Identifying Information Types in the Estimation of Informed Trading: An Improved Algorithm
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The growing frequency of news arrivals, partly fueled by the proliferation of data sources, has made the assumptions of the classical probability of informed trading (PIN) model outdated. In particular, the model’s assumption of a single type of information event no longer reflects the complexity of modern financial markets, making the accurate detection of information types (layers) crucial for estimating the probability of informed trading. We propose a layer detection algorithm to accurately find the number of distinct information types within a dataset. It identifies the number of information layers by clustering order imbalances and examining their homogeneity using properly constructed confidence intervals for the Skellam distribution. We show that our algorithm manages to find the number of information layers with very high accuracy both when uninformed buyer and seller intensities are equal and when they differ from each other (i.e., between 86% and 95% accuracy rates). We work with more than 500,000 simulations of quarterly datasets with various characteristics and make a large set of robustness checks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it