anomaly-atlas
Honesty doctrine. Every candidate anomaly is an artifact until proven otherwise; in-sample results are never findings; past statistical regularity does not imply future returns. This is research on statistical properties of market data — not investment advice, not a trading system.

Code / src/anomaly_atlas/validation/costs.py

src/anomaly_atlas/validation/costs.py 17 lines
# =============================================================================
#  Project   : anomaly-atlas
#  File      : src/anomaly_atlas/validation/costs.py
#  Purpose   : Transaction-cost models: spread, impact, commissions
#  Author    : Simon-Pierre Boucher
#  Contact   : contact@spboucher.ai
#  Data src  : hfmarketdata.io (sole data source)
#  Created   : 2026-08-12
#  Modified  : 2026-08-12
#  Platform  : macOS / Apple Silicon (arm64)
#  License   : All rights reserved (research code)
# =============================================================================
"""Transaction-cost models: spread, impact, commissions.

Stub scaffolded 2026-08-12; implemented in later phases (see CLAUDE.md).
"""