Making Use of Data for Improved Decision-making in the Housing Market - An Action Design Research Study
No Thumbnail Available
URL
Journal Title
Journal ISSN
Volume Title
School of Business |
Master's thesis
Authors
Date
2020
Department
Major/Subject
Mcode
Degree programme
Information and Service Management (ISM)
Language
en
Pages
50 + 8
Series
Abstract
This paper describes the process and findings of an Action Design Research study into the development of a user interface. The interface is developed for a machine learning model that estimates and predicts housing prices in the Finnish residential real estate market. The aim of this research is to gain insight into what kind of variables different stakeholders, such as banks, realtors and construction companies, employ in their decision-making processes regarding housing pricing. Firstly, this is to provide the owner of the machine learning model with a vision of how the model should be productized and marketed to prospective customers. Secondly, while there is abundant research on housing price determinants, a research gap is identified in how different stakeholders evaluate and implement these determinants in their respective pricing processes. As part of this research, the different potential user groups of this interface are identified and their informational needs are mapped out through interviews. Following the four stages of ADR - problem identification, building, intervention and evaluation, reflection and learning, and finally, formalization of learning – the researcher formulates an ensemble artifact that is the final interface concept. In addition to the business value of the findings, the researcher formulates design principles that can be applied to a class of similar problems in user interface design. This study contributes to the knowledge on housing price attributes and user interface design.Description
Thesis advisor
Tuunainen, VirpiKeywords
cost of housing, machine learning, ADR, user interface design, housing market, Finland