Forge FateEvaluating AI in quant research: roles, risks, and validation methods
Introduces AI roles in prediction, research, and automation and how to evaluate them, with a path to a separate executed baseline experiment.
Quant Investing and AI: Concepts and Validation Methods
Twelve parts on AI roles, data timing, validation, costs, and model-comparison methods. Part 6 provides code and an executed 2007–2025 historical-price comparison of two SPY/IEF/GLD baselines. Other design and synthetic examples do not establish AI performance.
- 1.
Quant & Data Research - 2.
Quant & Data Research Rules, Machine Learning, Deep Learning, and LLMs: Four Ways to Answer the Same Investment Question
Compare the inputs and outputs of rules, machine learning, deep learning, and LLMs. Define the task, data, and evaluation criteria before selecting a tool.
- 3.
Quant & Data Research Could You Have Known That Data at the Time? Data Traps to Check Before Running AI Investing Experiments
Audit historical data availability through adjusted prices, delistings, filing dates, revisions, and time zones, with an example of delayed closing-price signals.
- 4.
Quant & Data Research What Makes a Good Backtest Different? Designing the Validation Process Before Looking at Returns
Plan hypotheses, baselines, chronological splits, walk-forward validation, and protected test periods. Examine selection bias and the role of research records.
- 5.
Quant & Data Research What to Look at Before Returns: The Path of Losses and Trading Costs
Use hypothetical examples to examine loss paths and trading costs alongside returns, and interpret volatility, drawdown, Sharpe ratios, and turnover together.
- 6.
Quant & Data Research Running 12-month momentum on SPY, IEF, and GLD: a 2007–2025 baseline comparison
An executed 2007–2025 adjusted-price comparison of buy and hold and 12-month momentum, with four cost scenarios, complete code, equity paths, and trade ledgers.
- 7.
Quant & Data Research Designing a logistic-regression baseline: features, labels, and time splits
Designs features, labels, chronological splits, and retraining rules before evaluation; an educational design, not a report of measured model performance.
- 8.
Quant & Data Research Designing a fair comparison of logistic regression and tree models
Sets out fixed data, time splits, cost assumptions, and evaluation conditions; does not establish empirical model superiority.
- 9.
Quant & Data Research The Risk of Mistaking Chance Results for Skill in Financial Machine Learning—and How to Challenge Them
Examine noise, changing markets, repeated searches, leakage, costs, and selection bias, and define ways to challenge promising financial ML results.
- 10.
Quant & Data Research Verify the Research, Not the Price: Where LLMs Belong in Quant Research
Distinguish document transformation, validation support, and decision boundaries in LLM-assisted quant research. Check drafts against primary sources and raw data.
- 11.
Quant & Data Research 11. A Safe Way to Do Quant Research with LLMs: From Questions to Validation and Research Records
Organize LLM-assisted quant research around questions, evidence, code checks, timing, and experiment records, with human review and documented failures.
- 12.
Quant & Data Research Quant AI methodology review: available evidence and experiments still needed
Reviews the literature and methods across 12 parts, distinguishing the executed ETF baseline from AI and ML comparisons still outstanding.