How to Use the Racing Terminal
Tekbred runs two independent scoring systems on every race. Understanding the difference — and when to use each — is the core skill.
System Overview
Tekbred is a data-driven recommendation system. It does not tell you who will win — it identifies which horses have a statistically higher probability of finishing in the top positions, based on machine learning models trained on historical US race data.
Three base models analyze each horse independently: QUANT, VECTOR, and ALPHA. Their outputs are combined into two final scores — GRID and META — which you toggle between in the terminal.
META vs GRID — The Toggle
Every race card shows a META / GRID toggle at the top of the terminal. This is the most important control in the system.
A track-optimized weighted average of the three base models. Each track has its own weights determined by which model has historically performed best there.
Example: at Santa Anita, QUANT gets weight 0.58 because it outperforms the others there historically.
- Transparent — weights are visible
- More reliable on tracks with large sample sizes
- Best for identifying a single top selection
A second-layer machine learning model (meta-learner) trained on the outputs of QUANT, VECTOR, and ALPHA. Instead of fixed weights, it learns contextually — adapting to race conditions.
The terminal shows — META LEARNER — instead of weights because they vary per prediction.
- Higher top-2/top-3 coverage on most tracks
- Best for ranking multiple horses in a field
- Default recommended mode
Important: The Hit Rate (HR) displayed on each race card also changes when you toggle. META and GRID have different accuracy profiles per track — HR always reflects the active mode.
Interactive Demo
Same race, two modes. Toggle score mode and TOP depth — notice how rankings, HR, and model highlights all update together.
| # | Horse | QUANT | VECTOR | ALPHA |
|---|---|---|---|---|
6 | Munnings Express 2.56 | 3.65 | 4.29 | 3.12 |
2 | Paula's A Star 2.99 | 4.21 | 4.25 | 4.02 |
5 | Geez Eloise 3.45 | 4.67 | 3.56 | 3.71 |
3 | Intentious 4.41 | 4.91 | 3.88 | 3.60 |
What to notice
Switching modes can change the ranking order. When META and GRID agree on the top-ranked horse — that is the strongest signal the system produces.
HR + TOP depth
Try switching TOP from 3 → 1. HR drops because the bar is stricter — the winner must be the exact top-ranked horse, not just in the top 3.
The Three Base Models
These three models run independently on every horse entry. Their scores are the raw inputs to both GRID and META.
Specializes in speed and class patterns — raw speed figures, historical finishing times, and class level transitions.
Most influential at tracks where pace and class are the deciding factor.
Specializes in conditions analysis — surface, distance, and how each horse’s profile aligns with today’s specific race conditions.
Strongest when surface or distance is a key differentiator in the field.
Specializes in recent form and trainer intent — last race cycles, workout patterns, and stable signals that indicate a horse is being pointed for a top finish.
Often the first to flag an improving horse before the public recognizes it.
Reading the Score
The SCORE column is the final output — META or GRID depending on your toggle. It is a relative ranking signal within each race: lower is better. The score has no absolute meaning on its own — what matters is the horse's position relative to the rest of the field.
Highest model preference
The horse with the lowest score in the field is the model's top-ranked horse — regardless of the actual number. A score of 3.1 can be the top-ranked horse if everyone else is higher.
Indicates separation
A large gap between 1st and 2nd place (e.g. 2.1 vs 3.8) means strong model separation. Tight clustering (3.1, 3.2, 3.3) means the field is undifferentiated.
Visual relative ranking
The bar width is relative within the race — the top-ranked horse fills the bar fully. Use it to spot dominant selections at a glance without reading every number.
Hit Rate (HR)
HR is displayed on every race card. It shows how often the active scoring mode has correctly identified a top finisher at the selected track, across the validation window.
The TOP 1 / 2 / 3 buttons on each race card control which depth HR refers to. Button 3 (top-3 coverage) is the default and most useful for field analysis.
HR changes with the mode toggle
META and GRID have different hit rates per track. When you switch modes, HR updates immediately to reflect the selected model’s track record — always check HR after switching.
Sample track HR ranges (META, top-3)
Analysis Guide
Use META when:
- Ranking multiple horses across a full field
- META HR is higher at your track
- Default — start here
Use GRID when:
- Identifying the single strongest selection in a race
- GRID HR is higher at your track
- You want full model weight transparency