Forecasting construction industry demand,price and productivity in Singapore: the BoxJenkins approach

In academic research, the traditional Box-Jenkins approach is widely acknowledged as a benchmark technique for univariate methods because of its structured modelling basis and acceptable forecasting performance. This study examines the versatility of this approach by applying it to analyse and forecast three distinct variables of the construction industry, namely, tender price, construction demand and productivity, based on case studies of Singapore. In order to assess the adequacy of the Box-Jenkins approach to construction industry forecasting, the models derived are evaluated on their predictive accuracy based on out-of-sample forecasts. Two measures of accuracy are adopted, the root mean-square-error (RMSE) and the mean absolute percentage error (MAPE). The conclusive findings of the study include: (1) the prediction RMSE of all three models is consistently smaller than the model's standard error, implying the models' good predictive performance; (2) the prediction MAPE of all three models consistently falls within the general acceptable limit of 10%; and (3) among the three models, the most accurate is the demand model which has the lowest MAPE, followed by the price model and the productivity model.     

An ensemble wavelet bootstrap machine learning approach to water demand forecasting: a case study in the city of Calgary,Canada

This paper explores a hybrid wavelet, bootstrap and neural network (WBNN) modeling approach for daily (1, 3 and 5 day) urban water demand forecasting in situations with limited data availability. This method was tested using 3 years of daily water demand and meteorological data for the city of Calgary, Alberta, Canada. The performance of the WBNN method was compared to that of three other methods: traditional neural networks (NN), wavelet NNs (WNN), and bootstrap-based NN (BNN) models. While the hybrid WBNN and WNN models equally provided 1-day lead-time forecasts of greater accuracy than those obtained with other methods, for longer lead-time (3- or 5-day) forecasts the WBNN model alone outperformed the other models. The confidence bands generated using the WBNN model displayed the uncertainty associated with the forecasts.     

Using genetic algorithms and linear regression analysis for private housing demand forecast

An accurate prediction of prospective construction supply and demand, especially the private residential market, is paramount important to policy makers, as it could help formulate strategies to cultivate/stabilize the economy and satisfy the social needs (at macro level). Despite that, a realistic prediction of future private residential demand is never an easy task, as it is governed by a number of social and economic factors. In this paper, four leading indicator models are developed and compared for directly forecasting Hong Kong private sector residential demand. These comprise a (i) Linear Regression Analysis (LRA) model, (ii) Genetic Algorithms (GA) model, (iii) GA-LRA model, where LRA is used to select the indicator variables; and (iv) GA-LRA model with Adaptive Mutation Rate (AMR) to reduce the likelihood of local optima. The findings indicate that the GA-LRA model with AMR provides the most accurate forecasts and over a longer time horizon. In providing a range of possible forecasts, the model also provides an opportunity for the decision-maker to exercise judgment in selecting the most appropriate forecasts.     

Comparison of construction cost estimating models based on regression analysis,neural networks,and case-based reasoning

Adequate estimation of construction costs is a key factor in construction projects. This paper examines the performance of three cost estimation models. The examinations are based on multiple regression analysis (MRA), neural networks (NNs), and case-based reasoning (CBR) of the data of 530 historical costs. Although the best NN estimating model gave more accurate estimating results than either the MRA or the CBR estimating models, the CBR estimating model performed better than the NN estimating model with respect to long-term use, available information from result, and time versus accuracy tradeoffs.     

Forecasting building energy consumption with hybrid genetic algorithm-hierarchical adaptive network-based fuzzy inference system

There are several ways to forecast building energy consumption, varying from simple regression to models based on physical principles. In this paper, a new method, namely, the hybrid genetic algorithm-hierarchical adaptive network-based fuzzy inference system (GA-HANFIS) model is developed. In this model, hierarchical structure decreases the rule base dimension. Both clustering and rule base parameters are optimized by GAs and neural networks (NNs). The model is applied to predict a hotel’s daily air conditioning consumption for a period over 3 months. The results obtained by the proposed model are presented and compared with regular method of NNs, which indicates that GA-HANFIS model possesses better performance than NNs in terms of their forecasting accuracy.     

Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens

A comparison study has been performed with neural networks (NNs) and multiple linear regression models to forecast the next day's maximum hourly ozone concentration in the Athens basin at four representative monitoring stations that show very different behavior. All models use 11 predictors (eight meteorological and three persistence variables) and are developed and validated between April and October from 1992 to 1999. Performance results based on a wide set of forecast quality measures indicate that the NNs provide better estimates of ozone concentrations at the monitoring sites, whilst the more often used linear models are less efficient at accurately forecasting high ozone concentrations. The violation of the European information threshold of 180 microg/m(3) is successfully predicted by the NN in 72% of the cases on average. Results at all stations are consistent with similar ozone forecast studies using NNs in other European cities.     

Neural network model incorporating a genetic algorithm in estimating construction costs

This paper applies the back-propagation network (BPN) model incorporating genetic algorithms (GAs) to cost estimation. GAs were adopted in the BPN to determine the BPN's parameters and to improve the accuracy of construction cost estimation. Previously, there have been no appropriate rules to determine these parameters. The construction cost data for 530 residential buildings constructed in Korea between 1997 and 2000 were used for training and evaluating the performance of the model. This study showed that a BPN model incorporating a GA was more effective and accurate in estimating construction costs than the BPN model using trial and error.     

Large metropolitan water demand forecasting using DAN2, FTDNN,and KNN models: A case study of the city of Tehran,Iran

Efficient operation of urban water systems necessitates accurate water demand forecasting. We present daily, weekly, and monthly water demand forecasting using dynamic artificial neural network (DAN2), focused time-delay neural network (FTDNN), and K-nearest neighbor (KNN) models for the city of Tehran. The daily model investigates whether partitioning weekdays into weekends and non-weekends can improve forecast results; it did not. The weekly model yielded good results by using the summation of the daily forecast values into their corresponding weeks. The monthly results showed that partitioning the year into high and low seasons can improve forecast accuracy. All three models offer very good results for water demand forecasting. DAN2, the best model, yielded forecasting accuracies of 96%, 99%, and 98%, for daily, weekly, and monthly models respectively.     

Assessment of predictive uncertainty within the framework of water demand forecasting using the Model Conditional Processor (MCP)

This paper presents an application of the Model Conditional Processor (MCP), originally proposed by Todini (2008) within the hydrological framework, to assess the predictive uncertainty in water demand forecasting related to water distribution systems. The MCP enables us to assess the probability distribution of the future water demand conditional on the forecasts provided by two or more deterministic forecasting models. In the numerical application described here, where two years of hourly water demand data for a town in northern Italy are considered, two forecasting models are applied in order to forecast hourly water demands from 1 to 24 hours ahead: the first model has a modular structure comprising a periodic component which reflects the long-term effects and a persistence component which represents the short-term memory of the process; the latter is based on neural networks. The results highlight the effectiveness of the approach, provided that the data set used for the MCP parameterization is properly selected so as to be actually representative of the accuracy of the real-time water demand forecasting models.     

An evaluation of the accuracy of the multiple regression approach in forecasting sectoral construction demand in Singapore

In the current state of research in construction demand modelling and forecasting there is a predominant use of the multiple regression approach, particularly the linear technique. Because of the popularity, it may be useful at this stage to gain an insight into the accuracy of the approach by comparing the forecasting performance of different forms of regression analysis. It is only through such formal means that the relative accuracy of different regression techniques can be assessed. In a case-study of modelling Singapore's residential, industrial and commercial construction demand, both linear and nonlinear regression techniques are applied. The techniques used include multiple linear regression (MLR), multiple log-linear regression (MLGR) and autoregressive nonlinear regression (ANLR). Quarterly time-series data over the period 1975–1994 are used. The objective is to evaluate the reliability of these techniques in modelling sectoral demand based on ex-post forecasting accuracy. Relative measures of forecasting accuracy dealing with percentage errors are used. It is found that the MLGR outperforms the other two methods in two of the three sectors examined by achieving the lowest mean absolute percentage error. The general conclusion is that nonlinear techniques are more accurate in representing the complex relationship between demand for construction and its various associated indicators. In addition to improved accuracy, the use of nonlinear forms also expands the scope of regression analysis.     

Forecasting the sales of precast concrete building products

Sales of precast concrete building products are influenced by the general demand for construction. This demand is subject to substantial fluctuations, caused by such diverse factors as capital spending by Government, the general strength of the economy, the demand for housing — which in turn reflects mortgage interest rates -and also by seasonal factors and weather. These are some of the difficulties associated with sales forecasting in the precast concrete industry. Sales forecasting is crucial managerial practice and its accuracy is vital for any company's business survival. A survey of the current forecasting and planning practices in the industry concluded that forecasting, especially for major product groups, is fairly basic and not reliable. Against this background, a forecasting model has been developed to analyse historical data and forecast demand for 12 months ahead. Two forecasting methods were applied to historical data of 12 groups of products of a major manufacturer. The results of the forecasting model were encouraging and more accurate than the manufacturer's existing forecasting system. The authors interviewed the firm's marketing and sales staff to identify the advantages and disadvantages of the forecasting system and identify the factors which affect sales and forecasting in general. Some tangible indication of the practical use of this work is the support given to this research project by staff of this company, at all levels. The work described in this paper is part of a more general computerized capacity planning system for the precast industry. This would be suitable for major companies, most of whom produce a large number of different products in a number of different manufacturing plants dispersed throughout the UK.     

Forecasting short-term air passenger demand using big data from search engine queries

Forecasting air passenger demand is a critical aspect of formulating appropriate operation plans in airport operation. Airport operation not only requires long-term demand forecasting to establish long-term plans, but also short-term demand forecasting for more immediate concerns. Most airports forecast their short-term passenger demand based on experience, which provides limited forecasting accuracy, depending on the level of expertise. For accurate short-term forecasting independent of the level of expertise, it is necessary to create reliable short-term forecasting models and to reflect short-term fluctuations in air passenger demand. This study aims to develop a forecasting model of short-term air passenger demand using big data from search queries to identify these short-term fluctuations. The suggested forecasting model presents an average forecast error of 5.3% and indicates that an increase of approximately 195,000 air passengers is to be expected 8 months later, as the key query frequencies increase by 0.1%.     

Modeling diffusion of electrical appliances in the residential sector

This paper presents a methodology for modeling residential appliance uptake as a function of root macroeconomic drivers. The analysis concentrates on four major energy end uses in the residential sector: refrigerators, washing machines, televisions and air conditioners. The model employs linear regression analysis to parameterize appliance ownership in terms of household income, urbanization and electrification rates according to a standard binary choice (logistic) function. The underlying household appliance ownership data are gathered from a variety of sources including energy consumption and more general standard of living surveys. These data span a wide range of countries, including many developing countries for which appliance ownership is currently low, but likely to grow significantly over the next decades as a result of economic development. The result is a ‘global’ parameterization of appliance ownership rates as a function of widely available macroeconomic variables for the four appliances studied, which provides a reliable basis for interpolation where data are not available, and forecasting of ownership rates on a global scale. The main value of this method is to form the foundation of bottom-up energy demand forecasts, project energy-related greenhouse gas emissions, and allow for the construction of detailed emissions mitigation scenarios.     

Instantaneous pavement condition evaluation using non-destructive neuro-evolutionary approach

In this paper, a hybrid neural network (NN)-genetic algorithm (GA) based non-destructive pavement auscultation method for instantaneous airfield infrastructure condition assessment is discussed. NNs are employed for finite element aided forward prediction of pavement surface deflections resulting from non-destructive test impulse loading and the GAs are used for global optimisation of the pavement structural parameters by matching the NN predicted deflections with the measured pavement response. This hybrid approach takes advantage of the non-linear estimation capability provided by neural networks trained using finite element (FE) solutions in modelling the stress-dependent behaviour of unbound pavement geo-materials while improving the robustness to measurement uncertainty through the application of genetic algorithms. The performance of the developed hybrid pavement auscultation technique is evaluated through extensive field studies conducted at a state-of-the-art full-scale airfield pavement test facility. The results show that this approach is promising for real-time condition evaluation of airfield pavement infrastructure systems.     

What Is a Forecast for?

Abstract

Problem, research strategy, and findings: The forecasts transit agencies submit in support of applications for federal New Starts funding have historically overestimated ridership, as have ridership forecasts for rail projects in several countries and contexts. Forecast accuracy for New Starts projects has improved over time. Understanding the motivations of forecasters to produce accurate or biased forecasts can help forecast users determine whether to trust new forecasts. For this study I interviewed 13 transit professionals who have helped prepare or evaluate applications for federal New Starts funds. This sample includes interviewees who have had varying levels of involvement in all 82 New Starts projects that opened between 1976 and 2016. I recruited interviewees through a snowball sampling method; my interviews focus on the interviewees’ perspectives on how New Starts project evaluation and ridership forecasting has changed over time. Interview results suggest that ridership forecasters’ motivations to produce accurate forecasts may have increased with increased transparency, increased influence on local decision making, and decreased influence on external (federal) funding.

Takeaway for practice: Planners can evaluate the likely trustworthiness of forecasts based on transparency, internal influence, and external influence. If forecast users cannot easily determine a forecast’s key inputs and assumptions, if the forecaster has been tasked with producing a forecast to justify a predetermined action, and if an unfavorable forecast would circumvent decisions by the forecaster’s immediate client, forecasts should viewed with skepticism. Planners should seek to alter conditions that may create these conflicts of interest. Forecasters seem to be willing and able to improve forecast accuracy when the demand for accurate forecasts increases.     

Neural Network-Based Long-Term Hydropower Forecasting System

Artificial neural networks are alternatives to stochastic models even if the optimization of their architectures remains a tricky problem. Two different approaches in long-term forecasting of potential energy inflows using a feedforward neural network (FNN) and a recurrent neural network (RNN) are proposed. The problem of overfitting, particularly critical for limited hydrologic data records, is addressed using a new approach entitled optimal weight estimate procedure (OWEP). The efficiency of the two models using OWEP is assessed through multistep forecasts. The experiment results show that, in general, OWEP improves the models' performance and significantly reduces the training time on the order of 60 percent. The RNN outperforms the FNN but costs about a factor of 2 longer in training time. Furthermore, the neural network-based models provide more accurate forecasts than traditional stochastic models. Overall, the RNN appears to be the best suited for potential energy inflows forecasting and therefore for hydropower systems management and planning.     

Matching housing supply and demand: an empirical study of Hong Kong's market

This paper has the objective of improving on the issue of forecasting new housing construction, and highlights differences between space demand and investment demand in housing markets. Further, it indicates how these differences will affect construction decisions. The first step is to identify the factors associated with estimating residential property prices in Hong Kong, based on a demand-supply adjustment process. Specifically, this study examines the role of population growth, transaction volume, inflation and interest rate in determining house prices. Second, based on these estimations, a methodology is developed to estimate the investment demand schedule and new construction of residential property.     

Applicability of the transfer function approach to forecasting employment levels in small regions

The problem investigated in this paper is that of forecasting employment levels (both raw and seasonally adjusted) in small regions, regions typically lacking data sufficient for the construction of simultaneous equation econometric models. The method employed is transfer function analysis using readily available national variables as drivers. The results suggest that the transfer function approach is capable of providing accurate forecasts of employment levels in small regions, forecast accuracy being measured in terms of mean absolute percentage errors and root mean squared errors. We conclude on the basis of this demonstrated accuracy that this approach is a viable method for forecasting selected variables in a small region context.Support for this research was provided in part by a grant from the Manufacturers Association of Erie. Special thanks to Mrs. Dana Moreira for data entry, and miscellaneous statistical tasks. Any errors remain the responsibility of the authors.     

Predicting the compressive strength and slump of high strength concrete using neural network

High Strength Concrete (HSC) is defined as concrete that meets special combination of performance and uniformity requirements that cannot be achieved routinely using conventional constituents and normal mixing, placing, and curing procedures. HSC is a highly complex material, which makes modelling its behavior very difficult task. This paper aimed to show possible applicability of neural networks (NN) to predict the compressive strength and slump of HSC. A NN model is constructed, trained and tested using the available test data of 187 different concrete mix-designs of HSC gathered from the literature. The data used in NN model are arranged in a format of seven input parameters that cover the water to binder ratio, water content, fine aggregate ratio, fly ash content, air entraining agent, superplasticizer and silica fume replacement. The NN model, which performs in Matlab, predicts the compressive strength and slump values of HSC. The mean absolute percentage error was found to be less then 1,956,208% for compressive strength and 5,782,223% for slump values and R² values to be about 99.93% for compressive strength and 99.34% for slump values for the test set. The results showed that NNs have strong potential as a feasible tool for predicting compressive strength and slump values.     

Prediction of web crippling strength of cold-formed steel sheetings using neural networks

This study considers the use of neural networks (NNs) to predict the web crippling strength of cold-formed steel decks. Web crippling is critical for slender webs as in the case of trapezoidal sheetings which are widely used in roofing applications. The elastoplastic behaviour of web crippling is quite complex and difficult to handle. There is no well established analytical solution due to complex plastic behaviour. This leads to significant errors in various design codes. The objective of this study is to provide a fast and accurate method of predicting the web crippling strength of cold-formed steel sheetings and to introduce this in a closed-form solution which has not been obtained so far. The training and testing patterns of the proposed NN are based on well established experimental results from literature. The trained NN results are compared with the experimental results and current design codes (NAS 2001) and found to be considerably more accurate. Moreover, a trained neural network gives the results significantly more quickly than the design codes and finite element (FE) models. The web crippling strength is also introduced in closed-form solution based on the parameters of the trained NN. Extensive parametric studies are also performed and presented graphically to examine the effect of geometric and mechanical properties on web crippling strength.