"Would YOU Survive the Titanic?", with ML and .NET
summary
Uses Visual Studio 2022 and C# with ML.NET to solve Kaggle's Titanic challenge, starting with Jupyter/VS Code for EDA (pandas, matplotlib) then building ML.NET pipelines with custom mappings, one‑hot encoding and an age‑predictor to fill missing values. The process yields about 78.95% accuracy on Kaggle after hand‑crafted features (title, cabin deck, family size); a web app that predicts survival is deployed (in‑memory, no data stored) and the model runs and scores successfully.
AI-written summary · about
chapters (14)
- 0:00Introduction and context
- 1:19Understanding machine learning
- 3:53The machine learning process
- 6:10Historical context of Titanic
- 8:54Titanic trivia and media
- 12:23Data schema and key passengers
- 15:57Exploratory data analysis
- 20:33Identifying predictive patterns
- 26:23Implementing solutions in ML.NET
- 33:46Refining features and models
- 37:10Handling missing data
- 39:52Refined model implementation
- 47:34Audience simulation
- 50:12Advanced techniques and conclusion
related talks
39m"Would YOU Survive the Titanic?", with ML and .NET
01h 23mMachine learning in Action
39mPredicting Titanic Survivors with Machine Learning
57mMachine Learning Made Easy – An Introduction to ML.NET
44mA Practical-ish Introduction to Data Science
27mUsing Machine Learning to solve a classification problem with scikit-learn
51mHow to Test Artificial Intelligence and Machine Learning Solutions?
44mPredict the Future with Watson Studio AutoAI