AUTOML with FLAML

Inspiration Leveraging FLAML to automate machine learning for efficient model selection and hyperparameter tuning on the Chevron dataset.

What it does Automatically finds the best ML models and configurations to analyze and predict trends in the dataset.

How we built it Used FLAML’s AutoML framework to train and optimize models with minimal manual intervention.

Challenges we ran into Extracting model insights, handling large datasets, and integrating SHAP for feature importance.

Accomplishments that we're proud of Achieved high model efficiency with reduced training time while maintaining strong predictive performance.

What we learned How to leverage AutoML for real-world datasets, optimize model selection, and interpret results effectively.

What's next for AUTOML with FLAML Enhancing interpretability, expanding feature engineering, and testing additional AutoML frameworks for comparison.

Built With

• automl
• flaml
• python