Titanic-Survival

Inspiration

My inspiration for this project came from a wanting to deepen my understanding of machine learning. I wanted to build a project that was both educational and engaging, which led me to the Titanic dataset. It allowed me to explore predictive modeling while also offering interesting insights into which types of passengers were more likely to survive.

What it does

This project is an interactive web dashboard that predicts whether a Titanic passenger would survive based on factors such as age, class, sex, fare, and other features.

How I built it

I started by cleaning the data to address missing values and adjust values so the model could understand. Then used a catboost model to train and predict survival outcomes. After the model was finished, I created a Streamlit dashboard where users can input data and see the prediction.

Challenges I ran into

One of the main challenges was handling missing data and preprocessing complex features such as Cabin. Since the Cabin field contains both letters and numbers, it required additional transformation to be used by the model.

Accomplishments that I'm proud of

I am proud to have successfully built and deployed a complete machine learning application from start to finish. Creating an interactive dashboard that feels like a real product and overcoming deployment and UI challenges felt satisfying.

What I learned

Through this project, I learned how to develop a machine learning model and turn it into a web application. I gained hands-on experience with data preprocessing, model training, and building an interactive dashboard for real-time predictions.

What's next for Titanic-Survival

In the future, I plan to improve the model’s accuracy by incorporating additional features. I also aim to enhance the UI by adding more detailed visualizations and interactive elements to better explain how predictions are made.

Built With

• jupyter-notebook
• matplotlib
• pandas
• plotly
• python
• scikit-learn
• streamlit