trading pnl reconciliation

The problem

Manual reconciliation of trading activity is error-prone and slow. Discrepancies between execution logs and broker snapshots often lead to inaccurate P&L reporting and hidden accounting errors.

What it does

• Reconstructs signed positions and cash balances from raw fill data and manual adjustments.
• Identifies missing or duplicate fills by comparing reconstructed state against closing snapshots.
• Distinguishes between settlement cash and trade-date cash to ensure timing accuracy.
• Processes deposits, withdrawals, and dividends while preventing double-counted fees.
• Generates a structured ledger and a dedicated discrepancy table for audit trails.

Frameworks & tools

Python 3 for analysis scripts, JSON for data contracts, and standardized ledger modeling for spot and linear instruments.

Why this beats prompting it yourself

General-purpose LLMs struggle with the strict mathematical consistency required for position reconstruction. This skill enforces a specific accounting workflow that separates trade-date logic from settlement events, ensuring you don't miss small but compounding fee errors or timing mismatches.

Use cases

• Verifying daily trading activity against prime brokerage or exchange statements.
• Auditing strategy performance by isolating execution fills from external cash movements.
• Pre-processing raw trade data for tax-lot accounting or performance reporting systems.
• Investigating broken trade sequences and unexplained cash variances.

Known limitations

Does not handle tax reporting, FX conversions, or corporate actions like splits. Limited to spot and fully paid linear instruments; no native derivative margin accounting.