Several state departments of transportation (state DOTs) have encountered significant challenges to accurately estimate costs of their highway projects. It is not uncommon that states’ DOT estimates (owner’s estimates) are significantly different from contractors’ submitted bids. This is a critical problem for state highway agencies that strive to develop more accurate cost estimates, deliver projects within the budget, and optimize constrained funds for their highway programs. This inaccuracy problem is a temporal issue since the engineer’s estimate is developed ahead of time before the project is advertised and bids are received. The question that transportation agencies are interested in finding an answer to is: are there any significant risk factors in the construction market indicating to the increased likelihood of the deviation between owner’s estimate and the submitted low bid? In this research, a temporal perspective is selected to answer this question through identifying risk factors affecting the accuracy of the owner’s estimate. The ratio of low bid to owner’s estimate is examined using time-series analysis. The objectives of this research are to (1) examine several variables representing local highway construction market, overall construction market, macroeconomic conditions, and energy market, to identify the leading indicators of ratio of low bid to owner’s estimate; and (2) use the identified leading indicators to develop an appropriate time-series model to forecast the ratio of low bid to owner’s estimate. Four variables are identified as the major leading indicators: (1) number of projects awarded in the same month at the state level; (2) average number of bidders last month; (3) producer price index for steel mill products (PPISM); and (4) construction cost index (CCI). Several seasonal autoregressive integrated moving average with explanatory variable (ARIMAX) models are developed that are capable of forecasting the ratio of low bid to owner’s estimate with a high accuracy. This research contributes to the state of knowledge of analyzing the difference between owner’s estimate and low bid through: (1) identification of leading indicators of ratio of low bid to owner’s estimate that convey the extent of risk and uncertainty associated with construction projects at the cost estimation phase; and (2) development of appropriate multivariate time-series models (i.e., ARIMAX models) to predict the ratio of low bid to owner’s estimate. It is anticipated that the results will help cost estimating professionals in transportation agencies better understand the variability between their estimates and submitted bids by highway contractors, and thus, prepare more accurate cost estimates and develop appropriate risk management strategies for enhanced decision-making.

Forecasting pavement performance condition is essential within the pavement management system to optimize decisions with regard to planning maintenance and rehabilitation projects. Accurate forecasts facilitate timely interventions and assist in formulating cost-effective asset management plans. Data-driven machine learning models that utilize historical data to improve forecasting precision have gained attention in the field of asset management. Although numerous studies have employed regression-based models to forecast pavement condition, transportation asset management often operates according to condition index ranges rather than exact values. Therefore, classification models are suitable for predicting pavement condition grades and determining the appropriate maintenance type for pavement assets. This research focuses on developing five machine learning classification models to predict pavement condition: random forest; gradient boost; support vector machine; k-nearest neighbors; and artificial neural network. To enhance prediction performance, these models are integrated using ensemble methods, including voting and stacking. The classification models are developed using a dataset from the Georgia Department of Transportation that documented the condition of asphalt pavements for predefined maintenance sections between 2017 and 2021. A voting ensemble model constructed with the two best-performing individual classification models reached the highest accuracy rate at 83%. Although the performance of individual models fluctuates, ensemble models consistently produce a top-tier performance regardless of the variations in data sampling. Therefore, ensemble methods are recommended for developing pavement condition prediction models to improve accuracy and achieve a more consistent quality of predictions. The findings of this research will provide transportation agencies with information to help them strengthen their forecasting practices in relation to pavement condition, thereby improving their maintenance planning and cost savings.

Purpose: This study aims to analyze low bid deviations in transportation infrastructure projects, identify key project and market-related factors influencing these deviations, and employ a machine learning (ML) framework to improve bid accuracy and forecasting. Design/methodology/approach: This study analyzes 2,915 historical transportation project bids from Louisiana (2012–2024). The dataset was split into training (80%) and testing (20%) subsets. A two-stage feature selection process was implemented, combining Pearson correlation filtering and mutual information ranking to select the top nine predictive variables. Five ML models, LightGBM, CatBoost, XGBoost, TabNet, and a stacking ensemble, were trained and evaluated. Model interpretability was enhanced through SHapley Additive exPlanations (SHAP) and sensitivity analysis. Findings: TabNet achieved the best predictive performance, capturing complex, nonlinear relationships among variables. SHAP analysis revealed that the number of bidders, construction investment levels, and material costs were the most influential factors. Sensitivity analysis confirmed the measurable impact of construction demand and input prices on predicted deviations, while employment-related variables showed lower marginal influence. Research limitations/implications: This study is limited by its reliance on historical bid data from a single U.S. state (Louisiana), which may constrain the generalizability of the findings to other regions with different procurement frameworks, contractor behaviors, and economic dynamics. Furthermore, while the selected ML models demonstrated strong predictive performance under typical market conditions, their effectiveness may decrease during periods of economic volatility or unexpected disruption. These limitations highlight the need for future research to incorporate multi-state datasets, consider temporal modeling strategies, and explore regional heterogeneity in contractor markets and procurement practices. Such expansions would help validate and enhance the robustness of ML-based frameworks in broader public infrastructure contexts. Practical implications: The results underscore the practical value of using ML-based tools, such as TabNet, in transportation cost estimation and procurement planning. By identifying key predictors of bid deviations—such as competition levels, construction demand, and material prices—transportation agencies can refine early-stage cost estimates and reduce estimation bias. Additionally, using interpretable models with SHAP and sensitivity analysis empowers decision-makers with actionable insights, promoting transparency and informed procurement strategies. Encouraging broader contractor participation and integrating real-time market indicators into cost estimation workflows can ultimately enhance project planning accuracy and procurement efficiency. Originality/value: This research presents a replicable, interpretable ML framework for analyzing low bid deviations in public infrastructure projects. The approach enables transportation agencies to better understand the drivers of bid variability, improve cost estimation practices, and adapt procurement strategies to evolving market conditions.

Extensive destruction and damage to communities in the aftermath of large-scale disasters such as hurricanes, floods, and earthquakes can cause substantial disorder in social and economic activity. The ensuing repercussions to social and economic systems lead to considerable uncertainty in continuing existing construction projects and implementing new reconstruction is problematic for accurately determining construction costs and making appropriate investment decisions. A large-scale disaster magnifies the importance of empirically examining variations in construction costs. Therefore, the overarching objective of this research is to analyze submitted unit price bids for superpave asphaltic concrete line items for highway projects let in the state of Louisiana after hurricanes Katrina and Rita. We employ two-way analysis of variance and a cumulative sum (CUSUM) control chart to monitor and detect changes in submitted unit price bids for hurricane- and non-hurricane-impacted areas. The results of the CUSUM control chart indicate that unit price bids for asphalt line items in the impacted areas significantly increased immediately after Hurricane Katrina and Rita hit the Gulf of Mexico, and those in the non-hurricane-impacted areas significantly increased six months after the hurricane. The findings of this research enable transportation agencies to more closely estimate the cost of rebuilding highway projects and make more-informed investment decisions for highway recovery programs in the aftermath of large-scale disasters.

Construction Management students are the future driving forces of the construction industry advancement. The purpose of this research is to analyze the students’ perception of the Building Information Modeling (BIM) application in the construction management program in a university. This study investigates five major aspects of students’ perceptions toward a BIM application including, (1) the source of knowledge of BIM; (2) the perception of the BIM software applications with level of competency; (3) the awareness level of BIM to get a job in construction industry; (4) the perception of BIM-related jobs; the perception of the future of BIM in construction industry; and (5) the importance of BIM education within the CM degree program and CM undergraduate capstone projects. Thus, this study conducted a survey with different levels of the construction management students. Adopting the student population from Kennesaw State University as the case study, this research initiated a questionnaire-based approach followed by statistical analysis. Total number of students were collected of their responses to four Construction Management year groups. The research from student perspective would address perceptions of BIM implementation, especially construction management students’ opinions related to BIM implementation and help to get feedback from industry opinion to implement into curriculum.