Built and deployed a Hybrid TE-GRU + LightGBM forecasting API for smart grid energy optimization

Built and deployed a Hybrid TE-GRU + LightGBM forecasting API for smart grid energy optimizationBuilt and deployed a Hybrid TE-GRU + LightGBM forecasting API for smart grid energy optimization

The network for creativity

Join 1.25M professional creatives like you

Connect with clients, get discovered, and run your business 100% commission-free

Creatives on Contra have earned over $150M and we are just getting started

Back to feedPost

David Ayo

• 1d

Built and deployed a Hybrid TE-GRU + LightGBM forecasting API for smart grid energy optimization backed by Bayesian MCMC confidence bounds, to ensure physical hardware can react safely to volatile energy demands. Seeing the manual testing dashboard light up and run flawless predictions through the FastAPI backend is an incredible feeling.

Machine Learning Engineering AI Development FastAPI Python TensorFlow

Cansaas Agency

pro

• Apr 30

In this design, we streamlined how users interact with their smart home by combining device control, real-time status, and automation into one clean interface. From adjusting temperature to managing scenes and monitoring devices, every interaction is designed to feel effortless. With soft visuals, clear hierarchy, and intuitive flows, controlling your home becomes faster, smarter, and more enjoyable.

📩 Collaborate with Us? Contra Cansaas Agency

Mobile Development UX Design UI Design Adobe Photoshop Figma mobileappdesign uidesign uxdesign

Istiak Ahmed Khan

• Apr 30

great job 👌

Ritvik Tiwari

• Apr 29

:Designed and developed a responsive school website with a clean UI and smooth user experience using HTML & CSS.

Web Development Website CSS HTML5 Python Visual Studio Code

Muyideenaliyah Ayomide

• Apr 30

nice

Bryan Munuve

• Apr 28

Built an interactive Streamlit dashboard that models revenue recovery scenarios for e-commerce stores. Allows filtering by customer state, product category, and payment type. Three interactive sliders model recovery assumptions — late delivery reduction, customer churn rate, and cancellation recovery rate — and instantly recalculate dollar outcomes. Identified $333,874 in structural revenue risk across 99,441 orders with recovery potential of $40K–$137K depending on execution.