Latest Thinking
All postsPart 1 —Time-Series Foundations: Transformers, Diffusion, and Why They're Different
Before we build anything, we need a clear mental model of what these architectures actually do — not the marketing version, the mechanistic one.
Part 2 —Data Pipeline: NASDAQ-100, Options Chain, and Sentiment
How to align three different data sources into one consistent daily dataset — and why every alignment decision is also a leakage decision.
Part 3 —Feature Engineering: From OHLCV to a Rich Feature Matrix
What each feature actually measures, why it might matter for predicting NASDAQ-100 returns, and how to compute it without accidentally injecting future information.
Part 4 —The Standard Transformer: Architecture, Training, and Why It Collapsed
We built it. We ran it. It predicted the same thing for every stock. Here's exactly what happened and what it reveals about applying transformers to financial data.
Part 5 —Temporal Fusion Transformer: Gating, Memory, and Sector Learnability
The architecture that finally worked — and a precise explanation of why each component addresses a specific failure mode of the Standard Transformer on financial data.
Part 6 —Validation Discipline: Catching Leakage, Rank IC, and the Economic Viability Wall
The step most AI trading projects skip — and the reason most of them fail when they reach real capital. A rigorous validation framework for quantitative ML.
Part 7 —LightGBM as Signal Engine: Feature Sets, Clean Candidates, and OOS Testing
The model that finally survived adversarial validation — and why gradient boosting often beats deep learning on structured financial data.
Part 8 —System Architecture: Signal → Strategy → Execution
A statistically real signal is not yet a tradeable system. This is the architecture that converts +0.08 Rank IC into a deployable paper-trading framework — and why the layers between prediction and profit are harder than the model itself.