Team 3

• 

  Team Members

Inspiration

We aimed to assist companies in estimating their Scope 1 and Scope 2 emissions using readily available data. Our goal was to support a sustainability initiative.

What it does

The project predicts greenhouse gas emissions for companies based on their features and actions. Our project visualizes patterns using histograms, scatter plots, and correlation heatmaps, and provides predictive models to estimate emissions accurately.

How we built it

We loaded and cleaned the datasets, explored the distributions of key variables such as revenue and region, created log-transformed revenue and other engineered features, selected meaningful variables, and trained regression pipelines for Scope 1 and Scope 2 predictions.

Challenges we ran into

We faced issues with skewed revenue distributions, missing data, and deciding which features were most informative. Visualizing relationships between variables and aligning predictions with actual emissions also required careful debugging.

Accomplishments that we're proud of

We successfully engineered new features, visualized data, built robust prediction pipelines, and created correlation heatmaps that highlighted meaningful relationships between features and targets.

What we learned

We gained experience in data cleaning, feature engineering, visualization, and predictive modeling, and learned the importance of interpreting model outputs to derive actionable insights.

What's next for Team 3

We plan to refine the models, explore more advanced features, and incorporate additional datasets to enhance prediction accuracy, making the tool even more useful for companies seeking to track and reduce their emissions.

Built With

• jupyternotebook
• vscode