LLM, ML & Statistics

FIN uses three different types of intelligence working together: a Large Language Model (LLM) to reason and explain, Machine Learning (ML) to spot patterns and produce precise prices, and statistics to keep everything grounded in numbers.

Large Language Model (LLM)

The LLM is the "brain" that produces the thesis — the qualitative reasoning behind every prediction. Every time FIN runs, it feeds a rich set of data to the LLM so it can understand the full picture:

Stock prices — open, high, low, close, and volume with technical indicators
News articles — scored for sentiment (positive/negative) toward the company and the economy
Surprise signals — unexpected events like earnings beats or economic shocks
Psychology scores — 12 cognitive bias measurements (FOMO, herding, loss aversion, etc.)
Competitor data — peer price performance, valuation metrics, and competitor news sentiment
Financial statements — income, balance sheet, and cash flow data
Calendar events — earnings dates, dividend dates, and other market-moving events
Market context — beta, correlation, and relative strength vs SPY and sector ETFs
Options data — put/call ratios and implied volatility

All of this is packed into a single prompt and sent to the LLM. The model weighs every signal, considers how they interact, and produces:

A qualitative thesis — direction, conviction, regime assessment, bull/bear scenarios, and falsifiable hypotheses
Falsifiable hypotheses — testable predictions registered as thesis monitors (checked daily against live data)

What Makes the LLM Approach Unique

Unlike a black-box algorithm, the LLM explains its reasoning. You can read the full thesis text to understand exactly why the system thinks the stock will move in a certain direction — which news articles influenced it, which psychology biases were most relevant, and how the technical signals factored in.

Machine Learning (ML)

While the LLM handles reasoning, ML produces the numeric price predictions by learning from past results.

Quantile Models

The system trains quantile GBM models — five models per ticker and horizon that predict different points on the return distribution:

Model	Purpose
q10	Lower bound of the confidence band
q25	Conservative estimate
q50	Central (most likely) prediction
q75	Optimistic estimate
q90	Upper bound of the confidence band

The q10–q90 gap forms the confidence band. These bands are optionally calibrated by conformal prediction to guarantee ~80% coverage.

How ML Learns

Every prediction run saves a feature snapshot — a complete record of everything that went into that prediction:

Technical indicators, sentiment scores, psychology biases
Financial fundamentals, market context, options data
Thesis features (conviction, regime probabilities, etc.)

When the target date passes, the accuracy tracker resolves the snapshot with the actual outcome. Once enough resolved snapshots accumulate (100+), the system trains new models.

Tiered Architecture

At prediction time, the system picks the best available model:

Tier 1 — Your personal quantile model (best accuracy, needs ~100 snapshots)
Tier 2 — Pooled model from all users (good fallback)
Tier 3 — Sector-transfer model (from a similar company)
Tier 4 — Thesis heuristic (always available, no training needed)

Each tier is performance-gated: if its recent accuracy or coverage drops below a threshold, it's automatically downgraded. You never see a bad model's output.

Self-Correction

If a model gets stale as market conditions change, it's retired automatically. The system falls back to Tier 4 (thesis heuristic) until fresh models can be trained.

Cold Start

New tickers don't wait weeks. The system backfills historical feature snapshots from existing price data, enabling Tier 1 training on the first retrain cycle.

Statistics

Statistics are the foundation that keeps the LLM and ML honest. They measure, validate, and quantify everything the system does.

Prediction Accuracy

Every prediction is measured against what actually happened:

Metric	What It Tells You
Error %	How far off was the prediction? (absolute percentage difference)
Band Hit	Did the actual price fall within the confidence range? (Yes/No)
MAPE	Mean Absolute Percentage Error — the average error across recent predictions

Gating

If the system's recent MAPE exceeds a configurable threshold, predictions are automatically withheld (gated) until accuracy recovers. This prevents unreliable predictions from reaching the dashboard.

Sentiment Thresholds

News sentiment scores use statistical boundaries:

Below 45 — negative sentiment
45–55 — neutral
Above 55 — positive sentiment

Technical Indicators

Statistics power the technical analysis:

RSI (Relative Strength Index) — a 0–100 score. Above 70 suggests overbought, below 30 suggests oversold
Trend detection — ADF test determines if the price is trending or mean-reverting
Volume analysis — whether trading volume is increasing or decreasing relative to historical norms

Psychology Scoring

Each of the 12 cognitive biases is scored on a 0–100 scale using statistical analysis of article text:

Low (0–30) — barely detectable
Medium (30–60) — some influence present
High (60–100) — strongly influencing the market

How They Work Together

   Collected Data
         ↓
 ┌───────────────┐
 │  Statistics   │──→ Measure, validate, set thresholds
 └───────────────┘
         ↓
 ┌───────────────┐
 │      LLM      │──→ Reason, produce thesis, explain
 └───────────────┘
         ↓
 ┌───────────────┐
 │  ML (Tier 1-4)│──→ Quantile price from thesis + features
 └───────────────┘
         ↓
  Price + band + reasoning
         ↓
 (Feedback: actual outcome resolves snapshots → retrain ML)

Statistics measure the raw data and validate the outputs. The LLM uses that data to reason about what will happen and produce a qualitative thesis. ML uses the thesis features plus all historical data to produce precise quantile price predictions. The actual outcome feeds back to resolve feature snapshots, which train the next generation of ML models.