cyb006-baseline-classifier / ablation_results.json
pradeep-xpert's picture
Initial release: XGBoost + MLP for user-risk-tier classification, plus structural-leakage diagnostic on threat-actor detection
e6a6835 verified
{
"purpose": "Quantify how much each feature group contributes to the headline XGBoost score. Identical architecture, same stratified split, with one feature group dropped at a time.",
"full_model_metrics": {
"model": "xgboost",
"accuracy": 0.6666666666666666,
"macro_f1": 0.6453546453546454,
"weighted_f1": 0.6634032634032633,
"per_class_f1": {
"low": 0.7272727272727273,
"medium": 0.2857142857142857,
"high": 0.9230769230769231
},
"confusion_matrix": {
"labels": [
"low",
"medium",
"high"
],
"matrix": [
[
12,
5,
0
],
[
4,
2,
1
],
[
0,
0,
6
]
]
},
"macro_roc_auc_ovr": 0.8016919142238835
},
"ablations": {
"no_session_aggregates": {
"n_features": 26,
"dropped_count": 8,
"metrics": {
"model": "xgboost_no_session_aggregates",
"accuracy": 0.7,
"macro_f1": 0.6129870129870131,
"weighted_f1": 0.6671861471861472,
"per_class_f1": {
"low": 0.8,
"medium": 0.18181818181818182,
"high": 0.8571428571428571
},
"confusion_matrix": {
"labels": [
"low",
"medium",
"high"
],
"matrix": [
[
14,
3,
0
],
[
4,
1,
2
],
[
0,
0,
6
]
]
},
"macro_roc_auc_ovr": 0.7625392687732843
},
"delta_accuracy": -0.033333333333333326,
"delta_macro_f1": 0.03236763236763229
},
"no_user_aggregates": {
"n_features": 26,
"dropped_count": 8,
"metrics": {
"model": "xgboost_no_user_aggregates",
"accuracy": 0.5333333333333333,
"macro_f1": 0.45864045864045866,
"weighted_f1": 0.5130221130221131,
"per_class_f1": {
"low": 0.6486486486486487,
"medium": 0.0,
"high": 0.7272727272727273
},
"confusion_matrix": {
"labels": [
"low",
"medium",
"high"
],
"matrix": [
[
12,
4,
1
],
[
7,
0,
0
],
[
1,
1,
4
]
]
},
"macro_roc_auc_ovr": 0.7042183744549474
},
"delta_accuracy": 0.1333333333333333,
"delta_macro_f1": 0.18671418671418671
},
"no_risk_scores": {
"n_features": 28,
"dropped_count": 6,
"metrics": {
"model": "xgboost_no_risk_scores",
"accuracy": 0.5666666666666667,
"macro_f1": 0.5300213675213675,
"weighted_f1": 0.5745405982905983,
"per_class_f1": {
"low": 0.6875,
"medium": 0.13333333333333333,
"high": 0.7692307692307693
},
"confusion_matrix": {
"labels": [
"low",
"medium",
"high"
],
"matrix": [
[
11,
6,
0
],
[
4,
1,
2
],
[
0,
1,
5
]
]
},
"macro_roc_auc_ovr": 0.7397649416511309
},
"delta_accuracy": 0.09999999999999998,
"delta_macro_f1": 0.11533327783327785
},
"no_engineered": {
"n_features": 28,
"dropped_count": 6,
"metrics": {
"model": "xgboost_no_engineered",
"accuracy": 0.5666666666666667,
"macro_f1": 0.5444444444444444,
"weighted_f1": 0.5755555555555555,
"per_class_f1": {
"low": 0.6666666666666666,
"medium": 0.13333333333333333,
"high": 0.8333333333333334
},
"confusion_matrix": {
"labels": [
"low",
"medium",
"high"
],
"matrix": [
[
11,
6,
0
],
[
5,
1,
1
],
[
0,
1,
5
]
]
},
"macro_roc_auc_ovr": 0.7972402822147068
},
"delta_accuracy": 0.09999999999999998,
"delta_macro_f1": 0.10091020091020098
}
}
}