sale_price_usdOpenML #42092 ↗House Sales
The King County House Sales dataset provides transaction records for 21,613 residential properties sold between May 2014 and May 2015 in Greater Seattle. It serves as a gold-standard benchmark for regression models predicting property market values from structural, geospatial, and neighborhood features.
Business Objective: House Sales
01Business Context
Automated Valuation Models (AVMs) are central to modern mortgage underwriting, real estate brokerage, iBuying platforms, and property tax assessments. In high-velocity urban markets like King County / Seattle, manual property appraisal is cost-prohibitive and slow, creating substantial demand for automated, highly accurate continuous price estimation.
02Analytical Objective
Predict the final residential property sale price (in USD) using 19 structural, temporal, geospatial, and neighborhood characteristics.
03Economic & Decision Impact
Underpricing leads to lost commissions and seller margin erosion, whereas overpricing extends days on market (DOM) and creates mortgage default and liquidity exposure for institutional portfolio buyers. High-accuracy AVMs reduce appraisal turnaround from weeks to seconds and minimize variance in automated loan-to-value (LTV) calculations.
Tabular gradient boosting architectures like LightGBM and XGBoost achieve strong baseline performance (R² ~ 0.88–0.90) by capturing non-linear spatial interactions between latitude, longitude, and King County building grade. In-context foundation models such as TabICL / Carla deliver competitive zero-shot property valuations directly within spreadsheet environments without hyperparameter tuning, significantly lowering the barrier for real estate analysts and underwriters.
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 | sale_price_usdSale Price (USD) | TARGET | NUM | USD | Final realized sale transaction price of the home in US Dollars. |
| B | property_idProperty ID | Feature | NUM | — | Unique administrative parcel identifier assigned to each residential property in King County. |
| C | sale_dateSale Date | Feature | CAT | ISO 8601 string | Timestamp indicating when the property transaction occurred (format: YYYYMMDDT000000). |
| D | bedroom_countBedrooms | Feature | NUM | count | Total count of dedicated bedrooms in the house. |
| E | bathroom_countBathrooms | Feature | NUM | count | Total number of bathrooms, where 0.5 represents a toilet and sink (half bath) and 0.75 represents a shower without a tub. |
| F | living_area_sqftLiving Area (Sq Ft) | Feature | NUM | sq ft | Total interior living space measurement of the home. |
| G | lot_area_sqftLot Size (Sq Ft) | Feature | NUM | sq ft | Total surface area of the land parcel associated with the property. |
| H | floor_countNumber of Floors | Feature | NUM | floors | Total levels or stories in the residential building. |
| I | is_waterfrontWaterfront View | Feature | NUM | binary indicator | Binary indicator representing whether the property borders a waterfront (1 = Yes, 0 = No). |
| J | view_ratingView Rating (0-4) | Feature | NUM | index (0-4) | Qualitative index from 0 to 4 grading how scenic the property's surrounding view is. |
| K | condition_ratingCondition Rating (1-5) | Feature | NUM | index (1-5) | Physical state assessment of the property on an ordinal scale from 1 (poor/uninhabitable) to 5 (excellent). |
| L | construction_gradeKing County Construction Grade (1-13) | Feature | NUM | grade level (1-13) | Official King County grading scale reflecting construction materials, craftsmanship, and architectural design quality (1-3 poor, 7 average, 11-13 luxury/mansion). |
| M | above_ground_sqftAbove Ground Area (Sq Ft) | Feature | NUM | sq ft | Square footage of interior living housing space situated entirely above ground level. |
| N | basement_sqftBasement Area (Sq Ft) | Feature | NUM | sq ft | Square footage of interior living or storage housing space situated below ground level. |
| O | year_builtYear Built | Feature | NUM | year | The calendar year in which the primary building construction was completed. |
| P | year_renovatedYear Renovated | Feature | NUM | year | The calendar year of the most recent major structural restoration or remodel (0 if never renovated). |
| Q | postal_codeZIP Code | Feature | NUM | — | United States Postal Service 5-digit postal routing code representing the local micro-neighborhood. |
| R | latitudeLatitude | Feature | NUM | degrees | Geographic coordinate indicating the north-south position of the parcel. |
| S | longitudeLongitude | Feature | NUM | degrees | Geographic coordinate indicating the east-west position of the parcel. |
| T | nearest_15_living_sqftNearest 15 Neighbors Living Area (Sq Ft) | Feature | NUM | sq ft | Average interior living square footage of the 15 closest neighboring residential properties. |
| U | nearest_15_lot_sqftNearest 15 Neighbors Lot Size (Sq Ft) | Feature | NUM | sq ft | Average land lot square footage of the 15 closest neighboring residential properties. |
Interactive Data Table
Explore rows, feature values, and target labels for House Sales.
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 → | R² Score?Coefficient of determination measuring variance explained by the model.Learn more → | MAE?Mean Absolute Error in original target units, robust to outliers.Learn more → | RMSE?Root Mean Squared Error, penalizing large residual deviations.Learn more → | MAPE?Mean Absolute Percentage Error relative to true target values.Learn more → | RMSLE?Root Mean Squared Logarithmic Error, measuring proportional error scales.Learn more → |
|---|---|---|---|---|---|---|---|---|
| R1 / F1 | 14,408 | 7,205 | 61.09s | 0.9075 | 61,955.13 | 113,519.12 | — | — |
| R1 / F2 | 14,409 | 7,204 | 63.77s | 0.8833 | 62,449.36 | 131,019.24 | — | — |
| R1 / F3 | 14,409 | 7,204 | 63.65s | 0.9137 | 56,209.54 | 100,818.54 | — | — |
| R2 / F1 | 14,408 | 7,205 | 60.91s | 0.9056 | 58,602.19 | 107,041.69 | — | — |
| R2 / F2 | 14,409 | 7,204 | 63.31s | 0.8927 | 60,981.47 | 120,887.38 | — | — |
| R2 / F3 | 14,409 | 7,204 | 63.58s | 0.8978 | 61,009.45 | 122,408.74 | — | — |
| R3 / F1 | 14,408 | 7,205 | 61.21s | 0.8984 | 60,428.37 | 116,400.51 | — | — |
| R3 / F2 | 14,409 | 7,204 | 63.58s | 0.9001 | 60,379.13 | 111,866.66 | — | — |
| R3 / F3 | 14,409 | 7,204 | 63.05s | 0.9030 | 60,627.28 | 118,834 | — | — |
| Mean ± Std | — | — | 62.68s | 0.9002 ± 0.0083 | 60,293.5 | 115,866.2 | — | — |
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 | R² Score?Coefficient of determination (R²) measuring proportion of variance explained.Google ML Guide & Details → | MAE?Mean Absolute Error measuring average prediction error magnitude.Learn more → | RMSE?Root Mean Squared Error penalizing large prediction errors.Learn more → | Reference / Repo |
|---|---|---|---|---|---|---|---|
| #1 | Google TabFM v1.0 | Tabular Foundation Model | PyTorch/Python | 0.9273 | 54,970.9 | 98,886.8 | google-research/tabfm ↗ |
| #2 | EXAONE Tabular | Tabular Foundation Model | PyTorch/Python | 0.9264 | 55,303.3 | 99,519.6 | LGAI-Research/EXAONE-Tabular ↗ |
| #3 | TabPFN v3 | Tabular Foundation Model | PyTorch/Python | 0.9225 | 56,817 | 102,039.4 | PriorLabs/tabpfn ↗ |
| #4 | nanotabicl Vanilla | Tabular Foundation Model | PyTorch/Python | 0.9078 | 58,724.6 | 111,387 | soda-inria/nanotabicl ↗ |
| #5 | Full TabICLv2 (PyTorch Reference) | Tabular Foundation Model | PyTorch/Python | 0.9076 | 58,666.4 | 111,523.7 | soda-inria/tabicl ↗ |
| #6 | Streaming nanotabicl | Tabular Foundation Model | PyTorch/Python | 0.9017 | 59,637.7 | 115,032.2 | soda-inria/nanotabicl ↗ |
| #7 | Carla Engine (TabICLv2 WebGPU) | Tabular Foundation Model | Browser | 0.9002 | 60,293.5 | 115,866.2 | 100% In-Browser |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 21,613 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| A | sale_price_usdTARGET | NUM | 0 | 4,028 | [75000, 7700000] μ=540088.1 σ=367118.7 | 221900538000180000 |
| B | property_id | NUM | 0 | 21,436 | [1000102, 9900000190] μ=4580301520.9 σ=2876499023.4 | 712930052064141001925631500400 |
| C | sale_date | CAT | 0 | 372 | — | 20141013T00000020141209T00000020150225T000000 |
| D | bedroom_count | NUM | 0 | 13 | [0, 33] μ=3.4 σ=0.9 | 332 |
| E | bathroom_count | NUM | 0 | 30 | [0, 8] μ=2.1 σ=0.8 | 12.251 |
| F | living_area_sqft | NUM | 0 | 1,038 | [290, 13540] μ=2079.9 σ=918.4 | 11802570770 |
| G | lot_area_sqft | NUM | 0 | 9,782 | [520, 1651359] μ=15107.0 σ=41419.6 | 5650724210000 |
| H | floor_count | NUM | 0 | 6 | [1, 3.5] μ=1.5 σ=0.5 | 121 |
| I | is_waterfront | NUM | 0 | 2 | [0, 1] μ=0.0 σ=0.1 | 000 |
| J | view_rating | NUM | 0 | 5 | [0, 4] μ=0.2 σ=0.8 | 000 |
| K | condition_rating | NUM | 0 | 5 | [1, 5] μ=3.4 σ=0.7 | 333 |
| L | construction_grade | NUM | 0 | 12 | [1, 13] μ=7.7 σ=1.2 | 776 |
| M | above_ground_sqft | NUM | 0 | 946 | [290, 9410] μ=1788.4 σ=828.1 | 11802170770 |
| N | basement_sqft | NUM | 0 | 306 | [0, 4820] μ=291.5 σ=442.6 | 04000 |
| O | year_built | NUM | 0 | 116 | [1900, 2015] μ=1971.0 σ=29.4 | 195519511933 |
| P | year_renovated | NUM | 0 | 70 | [0, 2015] μ=84.4 σ=401.7 | 019910 |
| Q | postal_code | NUM | 0 | 70 | [98001, 98199] μ=98077.9 σ=53.5 | 981789812598028 |
| R | latitude | NUM | 0 | 5,034 | [47.1559, 47.7776] μ=47.6 σ=0.1 | 47.511247.72100000000000447.7379 |
| S | longitude | NUM | 0 | 752 | [-122.519, -121.315] μ=-122.2 σ=0.1 | -122.257-122.319-122.23299999999999 |
| T | nearest_15_living_sqft | NUM | 0 | 777 | [399, 6210] μ=1986.6 σ=685.4 | 134016902720 |
| U | nearest_15_lot_sqft | NUM | 0 | 8,689 | [651, 871200] μ=12768.5 σ=27303.5 | 565076398062 |
Frequently Asked Questions: House Sales
Common questions regarding the House Sales dataset, machine learning task formulations, and in-browser tabular inference.
What is the King County House Sales dataset used for?
The King County House Sales dataset is a renowned machine learning benchmark used to develop and evaluate Automated Valuation Models (AVMs) and regression algorithms that predict residential home sale prices based on physical attributes, construction quality, and geospatial coordinates.
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, allowing real estate professionals to forecast property values without configuring Python environments or cloud infrastructure.
What machine learning models perform best on the King County House Sales dataset?
Tree-based gradient boosting algorithms (LightGBM, XGBoost, CatBoost) historically achieve the highest accuracy (R² ~ 0.88–0.90) due to their ability to capture non-linear relationships in spatial coordinates and building grades, while modern tabular foundation models like TabICL offer competitive instant zero-shot performance.
What is the difference between sqft_living and sqft_living15?
The column 'sqft_living' measures the specific property's interior living area, whereas 'sqft_living15' represents the average interior living area of the 15 nearest neighboring properties, acting as a spatial smoothing feature.
Test TabICLv2 on House Sales 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 42092