Flight Delay Prediction Project

Overview

This project focuses on predicting flight delays using a robust machine learning pipeline implemented with PySpark. The goal is to provide accurate predictions by optimizing model performance and aligning evaluation metrics with business objectives.

Key Features

• ML Pipeline: Built and deployed a flight delay prediction model using PySpark.
• Hyperparameter Tuning: Used Hyperopt for systematic tuning to achieve optimal model performance.
• Performance Metrics: Achieved an F-beta score of 0.9, balancing precision and recall effectively.

Files

• Flight-Prediction Phase 3 - (Final Report).ipynb: The final report on the model and its performance.
• Phase 3 - HyperOpt.ipynb: The notebook demonstrating hyperparameter tuning with Hyperopt.
• Phase 3 - Modeling - best.ipynb: The notebook containing the best-performing model.
• Team 6-2 Presentation (Final).pdf: Final presentation slides summarizing project outcomes.

Installation & Setup

1. Clone this repository.
2. Install required dependencies via pip install -r requirements.txt.
3. Run the notebooks to explore data processing, model training, and evaluation.

License

This project is licensed under the MIT License.

---

Let me know if you'd like any changes!