Testing machine learning systems in real estate

Autonomous Systems Research Real-Time Machine Learning

Robots are required to learn and generalise about the world around while interacting with their immediate environment and thus reduce the training time. Despite the processing power limitations, the problems of real-time learning can be addressed using optimisation techniques. Fundamentals of one such technique, namely, reinforcement learning, are described in this report. By the end of the fie...

Testing for Information Asymmetries in Real Estate Markets

In housing markets, neighborhood characteristics are a key source of information heterogeneity: sellers are usually better informed about neighborhood values than buyers are, but some sellers and buyers are better informed than their peers are. Consistent with predictions from a new framework for analyzing such markets with heterogeneous assets and differentially informed agents, we find that c...

Urban Data Streams and Machine Learning: A Case of Swiss Real Estate Market

In this paper, we show how using publicly available data streams and machine learning algorithms one can develop practical data driven services with no input from domain experts as a form of prior knowledge. We report the initial steps toward development of a real estate portal in Switzerland. Based on continuous web crawling of publicly available real estate advertisements and using building d...

Bubbles in Real Estate Markets

Essays in Real Estate Appraisal

This is an academic dissertation submitted in partial fulfilment of the requirements for the degree of Doctor of Technology. The dissertation consists of a short summary and discussion of seven enclosed essays. All seven papers are devoted to central issues within real estate appraisal and valuation, with emphasis on the market for income property. Essay I analyses the market prices for mixed-u...