Results of machine learning models on Ca-Land.

<div><p>In the context of global economic austerity in the post epidemic era, housing, as one of the basic human needs, has become particularly important for accurate prediction of house prices. BP neural network is widely used in prediction tasks, but their performance is easily affecte...

Full description

Saved in:
Bibliographic Details
Main Author: Yulin Li (36434) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852016519104430080
author Yulin Li (36434)
author_facet Yulin Li (36434)
author_role author
dc.creator.none.fl_str_mv Yulin Li (36434)
dc.date.none.fl_str_mv 2025-09-17T17:38:40Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0332439.g017
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Results_of_machine_learning_models_on_Ca-Land_/30151622
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
thus metaheuristic algorithms
swarm intelligence algorithms
reduced population diversity
post epidemic era
local optimal solutions
indicators fully proves
global economic austerity
five evaluation metrics
fitness allocation strategy
elite evolution mechanism
cauchy variation strategy
become particularly important
basic human needs
66 %, 18
27 %, 28
10 %, 49
bp neural network
bpnn improved 17
network parameters
xlink ">
widely used
turn results
slow convergence
results show
prediction tasks
paper proposes
optimization tasks
house prices
four datasets
first compared
easily affected
accurate prediction
dc.title.none.fl_str_mv Results of machine learning models on Ca-Land.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>In the context of global economic austerity in the post epidemic era, housing, as one of the basic human needs, has become particularly important for accurate prediction of house prices. BP neural network is widely used in prediction tasks, but their performance is easily affected by weights and biases, and thus metaheuristic algorithms are needed to optimize the network parameters. Firstly, to address the shortcomings of the artificial Gorilla Troops Optimizer (GTO) in such optimization tasks, such as reduced population diversity, easy to fall into local optimal solutions and slow convergence, this paper proposes a fitness allocation strategy, a Cauchy variation strategy, and an elite evolution mechanism to improve the algorithm, which in turn results in an improved artificial Gorilla Troops Optimizer (IGTO). Subsequently, a BP neural network house price prediction model based on IGTO is constructed and experiments are conducted on four datasets, namely, Boston, California-Bay, California-Land and Taiwan. The experiments are first compared with eleven other swarm intelligence algorithms and then with four machine learning models, and the results show that IGTO-BPNN improved 17.66%, 18.27%, 28.10%, 49.35% and 24.83% on five evaluation metrics, namely, MAE, MAPE, R2, RMSE, and SMAPE, respectively. The improvement of these indicators fully proves the superiority and effectiveness of IGTO-BPNN in house price prediction.</p></div>
eu_rights_str_mv openAccess
id Manara_a8317e1caca0236dedf2f8ca2e869fed
identifier_str_mv 10.1371/journal.pone.0332439.g017
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30151622
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Results of machine learning models on Ca-Land.Yulin Li (36434)Biological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedthus metaheuristic algorithmsswarm intelligence algorithmsreduced population diversitypost epidemic eralocal optimal solutionsindicators fully provesglobal economic austerityfive evaluation metricsfitness allocation strategyelite evolution mechanismcauchy variation strategybecome particularly importantbasic human needs66 %, 1827 %, 2810 %, 49bp neural networkbpnn improved 17network parametersxlink ">widely usedturn resultsslow convergenceresults showprediction taskspaper proposesoptimization taskshouse pricesfour datasetsfirst comparedeasily affectedaccurate prediction<div><p>In the context of global economic austerity in the post epidemic era, housing, as one of the basic human needs, has become particularly important for accurate prediction of house prices. BP neural network is widely used in prediction tasks, but their performance is easily affected by weights and biases, and thus metaheuristic algorithms are needed to optimize the network parameters. Firstly, to address the shortcomings of the artificial Gorilla Troops Optimizer (GTO) in such optimization tasks, such as reduced population diversity, easy to fall into local optimal solutions and slow convergence, this paper proposes a fitness allocation strategy, a Cauchy variation strategy, and an elite evolution mechanism to improve the algorithm, which in turn results in an improved artificial Gorilla Troops Optimizer (IGTO). Subsequently, a BP neural network house price prediction model based on IGTO is constructed and experiments are conducted on four datasets, namely, Boston, California-Bay, California-Land and Taiwan. The experiments are first compared with eleven other swarm intelligence algorithms and then with four machine learning models, and the results show that IGTO-BPNN improved 17.66%, 18.27%, 28.10%, 49.35% and 24.83% on five evaluation metrics, namely, MAE, MAPE, R2, RMSE, and SMAPE, respectively. The improvement of these indicators fully proves the superiority and effectiveness of IGTO-BPNN in house price prediction.</p></div>2025-09-17T17:38:40ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0332439.g017https://figshare.com/articles/figure/Results_of_machine_learning_models_on_Ca-Land_/30151622CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301516222025-09-17T17:38:40Z
spellingShingle Results of machine learning models on Ca-Land.
Yulin Li (36434)
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
thus metaheuristic algorithms
swarm intelligence algorithms
reduced population diversity
post epidemic era
local optimal solutions
indicators fully proves
global economic austerity
five evaluation metrics
fitness allocation strategy
elite evolution mechanism
cauchy variation strategy
become particularly important
basic human needs
66 %, 18
27 %, 28
10 %, 49
bp neural network
bpnn improved 17
network parameters
xlink ">
widely used
turn results
slow convergence
results show
prediction tasks
paper proposes
optimization tasks
house prices
four datasets
first compared
easily affected
accurate prediction
status_str publishedVersion
title Results of machine learning models on Ca-Land.
title_full Results of machine learning models on Ca-Land.
title_fullStr Results of machine learning models on Ca-Land.
title_full_unstemmed Results of machine learning models on Ca-Land.
title_short Results of machine learning models on Ca-Land.
title_sort Results of machine learning models on Ca-Land.
topic Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
thus metaheuristic algorithms
swarm intelligence algorithms
reduced population diversity
post epidemic era
local optimal solutions
indicators fully proves
global economic austerity
five evaluation metrics
fitness allocation strategy
elite evolution mechanism
cauchy variation strategy
become particularly important
basic human needs
66 %, 18
27 %, 28
10 %, 49
bp neural network
bpnn improved 17
network parameters
xlink ">
widely used
turn results
slow convergence
results show
prediction tasks
paper proposes
optimization tasks
house prices
four datasets
first compared
easily affected
accurate prediction