Table 1 Evaluation results (for Experimentation-Plan-ID-1)
From: DD-KARB: data-driven compliance to quality by rule based benchmarking
Experimentation-plan-ID = 1 | Error percentage | |||||||
|---|---|---|---|---|---|---|---|---|
Exp. 1 Telegram | Exp. 2 Eita | Exp. 1 | Exp. 1 Soroush | Exp. 1 Bale | Average | |||
Type of benchmark | Quantitative, based on stats | IR-QUMA (simple average) | 18.4 | 24.3 | 26.3 | 31.8 | 30.1 | 26.2 |
Quantitative, based on sense | Expert quality scoring | 17.5 | 23.1 | 25.4 | 30.2 | 29.8 | 25.2 | |
Declarative, based on analysis | KARB + hill climbing | 11.8 | 15.6 | 15.8 | 17.9 | 16.4 | 15.5 | |
Hybrid, based on solving | Data-driven KARB | 8.8 | 13.2 | 13.5 | 16.8 | 14.0 | 13.3 | |