LIVE INFERENCE
House price prediction.
Send property features to the deployed machine learning service and receive a prediction through the inference API.
MODEL INPUT
Property details
PREDICTION RESULT
API connection pending
—
A prediction will appear here after the frontend is connected to the deployed BentoML inference endpoint.
HOW IT WORKS
Browser to model.
01 / INPUT
Property data
User-entered model features
→
02 / API
HTTP request
JSON sent to inference service
→
03 / MODEL
HouseService
BentoML model inference
04 / RESPONSE
Prediction
Model response returned as JSON
→
05 / UI
Result display
Prediction rendered in browser