---
id: "adult"
slug: "adult"
name: "Adult"
domain: "Economics & Public Policy"
taskType: "binary_classification"
numRows: 48842
numColumns: 15
targetColumn: "income_bracket"
primaryMetric: "1 - AUC Error"
primaryScore: "0.0793"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/adult/adult.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1cuv3iXP538yt3L9tY8IZWGFOUKzwfDtzmAK-3vtMcoU/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/adult"
---

# Dataset: Adult (adult)

> Benchmark demographic dataset consisting of 48,842 records extracted from the 1994 US Census Bureau database, designed to predict whether an individual's annual income exceeds $50,000.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `binary_classification` |
| **Business Domain** | Economics & Public Policy |
| **Target Column** | `income_bracket` |
| **Rows (Instances)** | 48,842 |
| **Features (Columns)** | 15 |
| **Primary Evaluation Metric** | 1 - AUC Error |
| **Best Benchmark Score** | **0.0793** |

## Business Decision Context
**Context:** Financial institutions, marketers, and public policy researchers require granular socioeconomic indicators to evaluate creditworthiness, segment consumer demographics, and assess workforce equity across regions without intrusive direct income disclosures.
**Objective:** Predict whether an individual earns more than $50,000 annually based on demographic, occupational, and capital investment characteristics.
**Decision Impact:** Enables precise customer lifetime value estimation, targeted financial product marketing, and automated wealth tiering while avoiding costly underwriting errors and mitigating demographic model bias.

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `income_bracket` | `categorical` | target | 2 | 0 | Annual income tier classification indicating whether total income is <=50K or >50K. |
| `age_years` | `numeric` | feature | 74 | 0 | Age of the individual in years. |
| `employment_sector` | `categorical` | feature | 8 | 2799 | General sector and type of employer (e.g., Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked). |
| `demographic_weight` | `numeric` | feature | 28,523 | 0 | Statistical sampling weight assigned by the US Census Bureau representing population control totals across demographic segments within each state. |
| `education_level` | `categorical` | feature | 16 | 0 | Highest level of formal education completed (e.g., Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool). |
| `education_years` | `numeric` | feature | 16 | 0 | Total completed years/stages of formal education represented on an ordinal numerical scale (1-16). |
| `marital_status` | `categorical` | feature | 7 | 0 | Marital status of the individual (e.g., Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse). |
| `job_occupation` | `categorical` | feature | 14 | 2809 | Primary job role or professional category (e.g., Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces). |
| `household_relationship` | `categorical` | feature | 6 | 0 | Role of the individual within their household (e.g., Wife, Own-child, Husband, Not-in-family, Other-relative, Unmarried). |
| `ethnicity_race` | `categorical` | feature | 5 | 0 | Self-reported racial background (e.g., White, Asian-Pac-Islander, Amer-Indian-Eskimo, Other, Black). |
| `gender` | `categorical` | feature | 2 | 0 | Biological sex of the individual (Male, Female). |
| `annual_capital_gain_usd` | `numeric` | feature | 123 | 0 | Recorded annual income gains derived from investments and capital asset sales. |
| `annual_capital_loss_usd` | `numeric` | feature | 99 | 0 | Recorded annual capital losses incurred from investments and asset sales. |
| `weekly_work_hours` | `numeric` | feature | 96 | 0 | Reported average working hours per week. |
| `country_of_origin` | `categorical` | feature | 41 | 857 | Country of birth or nationality of the individual. |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | Accuracy | ROC AUC | F1-Score |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **87.60%** | 0.9323 | 0.7162 |
| 2 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **87.58%** | 0.9320 | 0.7171 |
| 3 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **86.83%** | 0.9237 | 0.6992 |
| 4 | **FilteredClassifier J48** | Decision Tree | Python | **86.72%** | 0.8933 | 0.8615 |
| 5 | **FilteredClassifier MultiSearch LogitBoost REPTree** | Logistic / Linear Model | Python | **86.63%** | 0.9199 | 0.8603 |
| 6 | **DTNB** | Machine Learning Model | Python | **86.43%** | 0.9178 | 0.8617 |
| 7 | **SimpleCart** | Machine Learning Model | Python | **86.42%** | 0.8901 | 0.8573 |
| 8 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **86.38%** | 0.9201 | 0.6864 |
| 9 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **86.33%** | 0.9224 | 0.6941 |
| 10 | **NBTree** | Decision Tree | Python | **86.32%** | 0.9078 | 0.8599 |
| 11 | **FilteredClassifier MultilayerPerceptron** | Neural Network (MLP) | Python | **86.30%** | 0.8893 | 0.8566 |
| 12 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **86.23%** | 0.9207 | 0.6875 |
| 13 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **86.18%** | 0.9178 | 0.6817 |
| 14 | **J48** | Decision Tree | Python | **86.17%** | 0.8933 | 0.8553 |
| 15 | **END ND J48** | Decision Tree | Python | **86.11%** | 0.8892 | 0.8552 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 32561 | 16281 | 0.0753 | 23833ms |
| Fold 1 | 32561 | 16281 | 0.0840 | 23824ms |
| Fold 2 | 32562 | 16280 | 0.0835 | 23940ms |
| Fold 0 | 32561 | 16281 | 0.0723 | 23847ms |
| Fold 1 | 32561 | 16281 | 0.0854 | 23842ms |
| Fold 2 | 32562 | 16280 | 0.0747 | 23822ms |
| Fold 0 | 32561 | 16281 | 0.0731 | 23965ms |
| Fold 1 | 32561 | 16281 | 0.0725 | 23675ms |
| Fold 2 | 32562 | 16280 | 0.0929 | 23778ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/adult/adult.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1cuv3iXP538yt3L9tY8IZWGFOUKzwfDtzmAK-3vtMcoU/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/1590)
- **Academic Paper / Citation:** [Read Research Paper](https://archive.ics.uci.edu/dataset/2/adult)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/adult](https://carlahq.eu/datasets/adult)