by Brian Ezinwoke, Oliver Rhodes
Continue on SelfMadeQuant
Suggested foundations for financial machine learning and market microstructure and execution. Specialist prerequisites vary by paper.
Preserve time order and avoid future information in training.
Establish an interpretable baseline before a flexible model.
Read bid, ask, depth and queue-based market state.
Understand why fills and order flow can carry information.
Account for dependence and overlapping observations.
Examine which information contributes to predictions.
Connect trading speed and size to execution cost.
Choose a reproducible strategy, specify the trading rule, and test what remains after costs and estimation uncertainty.
Learn the trading state and execution trade-off before evaluating reinforcement-learning market makers.