---
id: "blood-transfusion-service-center"
slug: "blood-transfusion-service-center"
name: "Blood Transfusion Service Center"
domain: "Healthcare & Biomedicine"
taskType: "binary_classification"
numRows: 748
numColumns: 5
targetColumn: "class"
primaryMetric: "1 - AUC Error"
primaryScore: "0.2446"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmark-containers/resolve/main/containers/blood_transfusion_service_center/01a05c1e-3313-7123-a420-9d558c916775/dataset.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1FOruXkGmge3_o_yeQ7GP_P1NqB9hlV9fJBpya3yINRE/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/blood-transfusion-service-center"
---

# Dataset: Blood Transfusion Service Center (blood-transfusion-service-center)

> The Blood Transfusion Service Center dataset contains 748 donor profiles from Hsin-Chu City, Taiwan, designed for binary classification to predict whether a donor will donate blood during a targeted mobile drive campaign based on RFMTC (Recency, Frequency, Monetary, Time) behavioral metrics.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `binary_classification` |
| **Business Domain** | Healthcare & Biomedicine |
| **Target Column** | `class` |
| **Rows (Instances)** | 748 |
| **Features (Columns)** | 5 |
| **Primary Evaluation Metric** | 1 - AUC Error |
| **Best Benchmark Score** | **0.2446** |

## Business Decision Context
**Context:** Regional blood transfusion centers rely on mobile collection buses visiting institutions to maintain adequate blood reserves, facing unpredictable supply fluctuations and donor fatigue.
**Objective:** Predict the likelihood of a registered donor returning to donate blood during an upcoming mobile drive based on historical donation frequency, recency, and tenure.
**Decision Impact:** Accurate propensity scoring optimizes high-intent outreach campaigns and reduces marketing expenditure while preventing blood shortages. False negatives cause missed collection opportunities leading to critical inventory deficits, while false positives waste dispatch and communication budgets on unresponsive candidates.

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `class` | `numeric` | target | 2 | 0 | Binary target indicator representing whether the individual donated blood during the March 2007 mobile campaign (2 = Yes / Donated; 1 = No / Did not donate). |
| `v1` | `numeric` | feature | 31 | 0 | Number of months elapsed since the donor's most recent blood donation event. |
| `v2` | `numeric` | feature | 33 | 0 | Cumulative total number of blood donations made by the donor across their entire history. |
| `v3` | `numeric` | feature | 33 | 0 | Cumulative volume of blood donated by the individual measured in cubic centimeters (c.c.), where standard donation equals 250 c.c. |
| `v4` | `numeric` | feature | 78 | 0 | Number of months elapsed between the donor's very first recorded donation and the evaluation campaign. |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | Accuracy | ROC AUC | F1-Score |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **LMT** | Machine Learning Model | Python | **79.68%** | 0.7565 | 0.7756 |
| 2 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **79.41%** | 0.7555 | 0.4187 |
| 3 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **79.28%** | 0.7520 | 0.4197 |
| 4 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **79.16%** | 0.7554 | 0.4064 |
| 5 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **79.16%** | 0.7554 | 0.4064 |
| 6 | **MultilayerPerceptron** | Neural Network (MLP) | Python | **79.14%** | 0.7459 | 0.7782 |
| 7 | **ClassificationViaRegression M5P** | Decision Tree | Python | **79.14%** | 0.7472 | 0.7647 |
| 8 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **79.12%** | 0.7554 | 0.4052 |
| 9 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **79.10%** | 0.7548 | 0.4042 |
| 10 | **AdaBoostM1 DecisionStump** | AdaBoost | Python | **78.88%** | 0.7347 | 0.7675 |
| 11 | **J48** | Decision Tree | Python | **78.88%** | 0.7033 | 0.7712 |
| 12 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **78.72%** | 0.7538 | 0.3645 |
| 13 | **JRip** | Machine Learning Model | Python | **78.61%** | 0.6477 | 0.7698 |
| 14 | **LADTree** | Decision Tree | Python | **78.61%** | 0.7104 | 0.7691 |
| 15 | **KernelLogisticRegression RBFKernel** | Logistic / Linear Model | Python | **78.48%** | 0.7591 | 0.7433 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 498 | 250 | 0.2762 | 675ms |
| Fold 1 | 499 | 249 | 0.2450 | 609ms |
| Fold 2 | 499 | 249 | 0.2229 | 621ms |
| Fold 0 | 498 | 250 | 0.2574 | 607ms |
| Fold 1 | 499 | 249 | 0.2434 | 617ms |
| Fold 2 | 499 | 249 | 0.2253 | 606ms |
| Fold 0 | 498 | 250 | 0.2816 | 615ms |
| Fold 1 | 499 | 249 | 0.2697 | 621ms |
| Fold 2 | 499 | 249 | 0.1814 | 609ms |
| Fold 0 | 498 | 250 | 0.2568 | 600ms |
| Fold 1 | 499 | 249 | 0.2735 | 621ms |
| Fold 2 | 499 | 249 | 0.2093 | 603ms |
| Fold 0 | 498 | 250 | 0.2474 | 606ms |
| Fold 1 | 499 | 249 | 0.2204 | 614ms |
| Fold 2 | 499 | 249 | 0.2842 | 610ms |
| Fold 0 | 498 | 250 | 0.2123 | 604ms |
| Fold 1 | 499 | 249 | 0.2024 | 609ms |
| Fold 2 | 499 | 249 | 0.2990 | 624ms |
| Fold 0 | 498 | 250 | 0.2517 | 620ms |
| Fold 1 | 499 | 249 | 0.2689 | 603ms |
| Fold 2 | 499 | 249 | 0.2104 | 613ms |
| Fold 0 | 498 | 250 | 0.2112 | 602ms |
| Fold 1 | 499 | 249 | 0.2738 | 617ms |
| Fold 2 | 499 | 249 | 0.2467 | 601ms |
| Fold 0 | 498 | 250 | 0.2465 | 611ms |
| Fold 1 | 499 | 249 | 0.2635 | 596ms |
| Fold 2 | 499 | 249 | 0.2112 | 601ms |
| Fold 0 | 498 | 250 | 0.2272 | 600ms |
| Fold 1 | 499 | 249 | 0.2585 | 605ms |
| Fold 2 | 499 | 249 | 0.2598 | 605ms |
| Fold 0 | 498 | 250 | 0.2237 | 612ms |
| Fold 1 | 499 | 249 | 0.2462 | 597ms |
| Fold 2 | 499 | 249 | 0.2525 | 613ms |
| Fold 0 | 498 | 250 | 0.2652 | 600ms |
| Fold 1 | 499 | 249 | 0.1973 | 601ms |
| Fold 2 | 499 | 249 | 0.2805 | 600ms |
| Fold 0 | 498 | 250 | 0.2639 | 619ms |
| Fold 1 | 499 | 249 | 0.2514 | 602ms |
| Fold 2 | 499 | 249 | 0.2541 | 610ms |
| Fold 0 | 498 | 250 | 0.2300 | 602ms |
| Fold 1 | 499 | 249 | 0.2912 | 620ms |
| Fold 2 | 499 | 249 | 0.2214 | 602ms |
| Fold 0 | 498 | 250 | 0.2886 | 617ms |
| Fold 1 | 499 | 249 | 0.2446 | 599ms |
| Fold 2 | 499 | 249 | 0.1928 | 629ms |
| Fold 0 | 498 | 250 | 0.2543 | 602ms |
| Fold 1 | 499 | 249 | 0.2245 | 613ms |
| Fold 2 | 499 | 249 | 0.2395 | 594ms |
| Fold 0 | 498 | 250 | 0.2590 | 611ms |
| Fold 1 | 499 | 249 | 0.2097 | 598ms |
| Fold 2 | 499 | 249 | 0.2626 | 612ms |
| Fold 0 | 498 | 250 | 0.2760 | 593ms |
| Fold 1 | 499 | 249 | 0.2144 | 608ms |
| Fold 2 | 499 | 249 | 0.2045 | 600ms |
| Fold 0 | 498 | 250 | 0.2013 | 612ms |
| Fold 1 | 499 | 249 | 0.2644 | 613ms |
| Fold 2 | 499 | 249 | 0.3058 | 633ms |
| Fold 0 | 498 | 250 | 0.2291 | 600ms |
| Fold 1 | 499 | 249 | 0.2705 | 613ms |
| Fold 2 | 499 | 249 | 0.2169 | 604ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmark-containers/resolve/main/containers/blood_transfusion_service_center/01a05c1e-3313-7123-a420-9d558c916775/dataset.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1FOruXkGmge3_o_yeQ7GP_P1NqB9hlV9fJBpya3yINRE/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/1464)
- **Academic Paper / Citation:** [Read Research Paper](https://doi.org/10.1016/j.eswa.2007.11.025)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/blood-transfusion-service-center](https://carlahq.eu/datasets/blood-transfusion-service-center)