Read-only demo
No credits charged
No private job access
Time Series Count Regression
Weekly Event Count Forecast
What is the expected count of weekly events in the next period?
A time-series count workflow showing ordered time data, count-target checks, model comparison, and forecast-oriented review.
Demo outcome
Count Inception
Best model
Selected from replayed saved metrics.
2.760
Poisson Deviance
Primary metric for this workflow.
75 seconds
Observed run time
Demo replay based on saved job behavior.
This workspace is a guided public replay.
Training, SHAP, report generation, prediction, job deletion, and billing actions are unavailable in demo mode.
Completed
Demo ID: demo-time-series-count
Saved-output workflow
The demo, handbook, and job page use the same saved outputs.
Each item below comes from the completed source job, so the public replay matches what users review after a real run.
Data setup
Summary Only
The example records the data roles and checks shown in the replay.
None
Analysis checks
Summary Only
The replay explains the checks expected for this type of analysis.
None
Model explanation
Summary Only
The replay describes how model findings should be interpreted.
None
Reproducibility boundary
Available
The demo is read-only and does not run training, prediction, or billing.
None
Methods appendix
Available
A concise methods note is bundled with this public example.
methods_appendix.md
Dataset and roles
Readiness preview input
- Rows
- 520
- Features
- 6
- Target
- event_count
- Format
- XLSX
- Status
- Pass
time
target
features
Workflow steps
How the job moved
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 outputs
What users review
Time ordering check
readiness
Confirms time parsing and series continuity.
Count metric table
metrics
Poisson deviance, RMSE, MAE, and training time.
Forecast review notes
report
Interpretation for count outcomes and spikes.
Model comparison
Replayed performance table
| Model | Status | Metric | Value | Training Time |
|---|---|---|---|---|
| Count Inception | Best | Poisson Deviance | 2.760 | 3.7s |
| TCN Count | Trained | Poisson Deviance | 2.779 | 4.4s |
| GRU Count | Trained | Poisson Deviance | 2.835 | 5.5s |
| Count ARIMA | Baseline | Poisson Deviance | 3.570 | 0.8s |
Report summary
Decision-ready notes
- The workflow keeps temporal order explicit before training.
- Count Inception produced the lowest Poisson deviance in this demo.
- Forecast outputs should be reviewed for high-count periods before operational use.
Observed vs fitted
Seasonal pattern
The model follows the main temporal structure without treating records as unordered rows.
Residual check
Review spikes
High-count spikes should be reviewed before operational use.
Model comparison
Count Inception
Primary metric is lower-is-better for Poisson deviance.
Live log replay
The event stream users see during a real run
Press Replay logs to stream the curated demo events.
Ready for your own data?
Use the real workflow with authentication and billing safeguards.
A real run requires sign-in, readiness preview, visible cost estimate, and confirmation before training starts.