This document explains how to use the XGBoost Based Imputation pretrained model available on ArcGIS Living Atlas of the World. The model is used to fill in missing numeric values in feature and tabular datasets.
Data discontinuities and missing attribute values regularly interrupt GIS workflows, creating inconsistencies in analysis results and limiting downstream modeling reliability. Applying robust imputation methods helps minimize these gaps and maintain the integrity of spatial models. The XGBoost Based Imputation model is built upon the eXtreme Gradient Boosting (XGBoost) framework. Unlike traditional imputation that treats missing data as a statistical problem, this model treats it as a dynamic supervised learning problem. It uses an ensemble of decision trees to build a robust, high-performance predictor that can accurately reconstruct missing numeric values in complex, multivariate datasets.
The model performs predictive imputation by using records with observed values in the target fields for training. The remaining fields serve as predictor variables for the target field, allowing the trained model to predict missing values for records where the target field is null.
Model details
This model has the following characteristics:
- Input—Use a feature class or stand-alone table containing missing values in one or more fields.
- Output—The model returns a feature class or stand-alone table with missing values filled in the selected fields using model predictions.
- Compute—This model runs efficiently on CPU, and it also supports GPU computation for massive datasets. It uses GPU by default; it works on CPU if unavailable.
- Applicable geographies—The model is expected to work globally.
- Architecture—The XGBoost model is an ensemble framework building sequential, regularized decision trees that iteratively correct previous prediction errors.
Access and download the model
Download the XGBoost Based Imputation pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro in the Predict Missing Values Using AI Model tool.
- Browse to ArcGIS Living Atlas of the World.
- Sign in with your ArcGIS Online credentials.
- Search for XGBoost Based Imputation and open the item page from the search results.
- Click the Download button to download the model.
You can use the downloaded .dlpk file directly in ArcGIS Pro.
Release notes
The following are the release notes:
| Date | Description |
|---|---|
| May 2026 |
First release of the XGBoost Based Imputation model |