simple RAG Chatbot: The goal of this project is to develop a domain-specific application that combines the strengths of a Large Language Model (LLM) with the efficiency of a vector database for data storage and retrieval. Using Retrieval-Augmented Generation (RAG) for the method and Streamlit for the front-end, the application is built with Python.

• Image Filters: Image Filters is a Python project that offers a collection of creative filters for image manipulation using the OpenCV library. Each filter applies a specific transformation to the input image, resulting in visually distinct outputs.
• Python Pandas Tutorials: This repository contains a collection of tutorials to help you master the Pandas library, a powerful tool for data manipulation and analysis in Python.
• Python Matplotlib Tutorials: This repository contains a collection of tutorials to help you master Matplotlib, a versatile library for creating static, animated, and interactive visualizations in Python.
• Python NumPy Tutorials: This repository contains a collection of tutorials to help you master the NumPy library, a fundamental package for scientific computing and data manipulation in Python.