Bidgely UtilityAI Pro™ SaaS Demo Dataset

## **Description**

The **UtilityAI Pro™ SaaS Demo** dataset provides sample, non-production data designed to demonstrate Bidgely’s behind-the-meter analytics. It includes a representative subset of appliance-level load insights, customer attributes, and model-generated intelligence produced by the UtilityAI Pro SaaS platform.

This sample dataset mirrors the schema, field formats, and data organization of the production dataset. All records are synthetic or fictitious and are provided solely for demonstration and testing. Utilities, analysts, and developers can use this dataset to explore how Bidgely’s appliance-level disaggregation and customer intelligence can support segmentation, DSM program analysis, DER planning, and grid analytics.

<p><br/></p>

<p><br/></p>

## **What This Dataset Includes**

The UtilityAI Pro™ SaaS Demo provides representative fields from core Bidgely analytical model groups:

- **Appliance & DER Disaggregation** – Estimated hourly appliance-level consumption such as EV charging, HVAC, water heating, pool pumps, and behind-the-meter solar.<br/><br/>
- **Appliance & DER Attributes** – Presence and operational behavior indicators for common appliances and DER assets.<br/><br/>
- **Appliance Inefficiency Indicators** – Signals highlighting abnormal or inefficient usage patterns.<br/><br/>
- **Customer Lifestyle Features** – Derived patterns related to occupancy, daily routines, and seasonal behavior.<br/><br/>
- **Program Propensity Scores** – Likelihood estimates for EV rate adoption, TOU enrollment, DR participation, efficiency programs, and electrification opportunities.<br/><br/>

These representative fields align with the data structures used in the full UtilityAI Pro SaaS dataset and support testing and validation of analytics workflows.<br/><br/>This demo dataset can be used to explore:

- Customer segmentation for DSM, electrification, or rate design<br/><br/>
- Identifying EV ownership, HVAC load signatures, and other DER-related behaviors<br/><br/>
- Appliance-level load analysis for distribution planning and grid studies<br/><br/>
- Exploring drivers of peak load, electrification impacts, and load-shifting opportunities<br/><br/>
- Testing data pipelines, dashboards, machine-learning models, and BI workflows<br/><br/>
- Prototyping analytical logic for program design or grid forecasting<br/><br/>

The dataset provides a secure, non-production environment for experimentation and development.

<p><br/></p>