data/artifacts/models/mastery_model/metrics.json

{
  "model_name": "mastery_model",
  "model_version": "mastery_model_v2_baseline_001",
  "dataset_version": "2.0.0",
  "trained_at": "2026-05-21T05:59:11.764140+00:00",
  "seed": 42,
  "split_counts": {
    "train": 24515,
    "validation": 5218,
    "test": 5187
  },
  "metrics": {
    "validation": {
      "macro_f1": 0.8649,
      "weighted_f1": 0.8952,
      "per_class": {
        "weak": {
          "precision": 0.9661,
          "recall": 0.9626,
          "f1": 0.9643,
          "support": 2247
        },
        "developing": {
          "precision": 0.8884,
          "recall": 0.905,
          "f1": 0.8966,
          "support": 1337
        },
        "proficient": {
          "precision": 0.7831,
          "recall": 0.7385,
          "f1": 0.7601,
          "support": 826
        },
        "mastered": {
          "precision": 0.8234,
          "recall": 0.854,
          "f1": 0.8384,
          "support": 808
        }
      },
      "confusion_matrix": [
        [
          2163,
          84,
          0,
          0
        ],
        [
          76,
          1210,
          51,
          0
        ],
        [
          0,
          68,
          610,
          148
        ],
        [
          0,
          0,
          118,
          690
        ]
      ]
    },
    "test": {
      "macro_f1": 0.8754,
      "weighted_f1": 0.9029,
      "per_class": {
        "weak": {
          "precision": 0.9667,
          "recall": 0.9717,
          "f1": 0.9692,
          "support": 2120
        },
        "developing": {
          "precision": 0.9155,
          "recall": 0.9089,
          "f1": 0.9122,
          "support": 1394
        },
        "proficient": {
          "precision": 0.7814,
          "recall": 0.7555,
          "f1": 0.7683,
          "support": 814
        },
        "mastered": {
          "precision": 0.8395,
          "recall": 0.865,
          "f1": 0.8521,
          "support": 859
        }
      },
      "confusion_matrix": [
        [
          2060,
          60,
          0,
          0
        ],
        [
          71,
          1267,
          56,
          0
        ],
        [
          0,
          57,
          615,
          142
        ],
        [
          0,
          0,
          116,
          743
        ]
      ]
    }
  },
  "limitations": [
    "Trained on synthetic data only.",
    "4-class mastery labels derived from synthetic mastery_score thresholds.",
    "All features are numeric; no text or contextual features used.",
    "Class distribution may not reflect real-world mastery patterns."
  ]
}