Search results

This study aims to investigate the spatial distribution of housing prices and identify the affecting factors (independent variable) on the cost of residential units (dependent variable).

The method of the present study is descriptive-analytical and has an applied purpose. The used statistical population in this study is the residential units’ price in Tehran in 2021. For this purpose, the average per square meter of residential units in the city neighborhoods was entered in the geographical information system. Two techniques of ordinary least squares regression and geographically weighted regression have been used to analyze housing prices and modeling. Then, the results of the ordinary least squares regression and geographically weighted regression models were compared by using the housing price interpolation map predicted in each model and the accurate housing price interpolation map.

Based on the results, the ordinary least squares regression model has poorly modeled housing prices in the study area. The results of the geographically weighted regression model show that the variables (access rate to sports fields, distance from gas station and water station) have a direct and significant effect. Still, the variable (distance from fault) has a non-significant impact on increasing housing prices at a city level. In addition, to identify the affecting variables of housing prices, the results confirm the desirability of the geographically weighted regression technique in terms of accuracy compared to the ordinary least squares regression technique in explaining housing prices. The results of this study indicate that the housing prices in Tehran are affected by the access level to urban services and facilities.

Identifying factors affecting housing prices helps create sustainable housing in Tehran. Building sustainable housing represents spending less energy during the construction process together with the utilization phase, which ultimately provides housing at an acceptable price for all income deciles. In housing construction, the more you consider the sustainable housing principles, the more sustainable housing you provide and you take a step toward sustainable development. Therefore, sustainable housing is an important planning factor for local authorities and developers. As a result, it is necessary to institutionalize an integrated vision based on the concepts of sustainable development in the field of housing in the Tehran metropolis.

The current estimation practice in construction projects greatly needs upgrading, as there has been no improvement in the cost overrun issue over the past 70 years. The purpose of this research was to develop a new multiple regression analysis (MRA)-based model to forecast the final cost of road projects at the pre-design stage using data from 43 projects in New Zealand (NZ).

The research used the case study of 43 completed road projects in NZ. Document analysis was conducted to collect data, and statistical tests were used for model development and analysis.

Eight models were developed, and all models achieved the required F statistics and met the regression assumptions. The models’ mean absolute percentage error (MAPE) was between 21.25% and 22.77%. The model with the lowest MAPE comprised the road length and width, number of bridges, pavement area, cut and fill area, preliminary cost and cost indices change.

The model is based on road projects in NZ. However, it was designed to be able to adapt to other contexts. The findings suggest that the model can be used to improve traditional conceptual estimating methods. Past project data is often stored by the project team but rarely used for analysing and forecasting purposes. This research emphasises that past data can be effectively used to predict the project cost at the pre-design stage with limited information.

No research was conducted to adopt cost modelling techniques into the conceptual estimation practice in the NZ construction industry.

The purpose of this study is to make property price forecasts for the Chinese housing market that has grown rapidly in the last 10 years, which is an important concern for both government and investors.

This study examines Gaussian process regressions with different kernels and basis functions for monthly pre-owned housing price index estimates for ten major Chinese cities from March 2012 to May 2020. The authors do this by using Bayesian optimizations and cross-validation.

The ten price indices from June 2019 to May 2020 are accurately predicted out-of-sample by the established models, which have relative root mean square errors ranging from 0.0458% to 0.3035% and correlation coefficients ranging from 93.9160% to 99.9653%.

The results might be applied separately or in conjunction with other forecasts to develop hypotheses regarding the patterns in the pre-owned residential real estate price index and conduct further policy research.

Prediction models are essential tools for transportation agencies to forecast the condition of bridge decks based on available data, and artificial intelligence is paramount for this purpose. This study aims at proposing a bridge deck condition prediction model by assessing various classification and regression algorithms.

The 2019 National Bridge Inventory database is considered for model development. Eight different feature selection techniques, along with their mean and frequency, are used to identify the critical features influencing deck condition ratings. Thereafter, four regression and four classification algorithms are applied to predict condition ratings based on the selected features, and their performances are evaluated and compared with respect to the mean absolute error (MAE).

Classification algorithms outperform regression algorithms in predicting deck condition ratings. Due to its minimal MAE (0.369), the random forest classifier with eleven features is recommended as the preferred condition prediction model. The identified dominant features are superstructure condition, age, structural evaluation, substructure condition, inventory rating, maximum span length, deck area, average daily traffic, operating rating, deck width, and the number of spans.

The proposed bridge deck condition prediction model offers a valuable tool for transportation agencies to plan maintenance and resource allocation efficiently, ultimately improving bridge safety and serviceability.

This study provides a detailed framework for applying machine learning in bridge condition prediction that applies to any bridge inventory database. Moreover, it uses a comprehensive dataset encompassing an entire region, broadening the model’s applicability and representation.

The construction projects are highly subjected to uncertainties, which result in overruns in time and cost. Realistic estimates of workforce and duration are imperative for construction projects to attain their intended objectives. The aim of this study is to provide accurate labor and duration estimates for the construction projects, considering actual uncertainties.

The dataset was formulated from the information collected from 186 construction projects through direct interviews, group discussions and questionnaire methods. The actual uncertainties and exposure conditions of construction activities were recorded. The data were verified with the standard guideline to remove the outliers. The prediction model was developed using support vector regression (SVR), a machine learning (ML) method. The performance was evaluated using the widely adopted regression metrics. Further, the cross validation was made with the visualization of residuals and predicted errors, ridge regression with transformed target distribution and a Gaussian Naive Bayes (NB) regressor.

The prediction models predicted the duration and labor requirements with the consideration of actual uncertainties. The residual plot indicated the appropriate use of SVR to develop the prediction model. The duration (DC) and resource constraint (RC) prediction models obtained 80 and 82% accuracy, respectively. Besides, the developed model obtained better accuracy for the training and test scores than the Gaussian NB regressor. Further, the range of the explained variance score and R² was from 0.95 to 0.97, indicating better efficiency compared with other prediction models.

The researchers will utilize the research findings to estimate the duration and labor requirements under uncertain conditions and further improve the construction project management practices.

The research findings will enable industry practitioners to accurately estimate the duration and labor requirements, considering historical uncertain conditions. A precise estimation of resources will ensure the attainment of the intended project outcomes.

Delays in construction projects will be reduced by implementing the research findings, which significantly ensures the effective utilization of resources and attainment of other economic benefits. The policymakers will develop a guideline to develop a database to collect the uncertainties of the construction projects and relatively estimate the resource requirements.

This is the first study to consider the actual uncertainties of construction projects to develop RC and DC prediction models. The developed prediction models accurately estimate the duration and labor requirements with minimal computational time. The industry practitioners will be able to accurately estimate the duration and labor requirements using the developed models.

Given the growing emphasis among scholars, practitioners and policymakers on financial sustainability, this study aims to explore the applicability of machine learning techniques in predicting the financial performance of microfinance institutions (MFIs).

This study gathered 9,059 firm-year observations spanning from 2003 to 2018 from the World Bank's Mix Market database. To predict the financial performance of MFIs, the authors applied a range of machine learning regression approaches to both training and testing data sets. These included linear regression, partial least squares, linear regression with stepwise selection, elastic net, random forest, quantile random forest, Bayesian ridge regression, K-Nearest Neighbors and support vector regression. All models were implemented using Python.

The findings revealed the random forest model as the most suitable choice, outperforming the other models considered. The effectiveness of the random forest model varied depending on specific scenarios, particularly the balance between training and testing data set proportions. More importantly, the results identified operational self-sufficiency as the most critical factor influencing the financial performance of MFIs.

This study leveraged machine learning on a well-defined data set to identify the factors predicting the financial performance of MFIs. These insights offer valuable guidance for MFIs aiming to predict their long-term financial sustainability. Investors and donors can also use these findings to make informed decisions when selecting their potential recipients. Furthermore, practitioners and policymakers can use these findings to identify potential financial performance vulnerabilities.

This study stands out by using a global data set to investigate the best model for predicting the financial performance of MFIs, a relatively scarce subject in the existing microfinance literature. Moreover, it uses advanced machine learning techniques to gain a deeper understanding of the factors affecting the financial performance of MFIs.

Network coverage is crucial for the adoption of advanced Smart Home applications. The commonly used log-based path loss model is not able to accurately estimate WiFi signal strength in different houses, as it does not fully consider the impact of building morphology. To better describe the propagation of WiFi signals and achieve higher estimation accuracy, this paper studies the basic building morphology characteristics of houses.

A new path loss model based on a decision tree was proposed after measuring the WiFi signal strength passing through multiple housing units. Three types of regression models were tested and compared.

The findings demonstrate that the log-based path loss model fits small houses well, while the newly proposed nonlinear path loss model performs better in large houses (area larger than 125 m2 and area-to-perimeter ratio larger than 2.5). The impact of building design on path loss has been proven and specifically quantified in the model.

Proposed an improved model to estimate indoor network coverage. Quantify the impacts of building morphology on indoor WiFi signal strength. Improve WiFi signal strength estimation to support Smart Home applications.

This paper aims to compare the efficiency of spatial and nonspatial hedonic price models in capturing housing submarkets dynamics for cities in developing countries. This study expects to contribute to a better understanding of the housing price determinants from both nonspatial and spatial perspectives. In addition, this paper fills a gap in the literature on the study of housing prices from a spatial perspective in Latin American cities.

This study uses a comparative analysis between an ordinary least squares regression and a geographical weighted regression, GWR. The study also assesses the performance of two distinct data sources: the city’s cadastral records and a real estate sales web portal.

The results suggest that compared to the traditional regression model, the spatial regression models are more effective at capturing housing market variations on a fine scale. Moreover, they reveal interesting findings on the spatial varying, sometimes contradictory effects of some housing attributes on housing prices in different areas of the city, suggesting the potential impact from segregation.

The availability of data on housing prices and characteristics in Latin American cities is fragmented and complex. The level of detail, granularity and coverage is not consistent over time. For this reason, this study combines and compares data sets from official and unofficial sources in an effort to close this gap. Likewise, the socioeconomic variables that come from the census must be carefully analyzed, knowing the historical context in which they were constructed, what they represent and their interpretation.

This paper suggests that despite the improvement on the spatial models, the selection of a specific one should always be based on the diagnosis of it as it highly depends on the data used and the objectives of the study.

This study enriches the limited body of literature on spatial hedonic price models of housing in Latin American cities. It also shed light on the importance of spatial approaches to identify complex housing submarkets.

The COVID-19 pandemic, a sudden and disruptive external shock to the USA and global economy, profoundly affected various operations. Thus, it becomes imperative to investigate the repercussions of this pandemic on the US housing market. This study investigates the impact of the COVID-19 pandemic on a crucial facet of the real estate market: the Time on the Market (TOM). Therefore, this study aims to ascertain the net effect of this unprecedented event after controlling for economic influences and real estate market variations.

Monthly time series data were collected for the period of January 2010 through December 2022 for statistical analysis. Given the temporal nature of the data, we conducted the Durbin–Watson test on the OLS residuals to ascertain the presence of autocorrelation. Subsequently, we used the generalized regression model to mitigate any identified issues of autocorrelation. However, it is important to note that the response variable derived from count data (specifically, the median number of months), which may not conform to the normality assumption associated with standard regression models. To better accommodate this, we opted to use Poisson regression as an alternative approach. Additionally, recognizing the possibility of overdispersion in the count data, we also explored the application of the negative binomial model as a means to address this concern, if present.

This study’s findings offer an insightful perspective on the housing market’s resilience in the face of COVID-19 external shock, aligning with previous research outcomes. Although TOM showed a decrease of around 10 days with standard regression and 27% with Poisson regression during the COVID-19 pandemic, it is noteworthy that this reduction lacked statistical significance in both models. As such, the impact of COVID-19 on TOM, and consequently on the housing market, appears less dramatic than initially anticipated.

This research deepens our understanding of the complex lead–lag relationships between key factors, ultimately facilitating an early indication of housing price movements. It extends the existing literature by scrutinizing the impact of the COVID-19 pandemic on the TOM. From a pragmatic viewpoint, this research carries valuable implications for real estate professionals and policymakers. It equips them with the tools to assess the prevailing conditions of the real estate market and to prepare for potential shifts in market dynamics. Specifically, both investors and policymakers are urged to remain vigilant in monitoring changes in the inventory of houses for sale. This vigilant approach can serve as an early warning system for upcoming market changes, helping stakeholders make well-informed decisions.

Climate change is a problem that concerns all of us. Despite the information produced by organizations such as the Expert Team on Climate Change Detection and Indices and the United Nations, only a few cities have been planned taking into account the climate changes indices. This paper aims to study climatic variations, how climate conditions might change in the future and how these changes will affect the activities and living conditions in cities, specifically focusing on Mexico city.

In this approach, two distinct machine learning regression models, k-Nearest Neighbors and Support Vector Regression, were used to predict variations in climate change indices within select urban areas of Mexico city. The calculated indices are based on maximum, minimum and average temperature data collected from the National Water Commission in Mexico and the Scientific Research Center of Ensenada. The methodology involves pre-processing temperature data to create a training data set for regression algorithms. It then computes predictions for each temperature parameter and ultimately assesses the performance of these algorithms based on precision metrics scores.

This paper combines a geospatial perspective with computational tools and machine learning algorithms. Among the two regression algorithms used, it was observed that k-Nearest Neighbors produced superior results, achieving an R² score of 0.99, in contrast to Support Vector Regression, which yielded an R² score of 0.74.

The full potential of machine learning algorithms has not been fully harnessed for predicting climate indices. This paper also identifies the strengths and weaknesses of each algorithm and how the generated estimations can then be considered in the decision-making process.