---
id: "telco-customer-churn"
slug: "telco-customer-churn"
name: "Telco Customer Churn"
domain: "Telecommunications & Subscription Services"
taskType: "binary_classification"
numRows: 7043
numColumns: 21
targetColumn: "churn_status"
primaryMetric: "1 - AUC Error"
primaryScore: "0.1488"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/telco-customer-churn/telco-customer-churn.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1-P0FaTondYdzgL0sLsrsEBEliKv-nnO73lBd0248ulE/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/telco-customer-churn"
---

# Dataset: Telco Customer Churn (telco-customer-churn)

> Benchmark telecommunications dataset comprising 7,043 subscriber profiles designed to predict customer churn based on demographics, subscribed services, account tenure, and billing details.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `binary_classification` |
| **Business Domain** | Telecommunications & Subscription Services |
| **Target Column** | `churn_status` |
| **Rows (Instances)** | 7,043 |
| **Features (Columns)** | 21 |
| **Primary Evaluation Metric** | 1 - AUC Error |
| **Best Benchmark Score** | **0.1488** |

## Business Decision Context
**Context:** Subscription telecommunication providers operate in highly competitive, commoditized markets where acquiring a new customer costs 5 to 7 times more than retaining an existing subscriber. Identifying dissatisfaction and flight risk before service cancellation is vital for recurring revenue stability.
**Objective:** Predict the binary probability of an individual customer terminating their subscription within the upcoming month based on usage patterns, contract terms, and payment behavior.
**Decision Impact:** Accurate churn prediction allows proactive retention outreach and targeted discount incentives to protect customer lifetime value (LTV). A false negative results in permanent churn and lost monthly recurring revenue, whereas a false positive incurs unnecessary retention discount costs without retention upside.

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `churn_status` | `categorical` | target | 2 | 0 | Target variable indicating whether the customer terminated their service contract within the last month (Yes, No). |
| `customer_id` | `string` | feature | 7,043 | 0 | Unique alphanumeric identifier assigned to each telecom subscriber. |
| `gender` | `categorical` | feature | 2 | 0 | Biological sex/gender classification of the customer (Female, Male). |
| `is_senior_citizen` | `numeric` | feature | 2 | 0 | Binary indicator specifying whether the customer is a senior citizen (1 = Yes, 0 = No). |
| `has_partner` | `categorical` | feature | 2 | 0 | Indicator of whether the customer has a domestic partner or spouse (Yes, No). |
| `has_dependents` | `categorical` | feature | 2 | 0 | Indicator of whether the customer lives with dependents such as children or elderly family members (Yes, No). |
| `tenure_months` | `numeric` | feature | 73 | 0 | Total number of consecutive months the customer has maintained an active subscription with the company. |
| `has_phone_service` | `categorical` | feature | 2 | 0 | Indicates whether the customer subscribes to standard landline phone service (Yes, No). |
| `multiple_lines_status` | `categorical` | feature | 3 | 0 | Indicates whether the customer has multiple phone lines (Yes, No, No phone service). |
| `internet_service_type` | `categorical` | feature | 3 | 0 | The category of broadband internet connection utilized by the customer (DSL, Fiber optic, No). |
| `online_security_addon` | `categorical` | feature | 3 | 0 | Indicates if the customer subscribes to add-on online threat security features (Yes, No, No internet service). |
| `online_backup_addon` | `categorical` | feature | 3 | 0 | Indicates if the customer subscribes to cloud data backup services (Yes, No, No internet service). |
| `device_protection_plan` | `categorical` | feature | 3 | 0 | Indicates if the customer has subscribed to hardware warranty and insurance protection (Yes, No, No internet service). |
| `tech_support_addon` | `categorical` | feature | 3 | 0 | Indicates if the customer has premium technical support included in their subscription (Yes, No, No internet service). |
| `streaming_tv_addon` | `categorical` | feature | 3 | 0 | Indicates whether the subscriber uses third-party streaming television services provided over broadband (Yes, No, No internet service). |
| `streaming_movies_addon` | `categorical` | feature | 3 | 0 | Indicates whether the subscriber streams on-demand movies via provider packages (Yes, No, No internet service). |
| `contract_term` | `categorical` | feature | 3 | 0 | Customer agreement commitment duration (Month-to-month, One year, Two year). |
| `paperless_billing_enabled` | `categorical` | feature | 2 | 0 | Indicates whether invoice statements are delivered electronically rather than via postal mail (Yes, No). |
| `payment_method` | `categorical` | feature | 4 | 0 | Customer's selected invoice settlement option (Electronic check, Mailed check, Bank transfer (automatic), Credit card (automatic)). |
| `monthly_charges_usd` | `numeric` | feature | 1,585 | 0 | The recurring bill amount charged to the subscriber each month. |
| `total_charges_usd` | `numeric` | feature | 6,530 | 11 | Cumulative gross amount billed to the customer across their entire account lifecycle. |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | Accuracy | ROC AUC | F1-Score |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **80.59%** | 0.8514 | 0.5864 |
| 2 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **80.56%** | 0.8516 | 0.5886 |
| 3 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **80.55%** | 0.8512 | 0.5884 |
| 4 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **80.55%** | 0.8526 | 0.5864 |
| 5 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **80.54%** | 0.8513 | 0.5883 |
| 6 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **80.53%** | 0.8512 | 0.5878 |
| 7 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **80.49%** | 0.8511 | 0.5868 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 4695 | 2348 | 0.1474 | 2642ms |
| Fold 1 | 4695 | 2348 | 0.1480 | 2633ms |
| Fold 2 | 4696 | 2347 | 0.1497 | 2635ms |
| Fold 0 | 4695 | 2348 | 0.1437 | 2630ms |
| Fold 1 | 4695 | 2348 | 0.1474 | 2646ms |
| Fold 2 | 4696 | 2347 | 0.1541 | 2642ms |
| Fold 0 | 4695 | 2348 | 0.1276 | 2635ms |
| Fold 1 | 4695 | 2348 | 0.1517 | 2617ms |
| Fold 2 | 4696 | 2347 | 0.1696 | 2617ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/telco-customer-churn/telco-customer-churn.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1-P0FaTondYdzgL0sLsrsEBEliKv-nnO73lBd0248ulE/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/42178)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/telco-customer-churn](https://carlahq.eu/datasets/telco-customer-churn)