---
id: "amazon-employee-access"
slug: "amazon-employee-access"
name: "Amazon Employee Access"
domain: "Information Technology & Enterprise Security"
taskType: "binary_classification"
numRows: 32769
numColumns: 10
targetColumn: "access_approved"
primaryMetric: "1 - AUC Error"
primaryScore: "0.1483"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/amazon-employee-access/amazon-employee-access.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1grJ3LzMEVU4ut7UWlzlMFkhHhpmi3H60_UN5k0fGSGw/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/amazon-employee-access"
---

# Dataset: Amazon Employee Access (amazon-employee-access)

> Enterprise identity and access management benchmark containing 32,769 historical access requests to automate employee permission approvals and denials based on organizational roles.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `binary_classification` |
| **Business Domain** | Information Technology & Enterprise Security |
| **Target Column** | `access_approved` |
| **Rows (Instances)** | 32,769 |
| **Features (Columns)** | 10 |
| **Primary Evaluation Metric** | 1 - AUC Error |
| **Best Benchmark Score** | **0.1483** |

## Business Decision Context
**Context:** Enterprise employees continuously require specific software, database, and portal permissions as they transition across departments, projects, and seniority levels. Manual supervisor reviews create operational bottlenecks, delay onboarding, and increase IT ticket overhead.
**Objective:** Predict whether an employee's requested access to a specific enterprise resource should be automatically approved (1) or denied (0) based on their manager and organizational role hierarchy.
**Decision Impact:** Automates access provisioning workflows, slashing employee onboarding latency and IT helpdesk costs while mitigating compliance risks from wrongful authorization (false positives) and productivity loss from unnecessary denials (false negatives).

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `access_approved` | `numeric` | target | 2 | 0 | Binary decision target indicating whether access to the specified resource was approved (1) or denied/revoked (0). |
| `resource_id` | `numeric` | feature | 7,518 | 0 | Anonymized unique integer identifier representing the specific IT resource, database, or software application requested by the employee. |
| `manager_id` | `numeric` | feature | 4,243 | 0 | Unique anonymized employee identifier of the direct supervisor or manager responsible for the requesting employee. |
| `role_rollup_1` | `numeric` | feature | 128 | 0 | Highest-level organizational group identifier representing broad corporate divisions (e.g., US Engineering vs. EU Operations). |
| `role_rollup_2` | `numeric` | feature | 177 | 0 | Secondary organizational subdivision category identifier providing narrower departmental context within Rollup 1. |
| `role_department_id` | `numeric` | feature | 449 | 0 | Anonymized integer code corresponding to the employee's specific functional department (e.g., Retail Logistics, Security Infrastructure). |
| `role_title_id` | `numeric` | feature | 343 | 0 | Anonymized identifier corresponding to the formal business title of the employee (e.g., Senior Software Development Engineer). |
| `role_family_description_id` | `numeric` | feature | 2,358 | 0 | Anonymized identifier capturing the granular role family descriptor and technical track classification. |
| `role_family_id` | `numeric` | feature | 67 | 0 | High-level job family group identifier categorizing the broader profession (e.g., Software Engineering, Product Management). |
| `role_code_id` | `numeric` | feature | 343 | 0 | Granular unique code assigned to the exact role profile combining title, level, and departmental hierarchy. |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | Accuracy | ROC AUC | F1-Score |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **classif.ranger** | Machine Learning Model | Python | **95.24%** | 0.6638 | 0.9447 |
| 2 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **95.23%** | 0.8727 | 0.9750 |
| 3 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **95.20%** | 0.8768 | 0.9750 |
| 4 | **mlr.classif.ranger** | Machine Learning Model | Python | **95.14%** | 0.8660 | 0.9417 |
| 5 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **95.02%** | 0.8458 | 0.9741 |
| 6 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **95.00%** | 0.8513 | 0.9739 |
| 7 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **95.00%** | 0.8517 | 0.9739 |
| 8 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **94.99%** | 0.8523 | 0.9739 |
| 9 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **94.70%** | 0.8453 | 0.9726 |
| 10 | **IBk** | k-Nearest Neighbors (k-NN) | Python | **94.70%** | 0.8429 | 0.9410 |
| 11 | **classif.IBk** | k-Nearest Neighbors (k-NN) | Python | **94.63%** | 0.7345 | 0.9452 |
| 12 | **pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature selection.variance threshold.VarianceThreshold,classifier=sklearn.tree.tree.DecisionTreeClassifier)** | Decision Tree | Python | **94.55%** | 0.7168 | 0.9435 |
| 13 | **AttributeSelectedClassifier IBk** | k-Nearest Neighbors (k-NN) | Python | **94.44%** | 0.8241 | 0.9231 |
| 14 | **classif.ada** | Machine Learning Model | Python | **94.35%** | 0.6613 | 0.9380 |
| 15 | **JRip** | Machine Learning Model | Python | **94.27%** | 0.5272 | 0.9197 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 21846 | 10923 | 0.1579 | 11919ms |
| Fold 1 | 21846 | 10923 | 0.1446 | 11906ms |
| Fold 2 | 21846 | 10923 | 0.1414 | 11938ms |
| Fold 0 | 21846 | 10923 | 0.1511 | 11908ms |
| Fold 1 | 21846 | 10923 | 0.1501 | 11961ms |
| Fold 2 | 21846 | 10923 | 0.1405 | 11939ms |
| Fold 0 | 21846 | 10923 | 0.1393 | 11912ms |
| Fold 1 | 21846 | 10923 | 0.1513 | 11934ms |
| Fold 2 | 21846 | 10923 | 0.1587 | 11958ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/amazon-employee-access/amazon-employee-access.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1grJ3LzMEVU4ut7UWlzlMFkhHhpmi3H60_UN5k0fGSGw/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/4135)
- **Academic Paper / Citation:** [Read Research Paper](https://www.kaggle.com/c/amazon-employee-access-challenge)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/amazon-employee-access](https://carlahq.eu/datasets/amazon-employee-access)