Sample-data demonstration
This shows our AI testing process on public sample data. You can't upload your own data here.
From YourCloudGroup Model Manager.

Question: What a property will sell for
Sample data: Real Estate Valuation (UCI)
Attribution: Yeh, I. (2018). Real Estate Valuation [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5J30W. CC BY 4.0. Modified: split into training and held-out rows, predictions added.
Predicts: house price of unit area (Regression)

Result
Its predictive value is STRONG, measured on held-out rows that took no part in choosing it.
Certification: CERTIFIED — AUDITABLE & REPEATABLE PREDICTIVE MODEL
Value verified: yes. The winning model demonstrated strong predictive value over the baseline on holdout rows that took no part in choosing it.
Winner: Random Forest, best of 12 models built
Trained on: 311 rows

Certificate figures: the holdout half of the blind rows, 52 rows that took no part in choosing the winner
Error reduction: 55.3% (90% range 43.2-66.2%)
Mean absolute error: 5.783 vs 12.95 for the baseline
Baseline: always predict the training median (38.1)

Compare figures: all 103 blind rows, including the half the winner was chosen on
R2: 0.6583
MAE / RMSE: 4.96 / 9.21
Within 10%: 53 of 103

The predictions file
103 held-out rows, one per line: heldout_row, X1 transaction date, X2 house age, X3 distance to the nearest MRT station, X4 number of convenience stores, actual_Y house price of unit area, predicted_Y house price of unit area.
heldout_row numbers the held-out rows 1 to N in the order the product tested them. It is not a row number from the original dataset: the split shuffled the rows.
Columns left out of this download: X5 latitude, X6 longitude.

Run: model acd485e2-1dc1-4b78-bb11-423cdb484892, tournament real_estate_valuation_20261028-210037, completed 2026-10-28T21:02:50Z
Dataset file sha256: e0074220e235164e8fe010e055a94a4aed8bf484e0e33d7f8efc65e1b6a48b5e