A Comparison of Regression and Artificial Intelligence Methods in a Mass Appraisal Context

Article excerpt

A b s t r a c t

This paper describes a comparative study where several regression and artificial intelligence (AI)-based methods are used to assess properties in Louisville, Kentucky. Four regressionbased methods [traditional multiple regression analysis (MRA), and three non-traditional regression-based methods, Support Vector Machines using sequential minimal optimization regression (SVM-SMO), additive regression, and M5P trees], and three AI-based methods [neural networks (NNs), radial basis function neural network (RBFNN), and memory-based reasoning (MBR)] are applied and compared under various simulation scenarios. The results indicate that non-traditional regressionbased methods perform better in all simulation scenarios, especially with homogeneous data sets. AI-based methods perform well with less homogeneous data sets under some simulation scenarios.

The need for unbiased, objective, systematic assessment of real property has always been important, and never more so than now. Misleading prices for socalled level-three assets, defined as those classified as hard to value and hard to sell, have reduced confidence in balance sheets of financial institutions. Lenders need assurance that they have recourse to actual value in the event of default. Investors in large pools of asset-backed securities must have the comfort of knowing that, while they cannot personally examine each asset, those assets have been valued reliably. As always, valuations determined for real property have significant tax implications for current and new owners and must be substantiated in the courtroom in extreme cases. Annual property tax at the local level, as well as the occasional levy of estate and gift tax at the federal and state levels, is a function of the assessed value. Furthermore, the dissolution of a business or a marriage and the accompanying distribution of assets to creditors and owners require a fair appraisal of any real property.

In the United States, county/municipal tax assessors perform more appraisals than any other profession. Customarily they rely on a program known as Computer Assisted Mass Appraisal (CAMA). This affords them defense against accusations of subjectivity. Assessed values, initially based on sales price, are normally required by local law to be revised periodically with new data about more recent sales in the neighborhood. Conscientious assessors evaluate the quality of their operations by analyzing the degree to which their system's assessed values approximate actual sales prices.

The traditional approach to mass assessment has been based on multiple regression analysis (MRA) methods (Mark and Goldberg, 1988). MRA-based methods have been popular because of their established methodology, long history of application, and wide acceptance among both practitioners and academicians. The limitations of traditional linear MRA for assessing the value of real estate have been recognized for some time (Mark and Goldberg, 1988; Do and Grudnitski, 1992). These limitations result from common problems associated with MRA-based methods, such as the inability of MRA to adequately deal with interactions among variables, nonlinearity, and multicollinearity (Larsen and Peterson, 1988; Mark and Goldberg, 1988; Limsombunchai, Gan, and Lee, 2004). More recently artificial intelligence (AI)-based methods have been proposed as an alternative for mass assessment (Do and Grudnitski, 1992; Worzala, Lenk, and Silva, 1995; Guan and Levitan, 1997; McGreal, Adair, McBurney, and Patterson, 1998; Krol, Lasota, Nalepa, and Trawinski, 2007; Taffese, 2007; Guan, Zurada, and Levitan, 2008; Peterson and Flanagan, 2009).

The results from these studies have so far been mixed. While some studies show improvement in assessment using AI-based methods (Do and Grudnitski, 1992; Peterson and Flanagan, 2009), others find no improvement (Limsombunchai, Gan, and Lee, 2004; Guan, Zurada, and Levitan, 2008). A few studies even find neural networks (NN)-based methods to be inferior to traditional regression methods (Worzala, Lenk, and Silva, 1995; Rossini, 1997; McGreal, Adair, McBurney, and Patterson, 1998). …