Highway and bridge agencies use several systematic inspection approaches to ensure an acceptable standard for their assets in terms of safety, convenience, and economic value. The Bridge Condition Index (BCI), used by the Ontario Ministry of Transportation, is defined as the weighted condition of all bridge elements to determine the rehabilitation priority for the bridge. Therefore, accurate forecasting of BCI is essential for bridge rehabilitation budgeting and planning. The large amount of data available about bridge conditions for several years enables the use of different mathematical models to predict future BCI. This research focuses on investigating different classification models developed to predict the BCI in the province of Ontario, Canada, based on the publicly available historical data for 2,802 bridges over a period of more than 10 years. Predictive models used in this study include k-nearest neighbors (k-NN), decision trees (DTs), linear regression (LR), artificial neural networks (ANN), and deep learning neural networks (DLN). These models are compared and statistically validated via cross validation and paired $\mathrm{t}$ -test. The decision tree model showed acceptable predictive results (within 0.25% mean relative error) when predicting the future BCI and is the recommended option based on its performance and certainty in posterior maintenance decision making for the selected case study.

Due to a lack of suitable methods, extraction of reporting requirements from lengthy construction contracts is often completed manually. Because of this, the time and costs associated with completing reporting requirements are often informally approximated, resulting in underestimations. Without a clear understanding of requirements, contractors are prevented from implementing improvements to reporting workflows prior to project execution. This study developed an automated reporting requirement identification and time–cost prediction framework to overcome this challenge. Reporting requirements are extracted using Natural Language Processing (NLP) and Machine Learning (ML), and stochastic simulations are used to predict overhead costs and durations associated with report preparation. Functionality and validity of the framework were demonstrated using real contracts, and an accuracy of over 95% was observed. This framework provides a tool to rapidly and efficiently retrieve requirements and quantify the time and costs associated with reporting, in turn providing necessary insights to streamline reporting workflows.

Purpose: Decisions by construction contractors to bid (or not to bid) require the thorough assessment and evaluation of factors relevant to the decision, as well as the quantification of their combined impact, to produce successful bid/no-bid decisions. The purpose of this study is to present a fuzzy fault tree model to assist construction contractors to more efficiently bid for future projects. Design/methodology/Approach: The proposed model consist of two stages: first, identification of the factors that affect bidding decision using a questionnaire survey after an extensive literature review, and second, usage of the identified factors to build a fuzzy fault tree model to simulate the bidding decision. Findings: A list of 15 factors that affect bid/no-bid decisions was identified. Analysis of factors revealed that the highest-ranking factors were related to financial aspects of the project. A case study is presented to demonstrate the capabilities of the model, and a fuzzy important analysis is performed on the basic events to demonstrate the differences between three contractors’ bid/no-bid decisions. The results reveal that there is variation between the decisions of each contractor based on their willingness to participate. Besides, the influence of evaluation factors on the final decision for each contractor is different. Originality/value: The study contributes to the body of knowledge on tendering and bidding practices. The proposed model incorporated the fuzzy set theory, which suits human subjectivity. The proposed methodology overcomes the limitations of previous models as it can, using the linear pool opinion principle, combine and weigh the evaluations of multiple experts. In addition, the model is convenient for situations where historical data are not available.

Purpose: The bid/no-bid decision is critical to the success of construction contractors. The factors affecting the bid/no-bid decision are either qualitative or quantitative. Previous studies on modeling the bidding decision have not extensively focused on distinguishing qualitative and quantitative factors. Thus, the purpose of this paper is to improve the bidding decision in construction projects by developing tools that consider both qualitative and quantitative factors affecting the bidding decision.Design/methodology/approach: This study proposes a mixed qualitative-quantitative approach to deal with both qualitative and quantitative factors. The mixed qualitative-quantitative approach is developed by combining a rule-based expert system and fuzzy-based expert system. The rule-based expert system is used to evaluate the project based on qualitative factors and the fuzzy expert system is used to evaluate the project based on the quantitative factors in order to reach the comprehensive bid/no-bid decision.Findings: Three real bidding projects are used to investigate the applicability and functionality of the proposed mixed approach and are tested with experts of a construction company in Alberta, Canada. The results demonstrate that the mixed approach provides a more reliable, accurate and practical tool that can assist decision-makers involved in the bid/no-bid decision.Originality/value: This study contributes theoretically to the body of knowledge by (1) proposing a novel approach capable of modeling all types of factors (either qualitative or quantitative) affecting the bidding decision, and (2) providing means to acquire, store and reuse expert knowledge. Practical contribution of this paper is to provide decision-makers with a comprehensive model that mimics the decision-making process and stores experts' knowledge in the form of rules. Therefore, the model reduces the administrative burden on the decision-makers, saves time and effort and reduces bias and human errors during the bidding process.