attendedFitness Club
The Fitness Club dataset contains 1,500 booking records from the Canadian gym chain GoalZone to predict class attendance and minimize no-show rates for high-demand workout sessions.
Business Objective: Fitness Club
01Business Context
GoalZone operates boutique fitness classes capped at 15 or 25 participants. High booking demand frequently leads to fully booked sessions that paradoxically suffer from elevated no-show rates, leaving equipment underutilized and turning away motivated walk-in members.
02Analytical Objective
Predict whether a booked member will attend their scheduled fitness session based on membership tenure, physical profile, booking lead time, and session metadata.
03Economic & Decision Impact
Accurate attendance forecasting allows dynamic overbooking and waitlist backfilling, maximizing studio capacity utilization while preventing revenue loss. False negatives (predicting no-show for an attendee) risk customer dissatisfaction from overbooking, whereas false positives (predicting attendance for a no-show) leave empty spots on studio floors.
Standard gradient-boosted trees (XGBoost, LightGBM) and Random Forest achieve solid baseline ROC-AUC scores (~0.75-0.79) by heavily leveraging membership tenure and booking lead time. In-context tabular foundation models such as TabICL and Carla match or exceed these tree-based baselines zero-shot, eliminating feature encoding overhead and hyperparameter tuning directly within business spreadsheets.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 7 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| G | attendedAttended Class | TARGET | CAT | — | Binary ground-truth outcome indicating whether the booked member attended the scheduled class session ('Yes' or 'No'). |
| A | months_as_memberMembership Tenure (Months) | Feature | NUM | months | Total number of consecutive months the individual has held an active gym membership at GoalZone. |
| B | weightMember Weight | Feature | NUM | kg | Current recorded body weight of the member in kilograms. |
| C | days_beforeBooking Lead Time | Feature | NUM | days | Number of days in advance the member reserved their spot in the class. |
| D | day_of_weekClass Day of Week | Feature | CAT | — | The day of the week on which the fitness class is scheduled (e.g. Mon, Tue, Wed, Thu, Fri, Sat, Sun). |
| E | timeClass Time Period | Feature | CAT | — | Scheduled time block of the class, indicating morning (AM) or afternoon/evening (PM) sessions. |
| F | categoryFitness Class Category | Feature | CAT | — | Specific workout discipline or class type (e.g. HIIT, Strength, Cycling, Yoga, Aqua). |
Interactive Data Table
Explore rows, feature values, and target labels for Fitness Club.
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 | 1,000 | 500 | 1.31s | 78.60% | 0.8179 | 0.5932 | 0.7027 | 0.5132 |
| R1 / F2 | 1,000 | 500 | 1.25s | 78.60% | 0.8207 | 0.6081 | 0.6803 | 0.5497 |
| R1 / F3 | 1,000 | 500 | 1.27s | 77.40% | 0.8216 | 0.5272 | 0.7159 | 0.4172 |
| R2 / F1 | 1,000 | 500 | 1.25s | 76.60% | 0.8039 | 0.5618 | 0.6522 | 0.4934 |
| R2 / F2 | 1,000 | 500 | 1.24s | 79.60% | 0.8302 | 0.6016 | 0.7333 | 0.5099 |
| R2 / F3 | 1,000 | 500 | 1.24s | 77.40% | 0.8255 | 0.5462 | 0.6939 | 0.4503 |
| R3 / F1 | 1,000 | 500 | 1.25s | 77.80% | 0.8309 | 0.6050 | 0.6589 | 0.5592 |
| R3 / F2 | 1,000 | 500 | 1.24s | 80.40% | 0.8251 | 0.6048 | 0.7732 | 0.4967 |
| R3 / F3 | 1,000 | 500 | 1.25s | 75.60% | 0.7985 | 0.5159 | 0.6436 | 0.4305 |
| R4 / F1 | 1,000 | 500 | 1.24s | 77.00% | 0.7903 | 0.5848 | 0.6480 | 0.5329 |
| R4 / F2 | 1,000 | 500 | 1.25s | 79.20% | 0.8455 | 0.5906 | 0.7282 | 0.4967 |
| R4 / F3 | 1,000 | 500 | 1.26s | 78.00% | 0.8253 | 0.5635 | 0.7030 | 0.4702 |
| R5 / F1 | 1,000 | 500 | 1.25s | 79.80% | 0.8197 | 0.5878 | 0.7742 | 0.4737 |
| R5 / F2 | 1,000 | 500 | 1.23s | 77.00% | 0.8214 | 0.5907 | 0.6385 | 0.5497 |
| R5 / F3 | 1,000 | 500 | 1.24s | 76.80% | 0.8204 | 0.5504 | 0.6636 | 0.4702 |
| R6 / F1 | 1,000 | 500 | 1.24s | 79.40% | 0.8383 | 0.6084 | 0.7207 | 0.5263 |
| R6 / F2 | 1,000 | 500 | 1.24s | 78.00% | 0.8124 | 0.5703 | 0.6952 | 0.4834 |
| R6 / F3 | 1,000 | 500 | 1.23s | 77.40% | 0.8127 | 0.5670 | 0.6727 | 0.4901 |
| R7 / F1 | 1,000 | 500 | 1.25s | 73.60% | 0.7889 | 0.5147 | 0.5833 | 0.4605 |
| R7 / F2 | 1,000 | 500 | 1.25s | 80.40% | 0.8266 | 0.5950 | 0.7912 | 0.4768 |
| R7 / F3 | 1,000 | 500 | 1.24s | 79.60% | 0.8415 | 0.6165 | 0.7130 | 0.5430 |
| R8 / F1 | 1,000 | 500 | 1.23s | 78.40% | 0.8192 | 0.5781 | 0.7115 | 0.4868 |
| R8 / F2 | 1,000 | 500 | 1.24s | 78.00% | 0.8326 | 0.5635 | 0.7030 | 0.4702 |
| R8 / F3 | 1,000 | 500 | 1.24s | 78.40% | 0.8144 | 0.6087 | 0.6720 | 0.5563 |
| R9 / F1 | 1,000 | 500 | 1.24s | 78.40% | 0.8420 | 0.5814 | 0.7075 | 0.4934 |
| R9 / F2 | 1,000 | 500 | 1.25s | 77.20% | 0.8119 | 0.5615 | 0.6697 | 0.4834 |
| R9 / F3 | 1,000 | 500 | 1.30s | 76.80% | 0.8047 | 0.5538 | 0.6606 | 0.4768 |
| R10 / F1 | 1,000 | 500 | 1.34s | 81.20% | 0.8638 | 0.6299 | 0.7843 | 0.5263 |
| R10 / F2 | 1,000 | 500 | 1.25s | 75.20% | 0.7995 | 0.5373 | 0.6154 | 0.4768 |
| R10 / F3 | 1,000 | 500 | 1.25s | 77.80% | 0.7955 | 0.5647 | 0.6923 | 0.4768 |
| Mean ± Std | — | — | 1.25s | 77.99% ± 1.59% | 0.820 ± 0.017 | 0.576 ± 0.029 | 0.693 | 0.495 |
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 | nanotabicl Vanilla | Tabular Foundation Model | PyTorch/Python | 78.08% | 0.8205 | 0.5794 | soda-inria/nanotabicl ↗ |
| #2 | Streaming nanotabicl | Tabular Foundation Model | PyTorch/Python | 78.07% | 0.8205 | 0.5792 | soda-inria/nanotabicl ↗ |
| #3 | Full TabICLv2 (PyTorch Reference) | Tabular Foundation Model | PyTorch/Python | 78.07% | 0.8205 | 0.5792 | soda-inria/tabicl ↗ |
| #4 | TabPFN v3 | Tabular Foundation Model | PyTorch/Python | 78.01% | 0.8208 | 0.5797 | PriorLabs/tabpfn ↗ |
| #5 | Carla Engine (TabICLv2 WebGPU) | Tabular Foundation Model | Browser | 77.99% | 0.8200 | 0.5761 | 100% In-Browser |
| #6 | Google TabFM v1.0 | Tabular Foundation Model | PyTorch/Python | 77.97% | 0.8205 | 0.5778 | google-research/tabfm ↗ |
| #7 | EXAONE Tabular | Tabular Foundation Model | PyTorch/Python | 77.94% | 0.8203 | 0.5798 | LGAI-Research/EXAONE-Tabular ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 1,500 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| G | attendedTARGET | CAT | 0 | 2 | — | YesYesNo |
| A | months_as_member | NUM | 0 | 72 | [1, 148] μ=15.6 σ=12.9 | 151813 |
| B | weight | NUM | 20 (1.33%) | 1,241 | [55.41, 170.52] μ=82.6 σ=12.8 | 65.4777.8567.26 |
| C | days_before | NUM | 0 | 19 | [1, 29] μ=8.3 σ=4.1 | 6810 |
| D | day_of_week | CAT | 0 | 7 | — | WedThuFri |
| E | time | CAT | 0 | 2 | — | AMAMAM |
| F | category | CAT | 0 | 6 | — | HIITStrengthCycling |
Frequently Asked Questions: Fitness Club
Common questions regarding the Fitness Club dataset, machine learning task formulations, and in-browser tabular inference.
What is the Fitness Club dataset used for?
The Fitness Club dataset is used for binary classification tasks to predict whether a gym member will attend a booked class session based on membership tenure, weight, booking lead time, and session schedule details.
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 needing Python pipelines or external hosting.
What machine learning models perform best on the Fitness Club dataset?
Gradient boosting algorithms like XGBoost and LightGBM provide strong baseline ROC-AUC performance (~0.77), while tabular foundation models like TabICL and Carla deliver comparable accuracy zero-shot without manual hyperparameter tuning.
Test TabICLv2 on Fitness Club 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
@misc{ddosad2023fitness, author = {Ddosad}, title = {Fitness Club Dataset for ML Classification}, year = {2023}, howpublished = {\url{https://www.kaggle.com/datasets/ddosad/datacamps-data-science-associate-certification}}, note = {Kaggle dataset} }