Newest first
Design a fair comparison of momentum, logistic regression, trees, and forests. Control model selection and distinguish classification from economic performance.
Design features, labels, time splits, and monthly retraining for a logistic-regression baseline, keeping predictive accuracy separate from investment returns.
Use hypothetical examples to examine loss paths and trading costs alongside returns, and interpret volatility, drawdown, Sharpe ratios, and turnover together.
Plan hypotheses, baselines, chronological splits, walk-forward validation, and protected test periods. Examine selection bias and the role of research records.
Before comparing AI and ML models, fix a simple long/cash momentum baseline that will not change after you see the results. How to build the 12-month signal, monthly rebalancing, equal weighting, and trading-cost scenarios as reproducible Python code.
Audit historical data availability through adjusted prices, delistings, filing dates, revisions, and time zones, with an example of delayed closing-price signals.
Compare the inputs and outputs of rules, machine learning, deep learning, and LLMs. Define the task, data, and evaluation criteria before selecting a tool.
Distinguish AI's roles in prediction, research, and automation, and plan separate tests of productivity and investment performance while accounting for key risks.
Follow a proposed path from Java and Spring fundamentals to APIs, databases, testing, security, and operations, measuring progress through practical capabilities.
A practical checklist for safely validating ports, addressing, authentication, and read/write API contracts in Docker Compose.
Forge Fate