Forecasting Rental Values of Residential Properties: A Neural Network Model Approach

Oshodi, Olalekan Shamsideen; Ohiomah, Ifije; Odubiyi, Tawakalitu Bisola; Aigbavboa, Clinton; Thwala, Wellington Didibhuku

doi:10.1007/978-3-030-48465-1_52

Cited by 2 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

“…As compared to house price forecasting, research on rental price forecasting through machine learning (e.g. Clark and Lomax, 2018;Embaye et al, 2021;Hu et al, 2019;Li, 2018;Li and Li, 1996;Ma et al, 2018;Ma and Liu, 2019;Ming et al, 2020;Odubiyi et al, 2019;Oshodi et al, 2020Oshodi et al, , 2021Oyedeji Joseph et al, 2018;Oyedeji and Oyewale, 2018;Rafatirad, 2017;Tsai and Pan, 2014;Wang and Cao, 2019;Zhang et al, 2019) seems relatively scare. Hu et al (2019) explore the random forest, extra-trees, gradient-boosting, support vector, multi-layer perceptron neural network and k-nearest neighbor when building housing rent prediction models for Shenzhen in China in October 2017 and February 2018 and find that all of these algorithms, except for the support vector, generally present good performance with the random forest and extra-trees being the leaders.…”

Section: Introductionmentioning

confidence: 99%

“…Ma and Liu (2019) utilize integrated learning constituted of the random forest, extra trees and light gradient boosting to improve performance from a single model for house rental price forecasting. Oshodi et al (2021) apply the neural network to forecast rental values of residential properties in Cape Town, South Africa, and obtain accuracy of 66.67%. Ming et al (2020) compare the random forest, light gradient boosting and XGBoost for forecasting rental prices in Chengdu and find the XGBoost optima with accuracy of 85%.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Rent index forecasting through neural networks

Zhang

2021

JES

View full text Add to dashboard Cite

PurposeChinese housing market has been growing fast during the past decade, and price-related forecasting has turned to be an important issue to various market participants, including the people, investors and policy makers. Here, the authors approach this issue by researching neural networks for rent index forecasting from 10 major cities for March 2012 to May 2020. The authors aim at building simple and accurate neural networks to contribute to pure technical forecasting of the Chinese rental housing market.Design/methodology/approachTo facilitate the analysis, the authors examine different model settings over the algorithm, delay, hidden neuron and data spitting ratio.FindingsThe authors reach a rather simple neural network with six delays and two hidden neurons, which leads to stable performance of 1.4% average relative root mean square error across the ten cities for the training, validation and testing phases.Originality/valueThe results might be used on a standalone basis or combined with fundamental forecasting to form perspectives of rent price trends and conduct policy analysis.

show abstract