Read-only upload replay 0 credits
Time Series Count Regression

Weekly Event Count Forecast

This page shows the upload form, role mapping, readiness preview, model selection, and cost confirmation recorded for the completed source job.

Demo boundary
Actual job evidence, no upload

The controls below replay the completed job setup and are intentionally disabled.

Upload forms stay visible enough to teach the workflow.
This replay is sourced from saved outputs from completed jobs; real users still sign in before launching their own jobs.
1
Load dataset demo-time-series-count_source_dataset
2
Map roles Target, features, and service-specific columns
3
Preview readiness Pass
4
Launch saved job 75 seconds replay
Step 1 and 2

Dataset and role mapping before readiness

520 rows, 6 features, XLSX.
Step 3

Preview Data Readiness completed successfully

Pass
Confirm ordering
The time column was parsed and the target was validated as count-like.
Compare count models
Classical and deep time-series count models were compared.
Inspect forecast behavior
Error, deviance, and trend summaries are ready for review.
Saved evidence created for review
Data setup Analysis checks Model explanation Reproducibility boundary Methods appendix
Step 4

Training configuration that launched the saved job

Preset
Saved job configuration
Models
4
Reserved
0 credits
Count Inception TCN Count GRU Count Count ARIMA
Validation split
0.2 holdout
Runtime mode
Recorded completed job
Source job
saved job
Open completed job