Select a service area, service stage, and survey question. Advanced factor settings are optional.
Public Employment 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 Economic and Investment Promotion - Awareness, the summary combines 16 indicator-specific decision-tree model(s). Mean F1 is 50.6% and mean ROC AUC is 53.9%, 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 |
|---|---|---|---|---|---|---|---|---|---|
| J1_JEEiv Livelihood Programs |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (65.8%) | 4200 | 65.8% | 62.9% | -3.0 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 Economic and Investment Promotion. |
| J1_JETiii Investment promotion activities such as trade fairs, fiestas, business events and similar events |
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 (54.1%) | 4050 | 54.1% | 53.9% | -0.2 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 Economic and Investment Promotion. |
| J1_JEAii Access to irrigation facilities or equipment |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (54.1%) | 3600 | 54.1% | 53.7% | -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 Economic and Investment Promotion. |
| J1_JEAviii Accessible farmharvest buying/trading stations |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (50.6%) | 3300 | 50.6% | 54.4% | +3.8 pts | Citizen profiles may be too similar across outcome groups, or the survey may lack service-specific predictors. | Add or review awareness-source, barangay information channel, distance, and program availability variables for Economic and Investment Promotion. |
| J1_JEAi Organization and development of farmers, fishermen and their cooperatives |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (65.2%) | 4200 | 65.2% | 51.8% | -13.4 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 Economic and Investment Promotion. |
| J1_JEAvii Post-Harvest facilities such as crop dryers, slaughter houses or fish processing facilities |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (51.4%) | 4200 | 51.4% | 51.1% | -0.3 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 Economic and Investment Promotion. |
| J1_JEAiv Distribution of planting/farming/fishing materials and/or equipment |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (63.6%) | 4200 | 63.6% | 50.8% | -12.9 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 Economic and Investment Promotion. |
| J1_JEAiii Prevention and control of plant and animal pests and diseases; fish kill sand diseases |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (59.6%) | 4200 | 59.6% | 52.7% | -6.9 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 Economic and Investment Promotion. |
| J1_JETi Development and maintenance of touristattractions and facilities |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (58.6%) | 4200 | 58.6% | 51.0% | -7.7 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 Economic and Investment Promotion. |
| J1_JEEii Regulation and supervision of businesses |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (59.7%) | 4050 | 59.7% | 47.8% | -11.9 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 Economic and Investment Promotion. |
| J1_JEAv Access to facilities that promote agricultural production such as fish hatcheries and breeding stations |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (67.8%) | 3600 | 67.8% | 49.6% | -18.2 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 Economic and Investment Promotion. |
| J1_JETii Product/Brandmarketing and promotion of local goods and touristattractions |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (68.7%) | 3750 | 68.7% | 56.4% | -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 Economic and Investment Promotion. |
| J1_JEEi Public Employment Services |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | Yes / Positive (57.2%) | 4050 | 57.2% | 49.2% | -8.1 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 Economic and Investment Promotion. |
| J1_JETiv Organization,accreditation and training of tourism related concessions. |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (76.7%) | 2550 | 76.7% | 41.1% | -35.6 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 Economic and Investment Promotion. |
| J1_JEEiii Promotion of Barangay Micro Business Enterprises |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (60.5%) | 3150 | 60.5% | 59.6% | -0.8 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 Economic and Investment Promotion. |
| J1_JEAvi Water and soilresource utilization and conservation projects |
Needs more predictors | The model has difficulty separating respondents based on ROC AUC, recall, or F1. | No / Negative (63.9%) | 3600 | 63.9% | 58.1% | -5.8 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 Economic and Investment Promotion. |
The AVG values summarize 16 indicator model(s) for Economic and Investment Promotion - Awareness. They describe the overall pattern across indicators, not the result of one specific indicator.
Average F1 is 50.6%, which gives the most balanced quick reading because it considers both correct positive predictions and missed positive cases.
Average ROC AUC is 53.9%, 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 52.7%, precision is 51.9%, and recall is 54.3%. 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| J1_JEEiv | Livelihood Programs | 62.9% | 66.2% | 89.0% | 75.9% | 51.0% | 67.0% | 71.1% | 8 | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JETiii | Investment promotion activities such as trade fairs, fiestas, business events and similar events | 53.9% | 55.6% | 73.5% | 63.3% | 52.4% | 62.6% | 64.6% | all | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JEAii | Access to irrigation facilities or equipment | 53.7% | 56.3% | 64.1% | 59.9% | 55.0% | 46.2% | 60.2% | all | 17 | 0 | 17 | 3 | 35 | gini |
| J1_JEAviii | Accessible farmharvest buying/trading stations | 54.4% | 53.2% | 63.1% | 57.8% | 54.9% | 53.8% | 57.8% | 16 | 17 | 0 | 17 | 5 | 10 | gini |
| J1_JEAi | Organization and development of farmers, fishermen and their cooperatives | 51.8% | 68.8% | 47.9% | 56.5% | 55.8% | 63.6% | 69.8% | 8 | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JEAvii | Post-Harvest facilities such as crop dryers, slaughter houses or fish processing facilities | 51.1% | 49.8% | 61.4% | 55.0% | 52.2% | 44.0% | 53.3% | all | 17 | 0 | 17 | 6 | 10 | entropy |
| J1_JEAiv | Distribution of planting/farming/fishing materials and/or equipment | 50.8% | 67.3% | 44.0% | 53.2% | 53.6% | 61.8% | 67.7% | 8 | 17 | 0 | 17 | 3 | 35 | gini |
| J1_JEAiii | Prevention and control of plant and animal pests and diseases; fish kill sand diseases | 52.7% | 64.9% | 44.6% | 52.9% | 55.2% | 53.8% | 59.1% | all | 17 | 0 | 17 | 6 | 35 | gini |
| J1_JETi | Development and maintenance of touristattractions and facilities | 51.0% | 42.6% | 54.1% | 47.7% | 52.4% | 46.8% | 52.7% | all | 17 | 0 | 17 | 5 | 35 | entropy |
| J1_JEEii | Regulation and supervision of businesses | 47.8% | 60.0% | 37.7% | 46.3% | 51.7% | 52.9% | 61.2% | 8 | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JEAv | Access to facilities that promote agricultural production such as fish hatcheries and breeding stations | 49.6% | 34.9% | 65.2% | 45.4% | 53.1% | 43.9% | 42.2% | 8 | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JETii | Product/Brandmarketing and promotion of local goods and touristattractions | 56.4% | 36.2% | 51.4% | 42.5% | 57.6% | 42.5% | 43.9% | all | 17 | 0 | 17 | 6 | 10 | entropy |
| J1_JEEi | Public Employment Services | 49.2% | 60.5% | 32.2% | 42.1% | 53.6% | 56.2% | 61.1% | 16 | 17 | 0 | 17 | 3 | 10 | gini |
| J1_JETiv | Organization,accreditation and training of tourism related concessions. | 41.1% | 25.3% | 77.9% | 38.2% | 53.5% | 37.7% | 38.0% | all | 17 | 0 | 17 | 3 | 10 | entropy |
| J1_JEEiii | Promotion of Barangay Micro Business Enterprises | 59.6% | 48.3% | 31.5% | 38.1% | 56.3% | 46.5% | 46.2% | 8 | 17 | 0 | 17 | 6 | 35 | entropy |
| J1_JEAvi | Water and soilresource utilization and conservation projects | 58.1% | 39.9% | 31.7% | 35.3% | 54.2% | 46.4% | 43.0% | 16 | 17 | 0 | 17 | 6 | 35 | entropy |
| Code | Meaning | Code Values / Variable Type | How to Read the Split |
|---|---|---|---|
| A5 | Highest Educational Attainment | 1=Elem Undergraduate; 2=Elem Graduate; 3= Hi-Sch Undergraduate; 4=Hi Sch Graduate; 5=College Undergrad; 6=College Graduate ; 7= Masters Undergrad; 8=Masters Graduate; 9=Doctorate; 10=Vocational /TVET; 11=Apprenticeship; 99=Others | <= 4.5 means Elem Undergraduate, Elem Graduate, Hi-Sch Undergraduate, Hi Sch Graduate; > 4.5 means College Undergrad, College Graduate , Masters Undergrad, Masters Graduate, Doctorate, Vocational /TVET, Apprenticeship, Others. |
| B3 | HH Toilet Type | 1=Flush/Water-Sealed: OWN TOILET; 2=Flush/Water-Sealed: Shared; 3=PIT TOILET/LATRINE; 4=DROP/OVERHANG; 5=NO TOILET/OPEN FIELD; 99=OTHERS | <= 1.5 means Flush/Water-Sealed: OWN TOILET; > 1.5 means Flush/Water-Sealed: Shared, PIT TOILET/LATRINE, DROP/OVERHANG, NO TOILET/OPEN FIELD, OTHERS. |
| A3.1 | Age Group | 1=18→24; 2=25→29; 3=30→34; 4=35→39; 5=40→44; 6=45→54; 7=55→64; 8=65→74; 9=75 and above | <= 3.5 means 18→24, 25→29, 30→34; > 3.5 means 35→39, 40→44, 45→54, 55→64, 65→74, 75 and above. |
| A7 | Employment Status | 1=Working at least 40 hrs/wk; 2=Working less than 40 hrs/wk; 3=Not employed but looking for work; have worked in the past; 4=Not employed but looking for work; have not worked in the past; 5=No job, not looking for work; have not worked in the past; 6=Not employed, not looking for work; have worked in the past; 7=Student (not working); 8=Retired (not working) / Too old to work | <= 6.5 means Working at least 40 hrs/wk, Working less than 40 hrs/wk, Not employed but looking for work; have worked in the past, Not employed but looking for work; have not worked in the past, No job, not looking for work; have not worked in the past, Not employed, not looking for work; have worked in the past; > 6.5 means Student (not working), Retired (not working) / Too old to work. |
| Node | Type | Rule | Gini | Samples | Not Aware | Aware | Prediction |
|---|---|---|---|---|---|---|---|
| 0 | Split | A5 <= 4.500 | 0.5 | 4050 | 0.5 | 0.5 | Aware |
| 1 | Split | B3 <= 1.500 | 0.4982 | 2752 | 0.5 | 0.5 | Not Aware |
| 2 | Split | A3.1 <= 3.500 | 0.4997 | 2368 | 0.5 | 0.5 | Not Aware |
| 3 | Leaf | Prediction | 0.4915 | 554 | 0.6 | 0.4 | Not Aware |
| 4 | Leaf | Prediction | 0.5 | 1814 | 0.5 | 0.5 | Aware |
| 5 | Split | A7 <= 6.500 | 0.4662 | 384 | 0.6 | 0.4 | Not Aware |
| 6 | Leaf | Prediction | 0.4759 | 349 | 0.6 | 0.4 | Not Aware |
| 7 | Leaf | Prediction | 0.2968 | 35 | 0.8 | 0.2 | Not Aware |
| 8 | Split | A5 <= 54.500 | 0.4915 | 1298 | 0.4 | 0.6 | Aware |
| 9 | Split | A7 <= 1.500 | 0.4887 | 1251 | 0.4 | 0.6 | Aware |
| 10 | Leaf | Prediction | 0.4643 | 411 | 0.4 | 0.6 | Aware |
| 11 | Leaf | Prediction | 0.4956 | 840 | 0.5 | 0.5 | Aware |
| 12 | Leaf | Prediction | 0.4329 | 47 | 0.7 | 0.3 | Not Aware |