churn_statusOpenML #42178 ↗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.
Business Objective: Telco Customer Churn
01Business 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.
02Analytical 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.
03Economic & 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.
Standard GBDT implementations (XGBoost, LightGBM, and CatBoost) achieve strong benchmark performance on this dataset with ROC-AUC scores typically ranging between 0.84 and 0.86 when properly encoding categorical interactions and tenure. Modern tabular foundation models such as TabICL (Carla) achieve competitive zero-shot classification performance directly within in-context inference without requiring feature engineering or hyperparameter tuning pipelines.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 21 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| A | churn_statusChurn Status | TARGET | CAT | — | Target variable indicating whether the customer terminated their service contract within the last month (Yes, No). |
| B | customer_idCustomer ID | Feature | CAT | — | Unique alphanumeric identifier assigned to each telecom subscriber. |
| C | genderGender | Feature | CAT | — | Biological sex/gender classification of the customer (Female, Male). |
| D | is_senior_citizenSenior Citizen Status | Feature | NUM | — | Binary indicator specifying whether the customer is a senior citizen (1 = Yes, 0 = No). |
| E | has_partnerPartner Status | Feature | CAT | — | Indicator of whether the customer has a domestic partner or spouse (Yes, No). |
| F | has_dependentsDependents Status | Feature | CAT | — | Indicator of whether the customer lives with dependents such as children or elderly family members (Yes, No). |
| G | tenure_monthsTenure | Feature | NUM | months | Total number of consecutive months the customer has maintained an active subscription with the company. |
| H | has_phone_servicePhone Service | Feature | CAT | — | Indicates whether the customer subscribes to standard landline phone service (Yes, No). |
| I | multiple_lines_statusMultiple Lines | Feature | CAT | — | Indicates whether the customer has multiple phone lines (Yes, No, No phone service). |
| J | internet_service_typeInternet Service Provider | Feature | CAT | — | The category of broadband internet connection utilized by the customer (DSL, Fiber optic, No). |
| K | online_security_addonOnline Security | Feature | CAT | — | Indicates if the customer subscribes to add-on online threat security features (Yes, No, No internet service). |
| L | online_backup_addonOnline Backup | Feature | CAT | — | Indicates if the customer subscribes to cloud data backup services (Yes, No, No internet service). |
| M | device_protection_planDevice Protection | Feature | CAT | — | Indicates if the customer has subscribed to hardware warranty and insurance protection (Yes, No, No internet service). |
| N | tech_support_addonTechnical Support | Feature | CAT | — | Indicates if the customer has premium technical support included in their subscription (Yes, No, No internet service). |
| O | streaming_tv_addonStreaming TV | Feature | CAT | — | Indicates whether the subscriber uses third-party streaming television services provided over broadband (Yes, No, No internet service). |
| P | streaming_movies_addonStreaming Movies | Feature | CAT | — | Indicates whether the subscriber streams on-demand movies via provider packages (Yes, No, No internet service). |
| Q | contract_termContract Term | Feature | CAT | — | Customer agreement commitment duration (Month-to-month, One year, Two year). |
| R | paperless_billing_enabledPaperless Billing | Feature | CAT | — | Indicates whether invoice statements are delivered electronically rather than via postal mail (Yes, No). |
| S | payment_methodPayment Method | Feature | CAT | — | Customer's selected invoice settlement option (Electronic check, Mailed check, Bank transfer (automatic), Credit card (automatic)). |
| T | monthly_charges_usdMonthly Charges | Feature | NUM | USD | The recurring bill amount charged to the subscriber each month. |
| U | total_charges_usdTotal Charges | Feature | NUM | USD | Cumulative gross amount billed to the customer across their entire account lifecycle. |
Interactive Data Table
Explore rows, feature values, and target labels for Telco Customer Churn.
TabICLv2 WebGPU Benchmark Results
Complete performance metrics on persisted IID or non-IID evaluation splits, executed 100% locally in the browser sandbox.
| Evaluation Split | Train Rows | Test Rows | Split Duration?Wall-clock inference time taken for this evaluation split running 100% locally via WebGPU.Learn more → | Accuracy?Proportion of correct test predictions across all classes.Google ML Guide & Details → | ROC-AUC?Area under the ROC curve evaluating ranking capability across all thresholds.Google ML Guide & Details → | F1 Score?Harmonic mean of Precision and Recall, robust against class imbalance.Learn more → | Precision?Proportion of predicted positives that were actually positive.Google ML Guide & Details → | Recall?Proportion of actual positive cases successfully captured.Google ML Guide & Details → |
|---|---|---|---|---|---|---|---|---|
| R1 / F1 | 4,695 | 2,348 | 10.44s | 81.09% | 0.8531 | 0.6071 | 0.6765 | 0.5506 |
| R1 / F2 | 4,695 | 2,348 | 10.31s | 80.15% | 0.8516 | 0.5764 | 0.6646 | 0.5088 |
| R1 / F3 | 4,696 | 2,347 | 10.10s | 80.36% | 0.8502 | 0.5805 | 0.6702 | 0.5120 |
| R2 / F1 | 4,695 | 2,348 | 10.33s | 80.79% | 0.8565 | 0.5919 | 0.6784 | 0.5249 |
| R2 / F2 | 4,695 | 2,348 | 10.29s | 80.15% | 0.8517 | 0.5847 | 0.6573 | 0.5265 |
| R2 / F3 | 4,696 | 2,347 | 10.11s | 80.74% | 0.8467 | 0.5868 | 0.6815 | 0.5152 |
| R3 / F1 | 4,695 | 2,348 | 10.38s | 82.41% | 0.8724 | 0.6194 | 0.7273 | 0.5393 |
| R3 / F2 | 4,695 | 2,348 | 10.24s | 79.43% | 0.8481 | 0.5684 | 0.6411 | 0.5104 |
| R3 / F3 | 4,696 | 2,347 | 9.95s | 79.76% | 0.8310 | 0.5793 | 0.6462 | 0.5249 |
| Mean ± Std | — | — | 10.24s | 80.54% ± 0.82% | 0.851 ± 0.010 | 0.588 ± 0.015 | 0.671 | 0.524 |
Foundation Models vs Traditional ML Baselines
Side-by-side evaluation of our in-browser Carla engine (WebGPU), open-source tabular foundation models, and OpenML baselines.
| Rank | Algorithm / Model | Model Family | Runtime | Predictive Accuracy?Proportion of correct test predictions across cross-validation splits.Google ML Guide & Details → | ROC-AUC?Area under the ROC curve evaluating ranking capability.Learn more → | F-Measure?Harmonic mean of precision and recall.Learn more → | Reference / Repo |
|---|---|---|---|---|---|---|---|
| #1 | TabPFN v3 | Tabular Foundation Model | PyTorch/Python | 80.59% | 0.8514 | 0.5864 | PriorLabs/tabpfn ↗ |
| #2 | EXAONE Tabular | Tabular Foundation Model | PyTorch/Python | 80.56% | 0.8516 | 0.5886 | LGAI-Research/EXAONE-Tabular ↗ |
| #3 | Full TabICLv2 (PyTorch Reference) | Tabular Foundation Model | PyTorch/Python | 80.55% | 0.8512 | 0.5884 | soda-inria/tabicl ↗ |
| #4 | Google TabFM v1.0 | Tabular Foundation Model | PyTorch/Python | 80.55% | 0.8526 | 0.5864 | google-research/tabfm ↗ |
| #5 | Carla Engine (TabICLv2 WebGPU) | Tabular Foundation Model | Browser | 80.54% | 0.8513 | 0.5883 | 100% In-Browser |
| #6 | nanotabicl Vanilla | Tabular Foundation Model | PyTorch/Python | 80.53% | 0.8512 | 0.5878 | soda-inria/nanotabicl ↗ |
| #7 | Streaming nanotabicl | Tabular Foundation Model | PyTorch/Python | 80.49% | 0.8511 | 0.5868 | soda-inria/nanotabicl ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 7,043 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| A | churn_statusTARGET | CAT | 0 | 2 | 2 cats: No, Yes | NoNoYes |
| B | customer_id | CAT | 0 | 7,043 | — | 7590-VHVEG5575-GNVDE3668-QPYBK |
| C | gender | CAT | 0 | 2 | 2 cats: Male, Female | FemaleMaleMale |
| D | is_senior_citizen | NUM | 0 | 2 | [0, 1] μ=0.2 σ=0.4 | 000 |
| E | has_partner | CAT | 0 | 2 | 2 cats: No, Yes | YesNoNo |
| F | has_dependents | CAT | 0 | 2 | 2 cats: No, Yes | NoNoNo |
| G | tenure_months | NUM | 0 | 73 | [0, 72] μ=32.4 σ=24.6 | 1342 |
| H | has_phone_service | CAT | 0 | 2 | 2 cats: Yes, No | NoYesYes |
| I | multiple_lines_status | CAT | 0 | 3 | 3 cats: No, Yes, No phone service | No phone serviceNoNo |
| J | internet_service_type | CAT | 0 | 3 | 3 cats: Fiber optic, DSL, No | DSLDSLDSL |
| K | online_security_addon | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | NoYesYes |
| L | online_backup_addon | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | YesNoYes |
| M | device_protection_plan | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | NoYesNo |
| N | tech_support_addon | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | NoNoNo |
| O | streaming_tv_addon | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | NoNoNo |
| P | streaming_movies_addon | CAT | 0 | 3 | 3 cats: No, Yes, No internet service | NoNoNo |
| Q | contract_term | CAT | 0 | 3 | 3 cats: Month-to-month, Two year, One year | Month-to-monthOne yearMonth-to-month |
| R | paperless_billing_enabled | CAT | 0 | 2 | 2 cats: Yes, No | YesNoYes |
| S | payment_method | CAT | 0 | 4 | 4 cats: Electronic check, Mailed check, Bank transfer (automatic) +1 more | Electronic checkMailed checkMailed check |
| T | monthly_charges_usd | NUM | 0 | 1,585 | [18.25, 118.75] μ=64.8 σ=30.1 | 29.8556.9553.85 |
| U | total_charges_usd | NUM | 11 (0.16%) | 6,530 | [18.8, 8684.8] μ=2283.3 σ=2266.6 | 29.851889.5108.15 |
Frequently Asked Questions: Telco Customer Churn
Common questions regarding the Telco Customer Churn dataset, machine learning task formulations, and in-browser tabular inference.
What is the Telco Customer Churn dataset used for?
The Telco Customer Churn dataset contains 7,043 customer records used to benchmark supervised classification algorithms for predicting whether telecommunications subscribers will cancel their services.
Can I run zero-server predictions on this dataset in Google Sheets?
Yes, Carla HQ enables zero-server in-context tabular prediction directly in spreadsheets using TabICL foundation models without building or maintaining complex Python pipelines.
What machine learning models perform best on Telco Customer Churn?
Gradient boosting frameworks like LightGBM, CatBoost, and XGBoost typically achieve ROC-AUC scores around 0.84 to 0.86, while tabular foundation models like TabICL deliver comparable accuracy zero-shot.
Test TabICLv2 on Telco Customer Churn Yourself
Open the pre-loaded Google Sheet and let Carla configure the target and task for local, zero-cloud tabular machine learning.
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Review the Setup
Carla selects the dataset target and task from this page automatically.
Evaluate & Predict
Run predictions and compute metrics with zero server uploads.
Provenance & Attribution
OpenML Dataset 42178