---
id: "abalone"
slug: "abalone"
name: "Abalone"
domain: "Agriculture, Forestry & Fishing"
taskType: "regression"
numRows: 4177
numColumns: 9
targetColumn: "number_of_rings"
primaryMetric: "RMSE"
primaryScore: "2.03"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/abalone/abalone.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1oHtpxcQaCVeuAN4z7y8lAnBGfSBHc_PzVeDeo9hYddE/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/abalone"
---

# Dataset: Abalone (abalone)

> Benchmark aquaculture dataset containing 4,177 records designed to predict the age and shell ring count of abalones using non-destructive physical biometric measurements.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `regression` |
| **Business Domain** | Agriculture, Forestry & Fishing |
| **Target Column** | `number_of_rings` |
| **Rows (Instances)** | 4,177 |
| **Features (Columns)** | 9 |
| **Primary Evaluation Metric** | RMSE |
| **Best Benchmark Score** | **2.03** |

## Business Decision Context
**Context:** In commercial shellfish aquaculture and marine fisheries management, determining abalone maturity traditionally requires destructive cone slicing, chemical staining, and microscopic ring counting under a lab microscope.
**Objective:** Predict the exact number of shell rings (representing age in years + 1.5) non-destructively based on rapidly measurable physical dimensions and mass attributes.
**Decision Impact:** Eliminates destructive testing and tedious lab inspections, accelerating commercial grading throughput while preventing regulatory fines from harvesting underage stock. Underestimating age results in premature harvesting and revenue loss, while overestimating leads to unnecessary feed and holding expenditures.

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `number_of_rings` | `numeric` | target | 28 | 0 | Count of growth rings stained and identified under microscope; adding 1.5 yields the chronological age in years. |
| `sex` | `categorical` | feature | 3 | 0 | Biological sex classification of the abalone: 'M' (Male), 'F' (Female), or 'I' (Infant/Sexually Immature). |
| `length_mm` | `numeric` | feature | 134 | 0 | Longest linear dimension of the abalone shell (scaled in mm). |
| `diameter_mm` | `numeric` | feature | 111 | 0 | Measurement of the shell diameter perpendicular to the length axis (scaled in mm). |
| `height_mm` | `numeric` | feature | 51 | 0 | Vertical height of the shell including the meat core (scaled in mm). |
| `whole_weight_g` | `numeric` | feature | 2,429 | 0 | Total live weight of the intact abalone organism (scaled in grams). |
| `shucked_weight_g` | `numeric` | feature | 1,515 | 0 | Weight of the edible abalone meat extracted after shucking (scaled in grams). |
| `viscera_weight_g` | `numeric` | feature | 880 | 0 | Weight of the internal gut organs measured after post-harvest bleeding (scaled in grams). |
| `shell_weight_g` | `numeric` | feature | 926 | 0 | Weight of the calcified shell structure measured after thermal drying (scaled in grams). |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | R² Score | MAE | RMSE |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **0.6053** | 1.4 | 2 |
| 2 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **0.6044** | 1.4 | 2 |
| 3 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **0.6029** | 1.4 | 2 |
| 4 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **0.6019** | 1.4 | 2 |
| 5 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **0.6014** | 1.4 | 2 |
| 6 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **0.6012** | 1.4 | 2 |
| 7 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **0.5994** | 1.4 | 2 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 2784 | 1393 | 1.9116 | 1237ms |
| Fold 1 | 2785 | 1392 | 2.0916 | 1116ms |
| Fold 2 | 2785 | 1392 | 2.1122 | 1046ms |
| Fold 0 | 2784 | 1393 | 2.0587 | 1028ms |
| Fold 1 | 2785 | 1392 | 2.1177 | 1040ms |
| Fold 2 | 2785 | 1392 | 1.9128 | 1031ms |
| Fold 0 | 2784 | 1393 | 1.9914 | 1041ms |
| Fold 1 | 2785 | 1392 | 2.2076 | 1031ms |
| Fold 2 | 2785 | 1392 | 1.8920 | 1041ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/abalone/abalone.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1oHtpxcQaCVeuAN4z7y8lAnBGfSBHc_PzVeDeo9hYddE/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/42726)
- **Academic Paper / Citation:** [Read Research Paper](https://archive.ics.uci.edu/dataset/1/abalone)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/abalone](https://carlahq.eu/datasets/abalone)