Select a service area, service stage, and survey question. Advanced factor settings are optional.
Delivery of Frontline services
The cards below place this question alongside other questions from the selected service stage, so its evidence strength can be compared fairly.
Start with “Ready for interpretation.” Treat “Use with caution” as supporting evidence, and do not make strong claims from indicators that need stronger evidence.
Available data: The current dataset does not include direct access-barrier variables such as distance, waiting time, facility supply, staff interaction, or household service need. The portal should therefore improve the existing evidence first instead of inventing unavailable predictors.
Eligible responses: Stage-specific modeling is applied through the saved stage response files and skip-pattern handling: Awareness uses valid awareness responses; Availment uses the availment stage; Satisfaction and Need for Action are interpreted only for respondents who reached the service-use stage.
Predictor selection: The decision-tree pipeline now enriches the general profile and citizen-segment predictors with available service-context evidence when applicable: health background variables for Health Services, education background variables for Support to Education, and crime, disaster, corruption, and citizen-attitude evidence for Governance and Response. Feature selection remains part of the model search, while chi-square is kept in the citizen segment evidence area as profile-cluster support.
Model comparison: Recommended model comparison: keep Decision Tree as the official explanation model, then add Random Forest as a performance benchmark and Logistic Regression as a simple baseline. If another model improves ROC AUC or recall, report it as supporting evidence while keeping the decision tree for readable rules.
For Governance and Response - Awareness, the summary combines 8 indicator-specific decision-tree model(s). Mean F1 is 74.8% and mean ROC AUC is 59.7%, so the result should be read as an overall tendency across indicators. The indicator-level rows remain the main evidence for decision-support use.
Use the mean scores for the general story; use the indicator rows for the actual evidence.
Stage eligibility is handled before modeling: Awareness uses all valid Yes/No responses; Availment uses Awareness = Yes; Satisfaction and Need for Action use Awareness = Yes and Availment = Yes. Skip-pattern values such as 95-99 are excluded from the target class.
Show how strongly each available factor influenced the model result.
Read the tree together with its plain-language insights.
Show readiness review, indicator metrics, rule reference, and diagnostics.
| Indicator | Signal Quality (F1 / ROC AUC / Recall / Baseline) | Meaning | Majority Response (Baseline Class) | Eligible Records | Baseline Accuracy (Majority Guess) | Model Accuracy | Gain (Model - Baseline) | Possible Cause | Suggested Data Improvement |
|---|---|---|---|---|---|---|---|---|---|
| G1_GGPv Timely Response on Peace and Order andPublic Safety-related incidents |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (87.7%) | 4350 | 87.7% | 79.5% | -8.2 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPi Delivery of Frontline services |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (84.0%) | 4500 | 84.0% | 79.0% | -4.9 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPiv Conflict and dispute resolution in the barangays |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (83.8%) | 4200 | 83.8% | 77.0% | -6.8 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPviii Public Information Services |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (70.3%) | 4200 | 70.3% | 65.2% | -5.1 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPvii Disaster Risk Reduction and Management |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (76.3%) | 4350 | 76.3% | 64.0% | -12.3 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPii Local government’s response or action oncomplaints against an office,official orpersonnel of the LGU |
Limited signal | The model can be reviewed as an exploratory clue, but F1, ROC AUC, or baseline gain is not strong enough for confident prediction. | Yes / Positive (63.8%) | 4050 | 63.8% | 61.9% | -1.9 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPvi Traffic Management |
Moderate signal | The model has some useful signal based on F1 and ROC AUC, but separation between outcome groups is still limited. | Yes / Positive (61.6%) | 4050 | 61.6% | 61.2% | -0.4 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
| G1_GGPiii Mobile LGUservices/Provision ofmunicipal services to the barangays |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (69.1%) | 4050 | 69.1% | 42.3% | -26.7 pts | The result may be close to the majority-class baseline, meaning the model adds limited separation beyond the most common response. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Governance and Response. |
The AVG values summarize 8 indicator model(s) for Governance and Response - Awareness. They describe the overall pattern across indicators, not the result of one specific indicator.
Average F1 is 74.8%, which gives the most balanced quick reading because it considers both correct positive predictions and missed positive cases.
Average ROC AUC is 59.7%, so the model should be read as decision-support evidence. Values closer to 50% mean the predictors have limited ability to separate the outcome groups.
Average accuracy is 66.3%, precision is 77.6%, and recall is 74.5%. Compare the indicator rows below to see which indicators are stronger or weaker than the AVG.
| Target | Indicator | Accuracy | Precision | Recall | F1 | ROC AUC | CV F1 | Best CV F1 | Selected Features | Base Predictors | Service Context | Total Predictors | Depth | Leaf | Criterion |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| G1_GGPv | Timely Response on Peace and Order andPublic Safety-related incidents | 79.5% | 90.1% | 86.1% | 88.0% | 61.3% | 89.0% | 88.3% | 8 | 17 | 18 | 35 | 3 | 10 | gini |
| G1_GGPi | Delivery of Frontline services | 79.0% | 86.6% | 88.7% | 87.6% | 65.0% | 83.6% | 88.5% | 8 | 17 | 18 | 35 | 3 | 10 | entropy |
| G1_GGPiv | Conflict and dispute resolution in the barangays | 77.0% | 86.7% | 85.8% | 86.2% | 61.6% | 74.3% | 84.0% | 8 | 17 | 18 | 35 | 5 | 10 | entropy |
| G1_GGPviii | Public Information Services | 65.2% | 75.3% | 75.4% | 75.3% | 61.8% | 75.3% | 76.3% | all | 17 | 18 | 35 | 3 | 10 | entropy |
| G1_GGPvii | Disaster Risk Reduction and Management | 64.0% | 81.1% | 68.8% | 74.4% | 63.4% | 79.9% | 77.9% | 8 | 17 | 18 | 35 | 5 | 35 | entropy |
| G1_GGPii | Local government’s response or action oncomplaints against an office,official orpersonnel of the LGU | 61.9% | 65.6% | 84.7% | 73.9% | 54.6% | 57.2% | 68.7% | all | 17 | 18 | 35 | 5 | 10 | entropy |
| G1_GGPvi | Traffic Management | 61.2% | 65.9% | 76.6% | 70.9% | 58.1% | 62.6% | 72.0% | 8 | 17 | 18 | 35 | 3 | 10 | gini |
| G1_GGPiii | Mobile LGUservices/Provision ofmunicipal services to the barangays | 42.3% | 69.1% | 30.0% | 41.8% | 51.7% | 59.1% | 72.9% | 8 | 17 | 18 | 35 | 3 | 10 | gini |
| Code | Meaning | Code Values / Variable Type | How to Read the Split |
|---|---|---|---|
| Dim1 | MCA profile dimension 1 | A combined respondent-profile score from MCA. It is not a single survey question. | Dim1 <= 0.801 follows one side of the profile map; values above 0.801 follow the other side. |
| MCACluster_4 | Citizen segment | Cluster membership from the citizen segmentation model. | Use this as a respondent segment indicator, not as a direct survey answer. |
| Node | Type | Rule | Gini | Samples | Not Aware | Aware | Prediction |
|---|---|---|---|---|---|---|---|
| 0 | Split | Dim1 <= 0.801 | 0.5 | 4500 | 0.5 | 0.5 | Aware |
| 1 | Split | Dim1 <= -0.689 | 0.4997 | 3876 | 0.5 | 0.5 | Aware |
| 2 | Split | Dim1 <= -0.858 | 0.4952 | 583 | 0.5 | 0.5 | Not Aware |
| 3 | Leaf | Prediction | 0.471 | 86 | 0.4 | 0.6 | Aware |
| 4 | Leaf | Prediction | 0.4897 | 497 | 0.6 | 0.4 | Not Aware |
| 5 | Split | Dim1 <= -0.554 | 0.4988 | 3293 | 0.5 | 0.5 | Aware |
| 6 | Leaf | Prediction | 0.4824 | 675 | 0.4 | 0.6 | Aware |
| 7 | Leaf | Prediction | 0.4999 | 2618 | 0.5 | 0.5 | Aware |
| 8 | Split | MCACluster_4 <= 0.500 | 0.491 | 624 | 0.6 | 0.4 | Not Aware |
| 9 | Split | Dim1 <= 1.086 | 0.4953 | 531 | 0.5 | 0.5 | Not Aware |
| 10 | Leaf | Prediction | 0.4917 | 70 | 0.4 | 0.6 | Aware |
| 11 | Leaf | Prediction | 0.4921 | 461 | 0.6 | 0.4 | Not Aware |
| 12 | Split | Dim1 <= 1.202 | 0.4501 | 93 | 0.7 | 0.3 | Not Aware |
| 13 | Leaf | Prediction | 0.3947 | 50 | 0.7 | 0.3 | Not Aware |
| 14 | Leaf | Prediction | 0.496 | 43 | 0.5 | 0.5 | Not Aware |