---
license: mit
language:
- en
tags:
- football
- soccer
- la-liga
- sports
- prediction
- machine-learning
- catboost
pipeline_tag: tabular-classification
library_name: catboost
---

# La Liga Score Predictor

## What This Release Is
This is a public football prediction bundle for Spanish La Liga.

It is built for simple pre-match score prediction from structured historical match data.

Public package version:
- `2026.04.1`

Scope:
- supported competition: Spanish La Liga only
- intended usage: pre-match prediction for La Liga fixtures only

It does **not** include:
- non-prediction application code
- other internal model lines
- private ingestion code
- private infrastructure
- app-specific code

## Competition Scope
- This release supports Spanish La Liga matches only.
- It is not packaged or validated for other leagues.

## Who This Is For
- developers evaluating a football prediction model package
- teams integrating pre-match score prediction into their own apps or internal tools
- ML or analytics users who want a documented La Liga inference bundle

This release is strongest as:
- a technical package
- an integration starting point
- a reproducible model bundle for experimentation

It is not positioned as:
- a hosted prediction API
- a live data service
- a no-input prediction engine that already knows every future fixture context

The simplest way to think about it is:
- this is a model-and-inference bundle
- it is not a bundled football data service

## Important Reality Check
This bundle ships:
- the trained champion model
- the feature-building wrapper
- synthetic sample CSVs
- runnable examples

This bundle does **not** ship:
- a full production historical La Liga dataset
- a built-in live data feed
- a guarantee of matching an internal/private prediction environment exactly

That means:
- `predict_match(...)` still needs compatible historical match data
- the included sample CSVs are for demonstration and onboarding
- exact outputs depend on the history data provided to the feature builder
- using different history data can lead to different predictions, even with the same model artifact

For real upcoming-match prediction, users must supply compatible historical match data so the feature builder can compute pre-match context.

## What It Supports
- Predicting `home goals`
- Predicting `away goals`
- Predicting final `scoreline`
- Predicting `home / draw / away` probabilities
- Returning `confidence level`
- Returning `confidence score`
- Returning `confidence margin`
- Returning `abstain / score-range` signals for fragile matches
- Predicting from a full numeric feature row
- Predicting from `home_team`, `away_team`, and `match_date` when a compatible history CSV is available
- Batch prediction from a CSV of fixtures

## How The 48-Signal Model Relates To The CSV
The trained model uses `48` numeric signals at inference time.

Those `48` signals do **not** mean your history CSV must literally contain `48` raw columns.

In the public package, those signals come from a mix of:
- values directly present in the history CSV
- rolling features derived by the wrapper from past match rows
- fallback defaults when richer optional columns are not available

That means:
- the package can still run with a thinner history CSV
- prediction quality is better when the history CSV is richer
- the included sample demonstrates a better recommended shape, not just a minimum runnable shape

## Public API Methods
The public Python package exposes these main methods:

### `predict_match(home_team, away_team, match_date)`
- best for normal application use
- builds features from a compatible history CSV
- returns the full response shape, including advanced fields

Typical fields returned:
- `model_version`
- `expected_home_goals`
- `expected_away_goals`
- `predicted_home_goals`
- `predicted_away_goals`
- `predicted_score`
- `result_probabilities`
- `raw_result_probabilities`
- `confidence_level`
- `confidence_score`
- `confidence_margin`
- `abstain_recommended`
- `predicted_score_range` when triggered
- `decoder_diagnostics`
- `request`

### `predict_match_simple(home_team, away_team, match_date)`
- best for product-facing score cards and lighter UI integrations
- builds features from a compatible history CSV
- returns the smaller public response shape

Typical fields returned:
- `model_version`
- `predicted_home_goals`
- `predicted_away_goals`
- `predicted_score`
- `result_probabilities`
- `confidence_level`
- `confidence_score`
- `confidence_margin`
- `abstain_recommended`
- `predicted_score_range` when triggered
- `request`

### `predict_features(features)`
- best for advanced users who already manage engineered features themselves
- expects the full numeric feature row
- returns the full response shape, including advanced fields

Typical fields returned:
- `model_version`
- `expected_home_goals`
- `expected_away_goals`
- `predicted_home_goals`
- `predicted_away_goals`
- `predicted_score`
- `result_probabilities`
- `raw_result_probabilities`
- `confidence_level`
- `confidence_score`
- `confidence_margin`
- `abstain_recommended`
- `predicted_score_range` when triggered
- `decoder_diagnostics`

### `predict_features_simple(features)`
- best for advanced users who want the raw-feature path with a smaller response
- expects the full numeric feature row
- returns the smaller public response shape

Typical fields returned:
- `model_version`
- `predicted_home_goals`
- `predicted_away_goals`
- `predicted_score`
- `result_probabilities`
- `confidence_level`
- `confidence_score`
- `confidence_margin`
- `abstain_recommended`
- `predicted_score_range` when triggered

## Public Files
```text

  README.md
  LICENSE
  CHANGELOG.md
  RELEASE_GUIDE.md
  MODEL_CARD.md
  EVALUATION_SUMMARY.md
  DATA_FORMAT.md
  FAQ.md
  QUICK_PUBLISH_CHECKLIST.md
  ARTIFACTS_SHA256.txt
  requirements.txt
  pyproject.toml
  sample_history.csv
  sample_fixtures.csv
  predict_one.py
  predict_batch.py
  demo_cli.py
  smoke_test.py
  demo_notebook.ipynb
  la_liga_score_predictor/
    __init__.py
    predictor.py
    feature_builder.py
    artifacts/
      la_liga_score_predictor.json
      home_goals_model.cbm
      away_goals_model.cbm
      outcome_model.cbm
```

## Installation
From inside ``:

```bash
python3 -m venv .venv
source .venv/bin/activate
pip install .
```

If you prefer, the dependency list is also available in `requirements.txt`.

## Run The Included Example
This bundle includes an expanded synthetic `sample_history.csv` so the wrapper can be demonstrated without private data.

The included sample now provides:
- `120` synthetic historical match rows
- `20` Spanish La Liga team names
- `35` CSV columns
- enough match depth for rolling-form features in the demo flow
- richer optional fields such as player aggregates and tactic-stability values

It is still:
- synthetic
- limited
- not a substitute for a production historical dataset

From inside ``:

```bash
PYTHONPATH=. python3 predict_one.py
```

Expected result style:
- request summary
- predicted score
- home/draw/away probabilities
- confidence level
- abstain flag

## Batch Example
From inside ``:

```bash
PYTHONPATH=. python3 predict_batch.py
cat predictions_output.csv
```

## Smoke Test
From inside ``:

```bash
PYTHONPATH=. python3 smoke_test.py
```

This confirms that:
- the package imports
- the bundled model files load
- a sample prediction runs end to end
- the output has the expected public fields

## CLI Demo
From inside ``:

```bash
PYTHONPATH=. python3 demo_cli.py \
  --home-team 'Girona FC' \
  --away-team 'Mallorca' \
  --match-date '2026-05-01' \
  --dataset-csv sample_history.csv \
  --pretty
```

## Notebook Demo
A notebook starter is included for Kaggle or local notebook use:

```text
demo_notebook.ipynb
```

## Easiest Interface
The easiest interface is:

```python
from la_liga_score_predictor import LaLigaScorePredictor

predictor = LaLigaScorePredictor.from_defaults(
    dataset_csv_path="sample_history.csv"
)

result = predictor.predict_match(
    home_team="Athletic",
    away_team="Osasuna",
    match_date="2026-04-21",
)

print(result["predicted_score"])
print(result["result_probabilities"])
print(result["confidence_level"])
```

## What To Expect In Real Use
For a real application, the cleanest usage pattern is:

1. load the predictor
2. point it at your compatible historical match dataset
3. call `predict_match(...)` for upcoming fixtures

Keep expectations clear:
- same model + different history data = potentially different prediction
- sample CSVs are for demos, tests, and onboarding
- production-grade reproducibility requires production-grade historical context

## What Makes A Good History CSV
At a practical level, a strong history CSV should provide:

1. enough historical depth
- not just a few rows
- enough prior matches per team for rolling last-5 and last-10 features

2. stable team naming
- use one consistent naming style
- avoid mixing many variants for the same club

3. final scores for past matches
- these are essential because the wrapper derives rolling form from them

4. richer optional context where possible
- team IDs
- Elo values
- tactic IDs
- coach IDs
- player aggregate columns
- tactic stability columns

5. coverage for the teams you want to predict
- if a team is absent from the history CSV, `predict_match(...)` will fail

In short:
- minimum CSV shape lets the package run
- richer CSV shape lets the model behave more like a serious prediction engine

If you only want the product-facing fields, use:

```python
simple_result = predictor.predict_match_simple(
    home_team="Athletic",
    away_team="Osasuna",
    match_date="2026-04-21",
)
```

## Real Usage With Your Own History CSV
For real usage, replace `sample_history.csv` with your own compatible historical match CSV:

```python
from la_liga_score_predictor import LaLigaScorePredictor

predictor = LaLigaScorePredictor.from_defaults(
    dataset_csv_path="/path/to/your/history.csv"
)

result = predictor.predict_match(
    home_team="Real Madrid",
    away_team="Valencia",
    match_date="2026-05-10",
)
```

The same smaller response shape is available here too:

```python
simple_result = predictor.predict_match_simple(
    home_team="Real Madrid",
    away_team="Valencia",
    match_date="2026-05-10",
)
```

## Raw Feature Interface
If you already have the numeric features, use the lower-level interface:

```python
from la_liga_score_predictor import LaLigaScorePredictor

predictor = LaLigaScorePredictor.from_defaults()

features = {
    "home_avg_goals_last5_all": 1.4,
    "away_avg_goals_last5_all": 1.1,
    "home_avg_goals_last5_home": 1.6,
    "away_avg_goals_last5_away": 1.0,
    "home_avg_conceded_last5_all": 0.9,
    "away_avg_conceded_last5_all": 1.2,
    "home_avg_conceded_last5_home": 0.8,
    "away_avg_conceded_last5_away": 1.3,
    "home_win_rate_last10_all": 0.5,
    "away_win_rate_last10_all": 0.4,
    "home_win_rate_last10_home": 0.6,
    "away_win_rate_last10_away": 0.3,
    "home_draw_rate_last10": 0.2,
    "away_draw_rate_last10": 0.3,
    "home_goal_diff_last5": 2.0,
    "away_goal_diff_last5": -1.0,
    "home_rest_days": 6.0,
    "away_rest_days": 5.0,
    "home_elo_pre": 1715.0,
    "away_elo_pre": 1662.0,
    "elo_diff_pre": 53.0,
    "home_team_id": 12.0,
    "away_team_id": 19.0,
    "home_player_minutes_total_prev5": 4050.0,
    "away_player_minutes_total_prev5": 3970.0,
    "home_player_goals_total_prev5": 6.0,
    "away_player_goals_total_prev5": 4.0,
    "home_player_assists_total_prev5": 4.0,
    "away_player_assists_total_prev5": 3.0,
    "home_player_yellow_cards_total_prev5": 8.0,
    "away_player_yellow_cards_total_prev5": 10.0,
    "home_player_red_cards_total_prev5": 0.0,
    "away_player_red_cards_total_prev5": 0.0,
    "home_player_starters_count_prev5": 55.0,
    "away_player_starters_count_prev5": 55.0,
    "home_player_used_count_prev5": 76.0,
    "away_player_used_count_prev5": 73.0,
    "home_player_injured_count_prev5": 1.0,
    "away_player_injured_count_prev5": 2.0,
    "home_player_suspended_count_prev5": 0.0,
    "away_player_suspended_count_prev5": 1.0,
    "home_tactic_id": 4.0,
    "away_tactic_id": 7.0,
    "home_coach_id": 1012.0,
    "away_coach_id": 1048.0,
    "home_tactic_stability_last5": 0.8,
    "away_tactic_stability_last5": 0.4,
    "tactic_matchup_code": 4007.0,
}

result = predictor.predict_features(features)
print(result["predicted_score"])
```

For a smaller response:

```python
simple_result = predictor.predict_features_simple(features)
print(simple_result)
```

## Dataset Requirement For `predict_match()`
For `predict_match(home_team, away_team, match_date)` to work, the predictor needs a compatible historical match CSV.

Minimum required columns:
- `date`
- `home_team`
- `away_team`
- `home_goals`
- `away_goals`

Better results if your CSV also includes:
- Elo columns
- team ids
- player rolling aggregates
- tactic ids
- coach ids
- tactic stability fields

If advanced columns are missing, the wrapper falls back to dataset-level defaults. That keeps the interface runnable, but prediction quality may be weaker than the full training environment.

## Output Shape
Typical output:

```json
{
  "predicted_score": "1-0",
  "result_probabilities": {
    "home_win": 0.46,
    "draw": 0.31,
    "away_win": 0.23
  },
  "confidence_level": "medium",
  "confidence_score": 0.46,
  "confidence_margin": 0.15,
  "abstain_recommended": false
}
```

## Responsible Use
- This package is designed for pre-match football prediction only.
- It is guidance software, not a guarantee tool.
- It is not validated for live in-play forecasting.
- It is not validated for competitions outside Spanish La Liga.

## Simple vs Advanced Output
For most web or mobile products, the main fields to show are:
- `predicted_score`
- `result_probabilities`
- `confidence_level`
- `abstain_recommended`
- `predicted_score_range` when present

The helper methods for this are:
- `predict_match_simple(...)`
- `predict_features_simple(...)`

Advanced fields are also returned for developers and power users:
- `expected_home_goals`
- `expected_away_goals`
- `confidence_score`
- `confidence_margin`
- `raw_result_probabilities`
- `decoder_diagnostics`

Recommended product approach:
- use the simple fields in the main UI
- keep advanced fields for debug, analytics, or an expandable details view

## Field Glossary
- `predicted_score`
  - the final exact score chosen by the model
- `predicted_home_goals`
  - the home-goal side of the chosen scoreline
- `predicted_away_goals`
  - the away-goal side of the chosen scoreline
- `result_probabilities`
  - the calibrated probabilities for `home_win`, `draw`, and `away_win`
- `raw_result_probabilities`
  - the pre-calibration probabilities before temperature scaling
- `expected_home_goals`
  - the model's expected goals estimate for the home team before final score decoding
- `expected_away_goals`
  - the model's expected goals estimate for the away team before final score decoding
- `confidence_level`
  - a simple label: `high`, `medium`, or `low`
- `confidence_score`
  - the top outcome probability after calibration
- `confidence_margin`
  - the gap between the highest and second-highest outcome probabilities
- `abstain_recommended`
  - `true` when the fixture is fragile enough that an exact-score claim should be treated cautiously
- `predicted_score_range`
  - an optional home/away score band returned when the fixture is fragile
- `decoder_diagnostics`
  - advanced explanation fields for developers
- `top_outcome`
  - the outcome direction with the highest calibrated probability
- `top_outcome_probability`
  - the probability of that top outcome
- `second_outcome_probability`
  - the probability of the second-strongest outcome
- `draw_probability`
  - the calibrated draw probability
- `xg_delta`
  - `expected_home_goals - expected_away_goals`
  - positive values lean home
  - negative values lean away
  - near-zero values indicate a more balanced match
- `close_call_draw_override`
  - `true` when a near-tied outcome distribution and small expected-goal gap push the decoder toward a draw
- `outcome_enforced`
  - `true` when the outcome model is strong enough that the decoder forces the final score to match that direction
- `specialist_rule_triggered`
  - `true` when an internal score-adjustment rule fires
- `specialist_rule_name`
  - the name of that rule, if one was used
- `request`
  - echoes the `home_team`, `away_team`, and `match_date` used in `predict_match()`

## Example Supported Usage
- `predict_match("Athletic", "Osasuna", "2026-04-21")`
- `predict_match("Girona FC", "Real Betis", "2026-04-21")`
- `predict_match("Mallorca", "Valencia", "2026-04-21")`
- batch CSV prediction for a fixture list
- direct feature-row inference for power users

## What This Model Does Not Do
- It does not fetch fresh match history by itself.
- It is not a general multi-league model release.
- It does not know team names and dates magically without a compatible history CSV.
- It does not include application-layer components.
- It does not include app or database logic.
- It is not a betting guarantee engine.

## Versioning
This bundle ships the model artifact:
- `la_liga_score_predictor`

This bundle ships the public package version:
- `2026.04.1`

Planned public cadence:
- two releases per month

## Companion Documents
- `MODEL_CARD.md`
- `RELEASE_GUIDE.md`
- `EVALUATION_SUMMARY.md`
- `DATA_FORMAT.md`
- `FAQ.md`
- `QUICK_PUBLISH_CHECKLIST.md`
- `CHANGELOG.md`
- `ARTIFACTS_SHA256.txt`