Datasets
SEC 8-K filings, daily and minute-level prices, sector benchmarks and publicly disclosed Form 4 transactions.
Raw source filesTechnical architecture
From an official company release through AI extraction to a predictive model and an independent final test. Collection, language interpretation and evaluation remain separate; each step retains auditable intermediate files.
SEC 8-K filings, daily and minute-level prices, sector benchmarks and publicly disclosed Form 4 transactions.
Raw source filesDownloading, cleaning, aligning timestamps, selecting events and building reproducible tables.
Chronological eventsLocal semantic extraction of financial developments, guidance, risks, capital allocation and evidence excerpts.
Structured featuresBaselines, Ridge regression, text vectors and boosting are compared using the same chronological splits.
Frozen predictionsDirectional accuracy, correlation, uncertainty intervals, transaction costs and independent replication.
Audited final testResults, limitations, example records, documentation and live progress are published without selectively filtering the findings.
Website + downloadsTwo roles for AI
AI assistants help develop the website, prototypes and research software. Generated code is tested; software development is not evidence of a financial relationship.
Qwen3-4B LLM extracts features and evidence excerpts from selected financial passages. A separate model then examines their relationship with subsequent price reactions. Statistical analyses and simple baselines remain part of the comparison.
Read how Feronix is developedSeparation of responsibilities
Raw documents and prices are retained before features or predictions are created.
Qwen3-4B LLM receives financial text, but no future price reactions are included in its prompt.
Model settings and benchmarks are fixed before the final test set is evaluated.
A null result, an uncertain interval or a failed replication remains part of the published record.
Technology stack