In this paper an approach for automatic detection of segments where a regression model significantly underperforms and for detecting segments with systematically under- or overestimated prediction is introduced. This segmentational approach is applicable to various expert systems including, but...

To the best knowledge of authors, the use of Random forest as a potential technique for residential estate mass appraisal has been attempted for the first time. In the empirical study using data on residential apartments the method performed better than such techniques as CHAID, CART, KNN,...

Abstract After emerging from the U.S. real estate and financial markets, financial crisis has gradually become global. Due to both primary and secondary mortgage market problems in the U.S. are accepted as the essential reasons of the current crisis, it is believed that financial markets and...

Global financial crisis, arising from real estate and finance sectors, has caused extra ordinary costs for the world economy. Problems in the public management model of the US finance and real estate sectors would be accepted as one of the important reasons of the financial failures in the US...

This paper addresses the issue of data quality in the real estate market. In many countries, the returns indices for direct markets are provided by several sources differing in terms of the methodology adopted and index weights. These differences produce a lack of informative standardization,...

We use new data from a rental brokers' multiple listings service to examine the contractual agreements between landlords and brokers. The data display two sources of variation in the way in which agents are compensated: 1) 69 percent of listings involve exclusive relationships between landlords...

Motivated by a real-life situation, we put forward a model and then derive an optimal strategy that maximizes the expected real-estate selling price when one of the only two remaining buyers has already made an offer but the other one is yet to make. Since the seller is not sure whether the...

Dynamic conditioning is a technique that allows one to formulate correlation models for large baskets without incurring in the curse of dimensionality. The individual price processes for each reference name can be described by a lattice model specified semi-parametrically or even...