Titanic-Passenger-Survival-Prediction

A Machine Learning project focused on binary classification to predict passenger survival on the Titanic based on available passenger data.

Key Features:

End-to-End ML Pipeline: Covers all stages from data collection to modelling:

Data acquisition

Data cleaning

Exploratory Data Analysis (EDA)

Feature engineering

Feature selection

Model training and evaluation

Smart Data Analysis: Handles missing values, encodes categorical features, and explores relationships between features and survival.

Multiple ML Models: Experiments with models like Logistic Regression, Random Forest, Gradient Boosting to select the best-performing one.

Performance Evaluation: Uses Accuracy, Precision, Recall, F1-score, and ROC-AUC metrics for robust model assessment.

Interpretable Predictions: Identifies feature importance to understand which factors most influence survival.

Implementation Steps:

Load Dataset: Use Titanic passenger data from Kaggle or official sources.

Explore Data: Analyse columns such as Age, Sex, Passenger Class, Sib S p, and Parch.

Data Cleaning:

Handle missing values (e.g., Age, Cabin).

Remove irrelevant columns (e.g., Name, Ticket).

Feature Engineering:

Create new features like family size (Sib Sp + Parch).

Extract titles from passenger names to capture social status.

Data Transformation: Encode categorical features using Label Encoding or One-Hot Encoding.

Train-Test Split: Divide data into training and testing sets.

Model Training: Train and compare multiple classification models to select the best.

Model Evaluation: Assess model performance using multiple metrics to ensure accuracy and reliability.

Prediction: Use the trained model to predict survival for new passengers.

Project Value:

Provides insights into factors influencing passenger survival on the Titanic.

The model can be applied to similar datasets for survival or outcome predictions.

A strong addition to your Portfolio, demonstrating skills in Data Preprocessing, Feature Engineering, Model Selection, and Evaluation.