The Building Condition Index (BCI) is a widely adopted quantitative metric for assessing various aspects of a building’s condition, as it facilitates decision-making regarding maintenance, capital improvements and, most importantly, the identification of investment risk. In practice, longitudinal BCI scores are typically used to identify Building Condition Audit maintenance liabilities and trends and proactively provide indications when maintenance strategies need to be altered. This allows for a more efficient resource allocation and helps maximise the lifespan and functionality of buildings and their assets. Given the historical ambiguity concerns because of the reliance on visual inspections, this research investigates how AI and using ANN, DNN and CNN can improve the predictive accuracy of determining a recognisable Building Condition Index. It demonstrates how ANN and DNN perform over asset classes (apartment complexes, education and commercial buildings). The results suggest that DNN architecture is adept at dealing with diverse and complex datasets, thus enabling a more versatile BCI prediction model over various building categories. It is envisaged that with the expansion and maturity of ANN, DNN and CNN, the BCI calculation methodologies will become more sophisticated, automated and integrated with traditional assessment approaches