target_config.yaml

include:
  # === DISTRICT — age demographics ===
  - variable: person_count
    geo_level: district
    domain_variable: age

  # === DISTRICT — count targets ===
  - variable: person_count
    geo_level: district
    domain_variable: adjusted_gross_income
  - variable: household_count
    geo_level: district

  # === DISTRICT — dollar targets ===
  - variable: adjusted_gross_income
    geo_level: district
  - variable: real_estate_taxes
    geo_level: district
  - variable: total_self_employment_income
    geo_level: district
  - variable: taxable_pension_income
    geo_level: district
  - variable: eitc
    geo_level: district
  - variable: refundable_ctc
    geo_level: district
  - variable: non_refundable_ctc
    geo_level: district
  - variable: unemployment_compensation
    geo_level: district

  # === DISTRICT — ACA PTC (2% mean error, restored) ===
  - variable: aca_ptc
    geo_level: district
  - variable: tax_unit_count
    geo_level: district
    domain_variable: aca_ptc

  # === STATE ===
  - variable: person_count
    geo_level: state
    domain_variable: medicaid_enrolled
  # Restore old loss.py's national Medicaid enrollment count target.
  - variable: person_count
    geo_level: national
    domain_variable: medicaid_enrolled
  # REMOVED: is_pregnant — 100% unachievable across all 51 state geos
  - variable: snap
    geo_level: state
  - variable: household_count
    geo_level: state
    domain_variable: snap
  - variable: household_count
    geo_level: state
    domain_variable: housing_assistance
  - variable: tanf
    geo_level: state
  - variable: adjusted_gross_income
    geo_level: state
  # BEA regional wage totals. New macro targets like this must be wired into
  # both legacy utils/loss.py and the target DB ETL, or one publication path
  # will silently miss the constraint.
  - variable: employment_income_before_lsr
    geo_level: state
  - variable: rent
    geo_level: state
  - variable: spm_unit_count
    geo_level: state
    domain_variable: tanf
  - variable: eitc
    geo_level: state
  - variable: tax_unit_count
    geo_level: state
    domain_variable: eitc
  - variable: refundable_ctc
    geo_level: state
  - variable: non_refundable_ctc
    geo_level: state

  # === STATE — ACA marketplace APTC and bronze-plan enrollment counts ===
  - variable: tax_unit_count
    geo_level: state
    domain_variable: used_aca_ptc
  - variable: tax_unit_count
    geo_level: state
    domain_variable: selected_marketplace_plan_benchmark_ratio,used_aca_ptc

  # === STATE — fine AGI bracket targets (stubs 9/10 from in55cmcsv) ===
  - variable: person_count
    geo_level: state
    domain_variable: adjusted_gross_income
  - variable: adjusted_gross_income
    geo_level: state
    domain_variable: adjusted_gross_income
  # REMOVED: state_income_tax — ETL hardcodes $0 for WA and NH, but
  # PolicyEngine correctly computes non-zero tax (WA capital gains tax,
  # NH interest/dividends tax). The $0 targets produce catastrophic loss
  # that crushes WA/NH weights to zero. Fix the ETL before re-enabling.
  # - variable: state_income_tax
  #   geo_level: state
  # IRS SOI income tax (filer-filtered) at state level — 51 new
  # constraints to pin the AGI↔tax relationship state by state.
  - variable: income_tax
    geo_level: state

  # === NATIONAL — fine AGI bracket targets (Table 1.4) ===
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income
  - variable: adjusted_gross_income
    geo_level: national
    domain_variable: adjusted_gross_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits
  - variable: adjusted_gross_income
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits
  - variable: adjusted_gross_income
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,irs_employment_income
  - variable: irs_employment_income
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,irs_employment_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,irs_employment_income
  - variable: irs_employment_income
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,irs_employment_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,pension_income
  - variable: pension_income
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,pension_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,pension_income
  - variable: pension_income
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,pension_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,social_security
  - variable: social_security
    geo_level: national
    domain_variable: adjusted_gross_income,income_tax_before_credits,social_security
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,social_security
  - variable: social_security
    geo_level: national
    domain_variable: adjusted_gross_income,filing_status,income_tax_before_credits,social_security

  # === NATIONAL — wealth target (Federal Reserve SCF, no filer filter) ===
  - variable: net_worth
    geo_level: national

  # === NATIONAL — aggregate dollar targets ===
  - variable: adjusted_gross_income
    geo_level: national
  - variable: childcare_expenses
    geo_level: national
  - variable: employment_income_before_lsr
    geo_level: national
  - variable: self_employment_income_before_lsr+sstb_self_employment_income_before_lsr+farm_operations_income+partnership_s_corp_income
    geo_level: national
  # Do not train direct national interest_income/dividend_income totals against
  # BEA personal interest/dividend income. Those NIPA concepts include imputed
  # interest, pension-plan dividends, and trust flows; use SOI/CBO tax-return
  # targets below for tax/CPS interest and dividend variables.
  - variable: long_term_capital_gains
    geo_level: national
  - variable: medicaid
    geo_level: national
  - variable: person_count
    geo_level: national
    domain_variable: medicare_enrolled
  - variable: medicare_part_b_premium
    geo_level: national
  - variable: medicare_part_b_premium
    geo_level: national
    domain_variable: age
  - variable: real_estate_taxes
    geo_level: national
  - variable: rent
    geo_level: national
  - variable: snap
    geo_level: national
  - variable: social_security
    geo_level: national
  - variable: social_security_dependents
    geo_level: national
  - variable: social_security_disability
    geo_level: national
  - variable: social_security_retirement
    geo_level: national
  - variable: social_security_survivors
    geo_level: national
  - variable: ssi
    geo_level: national
  - variable: person_count
    geo_level: national
    domain_variable: ssi
  - variable: person_count
    geo_level: national
    domain_variable: age,ssi
  - variable: tanf
    geo_level: national
  - variable: spm_unit_count
    geo_level: national
    domain_variable: tanf
  - variable: household_count
    geo_level: national
    domain_variable: spm_unit_energy_subsidy_reported
  - variable: household_count
    geo_level: national
    domain_variable: housing_assistance
  - variable: tip_income
    geo_level: national
  - variable: unemployment_compensation
    geo_level: national
  - variable: wic
    geo_level: national

  # === NATIONAL — retirement contribution targets ===
  - variable: traditional_ira_contributions
    geo_level: national
  - variable: traditional_401k_contributions
    geo_level: national
  - variable: roth_401k_contributions
    geo_level: national
  - variable: roth_ira_contributions
    geo_level: national
  - variable: self_employed_pension_contribution_ald
    geo_level: national

  # === NATIONAL — IRS SOI domain-constrained dollar targets (restored: |rel_err| < 15%) ===
  - variable: aca_ptc
    geo_level: national
    domain_variable: aca_ptc
  - variable: eitc
    geo_level: national
    domain_variable: eitc_child_count
  - variable: eitc
    geo_level: national
    domain_variable: adjusted_gross_income,eitc,eitc_child_count
  - variable: net_capital_gains
    geo_level: national
    domain_variable: net_capital_gains
  # Per-AGI-bracket capital-income targets — without these the optimizer can
  # match the single national aggregate while letting individual records
  # blow up (see issues #555, #866).
  - variable: net_capital_gains
    geo_level: national
    domain_variable: adjusted_gross_income,net_capital_gains
  - variable: tax_unit_count
    geo_level: national
    domain_variable: net_capital_gains
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,net_capital_gains
  - variable: long_term_capital_gains
    geo_level: national
    domain_variable: adjusted_gross_income,long_term_capital_gains
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,long_term_capital_gains
  # Re-include dividend / interest aggregates that were previously dropped
  # for "high error or tension". 30% rel-error on a soft target is still
  # vastly better than the 5-15x inflation we get with no constraint.
  - variable: qualified_dividend_income
    geo_level: national
    domain_variable: qualified_dividend_income
  - variable: qualified_dividend_income
    geo_level: national
    domain_variable: adjusted_gross_income,qualified_dividend_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: qualified_dividend_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,qualified_dividend_income
  - variable: dividend_income
    geo_level: national
    domain_variable: dividend_income
  - variable: dividend_income
    geo_level: national
    domain_variable: adjusted_gross_income,dividend_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: dividend_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,dividend_income
  - variable: taxable_interest_income
    geo_level: national
    domain_variable: taxable_interest_income
  - variable: taxable_interest_income
    geo_level: national
    domain_variable: adjusted_gross_income,taxable_interest_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: taxable_interest_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,taxable_interest_income
  - variable: tax_exempt_interest_income
    geo_level: national
    domain_variable: tax_exempt_interest_income
  - variable: tax_exempt_interest_income
    geo_level: national
    domain_variable: adjusted_gross_income,tax_exempt_interest_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: tax_exempt_interest_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,tax_exempt_interest_income
  - variable: miscellaneous_income
    geo_level: national
    domain_variable: miscellaneous_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: miscellaneous_income
  - variable: refundable_ctc
    geo_level: national
    domain_variable: refundable_ctc
  - variable: refundable_ctc
    geo_level: national
    domain_variable: adjusted_gross_income,refundable_ctc
  - variable: non_refundable_ctc
    geo_level: national
    domain_variable: non_refundable_ctc
  - variable: non_refundable_ctc
    geo_level: national
    domain_variable: adjusted_gross_income,non_refundable_ctc
  - variable: total_self_employment_income
    geo_level: national
    domain_variable: total_self_employment_income
  - variable: tax_unit_partnership_s_corp_income
    geo_level: national
    domain_variable: tax_unit_partnership_s_corp_income
  - variable: taxable_pension_income
    geo_level: national
    domain_variable: taxable_pension_income
  - variable: unemployment_compensation
    geo_level: national
    domain_variable: unemployment_compensation
  - variable: refundable_american_opportunity_credit
    geo_level: national
    domain_variable: refundable_american_opportunity_credit
  - variable: education_tax_credits
    geo_level: national
    domain_variable: education_tax_credits

  # === NATIONAL — IRS SOI filer count targets (restored: |rel_err| < 10%) ===
  - variable: tax_unit_count
    geo_level: national
    domain_variable: aca_ptc
  - variable: tax_unit_count
    geo_level: national
    domain_variable: eitc_child_count
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,eitc,eitc_child_count
  # Restore old loss.py's ACA enrollment count target.
  - variable: person_count
    geo_level: national
    domain_variable: aca_ptc
  - variable: tax_unit_count
    geo_level: national
    domain_variable: refundable_ctc
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,refundable_ctc
  - variable: tax_unit_count
    geo_level: national
    domain_variable: non_refundable_ctc
  - variable: tax_unit_count
    geo_level: national
    domain_variable: adjusted_gross_income,non_refundable_ctc
  # Restore old loss.py's self-employment return-count target.
  - variable: tax_unit_count
    geo_level: national
    domain_variable: total_self_employment_income
  - variable: tax_unit_count
    geo_level: national
    domain_variable: refundable_american_opportunity_credit
  - variable: tax_unit_count
    geo_level: national
    domain_variable: education_tax_credits
  - variable: tax_unit_count
    geo_level: national
    domain_variable: real_estate_taxes,tax_unit_itemizes
  - variable: tax_unit_count
    geo_level: state
    domain_variable: real_estate_taxes,tax_unit_itemizes

  # === NATIONAL — identity / population count targets from old loss.py ===
  - variable: person_count
    geo_level: national
    domain_variable: ssn_card_type
  - variable: person_count
    geo_level: national
    domain_variable: wic

  # === NATIONAL — SOI deduction totals (non-reform) ===
  - variable: charitable_deduction
    geo_level: national
    domain_variable: charitable_deduction
  - variable: tax_unit_count
    geo_level: national
    domain_variable: charitable_deduction
  - variable: medical_expense_deduction
    geo_level: national
    domain_variable: medical_expense_deduction,tax_unit_itemizes
  - variable: qualified_business_income_deduction
    geo_level: national
    domain_variable: qualified_business_income_deduction
  - variable: tax_unit_count
    geo_level: national
    domain_variable: qualified_business_income_deduction

  # === NATIONAL — JCT tax expenditure targets (reform_id=1..5) ===
  - variable: salt_deduction
    geo_level: national
  - variable: charitable_deduction
    geo_level: national
  # REMOVED: deductible_mortgage_interest — target is unachievable
  # (zero row-sum in the sparse matrix) so it contributed 1 full unit
  # of loss for no benefit. Restore only after fixing the matrix
  # builder so mortgage-interest clones can contribute to this row.
  - variable: medical_expense_deduction
    geo_level: national
  - variable: qualified_business_income_deduction
    geo_level: national

  # === NATIONAL — CBO income tax target (re-enabled: 22% error < 54% unconstrained) ===
  - variable: income_tax_positive
    geo_level: national
  # IRS SOI income tax scalar at national — complements income_tax_positive
  # and pairs with the state-level income_tax rule above.
  - variable: income_tax
    geo_level: national

  # NOT INCLUDED — high error or tension (from prior validation)
  # =====================================================================
  # rental_income (20%), income_tax_before_credits (21%),
  # salt SOI (102%),
  # taxable_ira_distributions (68%), taxable_social_security (55%),
  # person_count by AGI bins (100%)
  #
  # Re-included above (despite higher error) because excluding them lets
  # aggregates run wild — see issues #555 and #866:
  #   dividend_income (was 26% rel-err)
  #   qualified_dividend_income (was 29%)
  #   taxable_interest_income (was 61%)
  #   tax_exempt_interest_income (was 61%)