Temporal metagraph: A new mathematical approach to capture temporal dependencies and interactions between different entities over time
Sergio Iglesias-Perez and
Regino Criado
Chaos, Solitons & Fractals, 2023, vol. 175, issue P1
Abstract:
Predicting real estate prices is a difficult task that requires consideration of various factors and their dynamic interactions over time. In this study, based on the introduction of a new mathematical structure called temporal metagraph, we use a novel approach that exploits the properties of this structure to predict real estate prices in Helsinki by integrating information derived from bicycle trips. The temporal metagraph concept intrinsically captures temporal dependencies and interactions between different entities or agents (nodes of the metagraph), allowing us to model and analyze different real situations and, in particular, the dynamic relationships between bicycle commuting and real estate prices. Our experimental results demonstrate the effectiveness of the proposed approach, as more accurate and reliable predictions are achieved than traditional models, which are based solely on historical price data.
Keywords: Temporal metagraph; Time series; Complex networks; Clustering; Real estate price forecasting (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S096007792300841X
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:175:y:2023:i:p1:s096007792300841x
DOI: 10.1016/j.chaos.2023.113940
Access Statistics for this article
Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros
More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. (repec@elsevier.com).