📌 Project Overview This project analyzes wildlife collision data to identify factors affecting vehicle damage. Insights from Exploratory Data Analysis (EDA) are validated using statistical tests to ensure accuracy.

##Dataset Source: Kaggle - Airplane Bird Strikes

##Objective: To predict damage from bird strikes, identify key risk factors, enhance safety, optimize costs, and support regulatory compliance.

##Key Findings:

Most bird strikes do not cause damage, but severe cases exist.

Takeoff & landing are the most vulnerable flight phases.

Larger birds pose higher risks.

Strikes vary across locations.

Larger aircraft with more engines provide better protection.

Improved safety measures can reduce costs and disruptions.

##Model Development: Using a Voting Classifier that combines Decision Tree, XGBoost, and LightGBM.

##Performance Highlights:

Accuracy: 92%

Recall: 54%

(Future improvements will focus on recall to reduce false negatives.) Model is well-generalized and captures key patterns in bird strikes.

##Technologies Used: Python (Pandas, NumPy, Matplotlib, Seaborn), Statsmodels & SciPy, Jupyter Notebook.