feat: add SLC student loan calibration targets

Adds Plan 2 and Plan 5 England borrower counts (earning above threshold,
2025-2030) from SLC Table 6a as calibration targets, wired into the
target registry and loss matrix.

Author: nikhilwoodruff

changelog_entry.yaml

@@ -1,4 +1,4 @@
-- bump: patch
+- bump: minor
   changes:
     added:
-    - Test for highest_education in enhanced FRS dataset.
+      - SLC student loan calibration targets for Plan 2 and Plan 5 England borrowers earning above repayment threshold (2025-2030), wired into the target registry and loss matrix.

policyengine_uk_data/targets/build_loss_matrix.py

@@ -37,6 +37,7 @@
     compute_scotland_demographics,
     compute_scotland_uc_child,
     compute_scottish_child_payment,
+    compute_student_loan_plan,
     compute_ss_contributions,
     compute_ss_headcount,
     compute_ss_it_relief,
@@ -302,6 +303,10 @@ def _compute_column(
     if name == "sss/scottish_child_payment":
         return compute_scottish_child_payment(target, ctx)
 
+    # Student loan plan borrower counts (SLC)
+    if name.startswith("slc/plan_"):
+        return compute_student_loan_plan(target, ctx)
+
     # PIP claimants
     if name in (
         "dwp/pip_dl_standard_claimants",

policyengine_uk_data/targets/compute/__init__.py

@@ -37,6 +37,7 @@
     compute_housing,
     compute_savings_interest,
     compute_scottish_child_payment,
+    compute_student_loan_plan,
     compute_vehicles,
 )
 
@@ -55,6 +56,7 @@
     "compute_scotland_demographics",
     "compute_scotland_uc_child",
     "compute_scottish_child_payment",
+    "compute_student_loan_plan",
     "compute_ss_contributions",
     "compute_ss_headcount",
     "compute_ss_it_relief",

policyengine_uk_data/targets/compute/other.py

@@ -1,7 +1,20 @@
-"""Miscellaneous compute functions (vehicles, housing, savings, SCP)."""
+"""Miscellaneous compute functions (vehicles, housing, savings, SCP,
+student loans)."""
 
 import numpy as np
 
+_ENGLAND_REGIONS = {
+    "NORTH_EAST",
+    "NORTH_WEST",
+    "YORKSHIRE",
+    "EAST_MIDLANDS",
+    "WEST_MIDLANDS",
+    "EAST_OF_ENGLAND",
+    "LONDON",
+    "SOUTH_EAST",
+    "SOUTH_WEST",
+}
+
 
 def compute_vehicles(target, ctx) -> np.ndarray:
     """Compute vehicle ownership targets."""
@@ -34,3 +47,25 @@ def compute_scottish_child_payment(target, ctx) -> np.ndarray:
     """Compute Scottish child payment spend."""
     scp = ctx.sim.calculate("scottish_child_payment")
     return ctx.household_from_person(scp)
+
+
+def compute_student_loan_plan(target, ctx) -> np.ndarray:
+    """Count England borrowers on a given plan with repayments > 0.
+
+    SLC targets cover borrowers liable to repay AND earning above threshold
+    in England only — matching exactly what the FRS captures via PAYE.
+    """
+    plan_name = target.name  # e.g. "slc/plan_2_borrowers_above_threshold"
+    if "plan_2" in plan_name:
+        plan_value = "PLAN_2"
+    elif "plan_5" in plan_name:
+        plan_value = "PLAN_5"
+    else:
+        return None
+
+    plan = ctx.sim.calculate("student_loan_plan").values
+    region = ctx.sim.calculate("region", map_to="person").values
+    is_england = np.isin(region, list(_ENGLAND_REGIONS))
+    on_plan = (plan == plan_value) & is_england
+
+    return ctx.household_from_person(on_plan.astype(float))

policyengine_uk_data/targets/sources/slc.py

@@ -0,0 +1,64 @@
+"""Student Loans Company (SLC) calibration targets.
+
+Borrower counts for England only: Plan 2 and Plan 5, restricted to
+borrowers liable to repay and earning above the repayment threshold.
+This matches the FRS coverage (PAYE deductions only).
+
+Source: SLC 'Student loans: borrower liability and repayment' statistical
+release, Table 6a — Forecast number of student borrowers liable to repay
+and number earning above repayment threshold.
+https://www.gov.uk/government/collections/student-loans-in-england-statistics
+"""
+
+from policyengine_uk_data.targets.schema import Target, Unit
+
+
+def get_targets() -> list[Target]:
+    targets = []
+
+    _REFERENCE = (
+        "https://www.gov.uk/government/collections/"
+        "student-loans-in-england-statistics"
+    )
+
+    # Plan 2 — England, earning above threshold
+    # Academic year 20XX-YY maps to calendar year 20XX.
+    targets.append(
+        Target(
+            name="slc/plan_2_borrowers_above_threshold",
+            variable="student_loan_plan",
+            source="slc",
+            unit=Unit.COUNT,
+            is_count=True,
+            values={
+                2025: 3_985_000,
+                2026: 4_460_000,
+                2027: 4_825_000,
+                2028: 5_045_000,
+                2029: 5_160_000,
+                2030: 5_205_000,
+            },
+            reference_url=_REFERENCE,
+        )
+    )
+
+    # Plan 5 — England, earning above threshold
+    targets.append(
+        Target(
+            name="slc/plan_5_borrowers_above_threshold",
+            variable="student_loan_plan",
+            source="slc",
+            unit=Unit.COUNT,
+            is_count=True,
+            values={
+                2026: 35_000,
+                2027: 145_000,
+                2028: 390_000,
+                2029: 770_000,
+                2030: 1_235_000,
+            },
+            reference_url=_REFERENCE,
+        )
+    )
+
+    return targets

policyengine_uk_data/tests/test_student_loan_targets.py

@@ -0,0 +1,34 @@
+"""Tests for SLC student loan calibration targets."""
+
+import pytest
+
+
+def test_slc_targets_registered():
+    """SLC targets appear in the target registry."""
+    from policyengine_uk_data.targets.registry import get_all_targets
+
+    targets = {t.name: t for t in get_all_targets()}
+    assert "slc/plan_2_borrowers_above_threshold" in targets
+    assert "slc/plan_5_borrowers_above_threshold" in targets
+
+
+def test_slc_plan2_values():
+    """Plan 2 target values match SLC Table 6a."""
+    from policyengine_uk_data.targets.registry import get_all_targets
+
+    targets = {t.name: t for t in get_all_targets()}
+    p2 = targets["slc/plan_2_borrowers_above_threshold"]
+    assert p2.values[2025] == 3_985_000
+    assert p2.values[2026] == 4_460_000
+    assert p2.values[2029] == 5_160_000
+
+
+def test_slc_plan5_values():
+    """Plan 5 target values match SLC Table 6a."""
+    from policyengine_uk_data.targets.registry import get_all_targets
+
+    targets = {t.name: t for t in get_all_targets()}
+    p5 = targets["slc/plan_5_borrowers_above_threshold"]
+    assert 2025 not in p5.values  # no Plan 5 borrowers yet in 2024-25
+    assert p5.values[2026] == 35_000
+    assert p5.values[2029] == 770_000