kelvi23/

settlement-stress-flagger-v1

Settlement “Stress” Flagging with LightGBM

• Raw inputs: daily “fails‐to‐deliver” count (QUANTITY (FAILS)) and price
• Engineered signals (all lagged or historical, no leakage):
  • 1‑day lags: qty_lag1, price_lag1, fail_value_lag1
  • Rolling stats per‑CUSIP: 7‑day mean/std of quantity, 30‑day mean/std of fail value
  • Momentum: qty_pct_change, price_pct_change
  • Cumulative counts: days since last fail, # of days with any fail, cum qty
  • Event timing: day_of_week, is_month_end, is_quarter_end, is_year_end
  • Text flags: is_foreign, is_adr, is_etf, is_reit
  • Heavy‑tail transforms: log_qty, log_val, extreme spikes

• Algorithm: LightGBM Classifier (handles missing values out‑of‑the‑box, extremely fast)
• Training
  • Split by date: train = all data before 2025‑01‑01, test = after
  • Positive class = fail_value > 90th percentile (train)
  • Early‑stop on AUC & binary_error on the hold‑out
  • Best iteration: ~20 boosting rounds

• Threshold (train 90th pctile of fail_value): 445 122.29
• ROC‑AUC: 1.000
• Precision: 0.99
• Recall: 1.00
• F1‑Score: 1.00

1. Calibrate probability threshold for ops SLAs.
2. Monitor drift in AUC/precision‐recall over time.

Quick start

Citation

Musodza, K. (2025). Bond Settlement Automated Exception Handling and Reconciliation. Zenodo. https://doi.org/10.5281/zenodo.16828730

➡️ Technical white-paper & notebooks: https://github.com/Coreledger-tech/Exception-handling-reconciliation.git