RapidRate^TM is a tool developed by CSIRO, using Artificial Intelligence techniques, that can quickly estimate the energy efficiency of a dwelling using a relatively small number of inputs.

RapidRate^TM Thermal assesses the thermal shell of a dwelling and generates an estimated Star Rating, heating energy, and cooling energy. Inputs include: postcode, dwelling type (house or apartment); floor area; external wall area by orientation; window area by orientation (including area double glazed); and main wall, floor, and roof materials (including insulation).

RapidRate^TM Whole of Home, in addition to the thermal outputs, estimates energy consumption (for heating, cooling, hot water, lights, cooking, plug in appliances, and pools), solar energy generation, and carbon emissions. Additional inputs include major appliance types.

Whilst RapidRate^TM attempts to align with the Nationwide House Energy Rating Scheme (NatHERS), RapidRate^TM is not an official NatHERS accredited tool. Outputs cannot be directly compared as underlying assumptions and calculations are not identical.

Find out more about the AI model that sits behind RapidRate^TM Thermal here.

Find out how well your home rates by using the RapidRate^TM Thermal Calculator or the RapidRate^TM Whole of Home Calculator.

An Application Programming Interface (API) enables connection of RapidRate^TM to any user interface or application. The RapidRate^TM API can be used to assess large numbers of dwellings at a time, with inputs submitted via a csv file.

RapidRate^TM background

RapidRate background

RapidRate^TM model accuracy

RapidRate^TM development commenced in 2020 and has been an iterative process. RapidRate^TM will continue to grow and evolve over time. The accuracy of the RapidRate^TM model is influenced by several factors including the training data used, and the machine learning techniques used.

The current training data comes from the CSIRO NatHERS certificate database. This contains data for Australian dwellings built since June 2016. This means that the RapidRate^TM model may not yet be fully representative of all Australian housing.

Some of the training data is used to train the model, and some is used to evaluate the model. Evaluation results reflect the ability of RapidRate^TM to rate dwellings represented by the training data.

There are two ways in which the accuracy of the RapidRate^TM model is described.

1. Prediction interval gives an idea of accuracy at an individual dwelling level

When a rating for an individual dwelling is conducted, point estimates for star rating, heating energy, and cooling energy are returned. In addition to this, prediction intervals for each measure are returned. For example, a dwelling may rate at 3.4 stars with 90% confidence that the value is between 2.9 and 3.9 stars.

2. Accuracy measures give an idea of accuracy of the model overall

A variety of measures are used to assess the accuracy of the RapidRate^TM model.

Fig. 1 shows predicted star ratings against actual star ratings using the evaluation training data.

RapidRate model summary measures:

• R² (test): 0.80
• Root Mean Square Error (test): 0.46 stars
• Mean Absolute Error (test): 0.31 stars
• Median Absolute Error (test): 0.2 stars

The accuracy of the RapidRate^TM model varies for different sub-segments of dwellings. This is generally due to the amount of training data available. Further analysis of the accuracy of the RapidRate^TM model is available here.

Working with Cotality

CSIRO are collaborating with property data analytics company Cotality to trial the use of RapidRate^TM. See here for more information.