Insights & Learning
Scope:
All shops (combined)
Valley Automotive
EuroPro Automotive
⬇ Export training data (CSV)
Suggested tuning (you approve — Phase 2)
- 💡 Diagnostic conversion is 0% (8 jobs) — a sign contact-time follow-up on diagnostics needs attention.
—
Estimate accuracy
0 jobs · est —h vs actual —h
29%
Recommendation hit rate
38 assigned jobs
0%
Diagnostic conversion
0 of 8 converted
100%
Deadline met
15 of 15 completed
By complexity tier
| Tier | Jobs | Avg actual hours | Est→actual ratio | Avg GP % |
|---|---|---|---|---|
| High | 8 | — | — | — |
| Medium | 126 | 4.73 | — | 58.0% |
| Low | 13 | — | — | — |
Observed technician performance (from completed work)
| Technician | Jobs | Avg actual hours | Implied efficiency | Avg GP % |
|---|---|---|---|---|
| Spirka, Charlie | 40 | 5.46 | need estimates | 68.0% |
| Verhaeghe, Jered | 22 | 9.55 | need estimates | 65.0% |
| Meldrum, Zack | 6 | 0.07 | need estimates | 5.0% |
| Sean Lake | 4 | 2.98 | need estimates | 66.0% |
| Franklin, Blake | 2 | 0.5 | need estimates | 47.0% |
| Traweek, Derrik | 2 | 5.1 | need estimates | 62.0% |
| Reed, Josh | 1 | 0.0 | need estimates | — |
Implied efficiency compares estimated vs actual hours — the data-driven version of the number you set per technician. It sharpens as more imports land.
The road to combined ML
Phase 1 (now): every import snapshots outcomes here — pooled across both shops. Phase 2: the suggestions above become approve-able tuning. Phase 3: once enough history accrues, the exported training data trains models (job duration, best technician, deadline risk) whose predictions feed back into the workflow. Combined across shops means a bigger, richer dataset than either shop alone.