The problem
People see one monthly bill and cannot tell which appliances drive it, so saving advice stays generic.
What to build
Develop a model that infers appliance-level usage from smart meter data and recommends the most valuable savings.
Success looks like
Appliance-level estimates validated against sub-metered data on a public dataset and savings tips ranked by impact.
Suggested technologies
- Non-intrusive load monitoring
- Time-series ML
- Smart meter data
- Recommendations
- Privacy
An original, independent statement. It is not an official Smart India Hackathon problem statement, and Arventiq Labs is not affiliated with or endorsed by that programme. The scenario is illustrative and does not describe any specific organisation. Free to use with credit.