Assessing the Rental Value of Residential Properties: An Abductive Learning Networks Approach

This paper attempts to estimate rental value of residential properties using Abductive Learning Networks (ALN), and artificial intelligence technique. The results indicate that the ALN model provides an accurate estimation of rents with only seven input variables, while other multivariate statistical techniques do not. The ALN model automatically selects the best network structure, node types and coefficients, and therefore it simplifies the maintenance of the model. Once the final model is synthesized, the ALN model becomes very compact, rapidly executable and cost-effective.