Muhammad Yamusa

Public procurement spending in Nigeria are usually documented and presented in non-standardised formats. This manifests in spends categorisation and classification inefficiencies. To address this, this research uses natural language processing (NLP) to classify the government’s procurement spending based on the United Nations Standard for Product and Service Code (UNSPSC) procurement taxonomy. This research developed a machine learning model for the classification of procurement spending to the UNSPSC commodity level. The dataset was obtained from federal procuring entities. TF-IDF was used to transform them into NLP features. Multiple machine learning algorithms were employed to develop the classification model. The best performing algorithm is SVM with a 93% and 92% accuracy under the train-test split and k-fold cross-validation respectively. The higher level of accuracies obtained for many of the algorithms mean that the model can be practically deployed for the classification of the procurement spending based on UNSPSC standard procurement taxonomy.

Purpose A serious concern for construction costs has been the presence of uncertainties in construction operations and how they affect project performance. Several models exist for predicting construction project costs. However, the models overlook the effects of uncertainties on construction costs. This study, therefore, aims to develop a predictive model that considers uncertainty when estimating building renovation project costs. Design/methodology/approach The study employed project scope factors and 45 uncertainty factors in the model development. SHapley Additive exPlanations (SHAP) was used to reveal the uncertainty factors that had a significant impact on the construction costs and to improve the performance of the model. The study then used the outcome of the sensitivity analysis along with the project scope factors to train and test a prediction model using XGBoost. Findings The study found crude oil price, project complexity, delays in payment, regulatory requirements and Inappropriate design to have the most significant impact on construction renovation project costs. The XGBoost model for predicting construction renovation project costs has produced promising outcomes with an accuracy of 91.20%. Practical implications Findings from this study will enable project managers and stakeholders to make informed decisions, optimise resource allocation and mitigate project risks. Originality/value To improve the cost performance of construction renovation projects, it is essential to take uncertainty into account, its impact on predictions and the accuracy and value of model predictions. In this study, a novel machine learning approach was developed to predict the construction cost of renovation projects by leveraging the uncertainty factors.

The manual approach to public procurement is plagued with inefficiencies. To address these problems, efforts were made to digitize the processes in Nigeria. However, the e-compliance readiness of procurement processes is not known. This study attempts to assess e-compliance maturity of public procurement lifecycle in Nigeria. The study adopted a mixed research approach. A qualitative research method was used to establish criteria for evaluating the readiness of public procurement processes for digitization. Focus group interview with Six (6) automation and procurement professionals was conducted to arrive at the parameters used for the readiness assessment. Consequently, a questionnaire survey was administered on experienced public procurement professionals to evaluate the e-compliance readiness of some identified public procurement processes. Best to Worst Method (BWM) was used to evaluate e-compliance maturity level. The study shows that the processes are readily compliant for digitization.

Recession has been found to severely affect the Construction Industry through reduction of construction projects output, decreased employment as well as profitability, and at times, results in firms becoming insolvent. This led to the development of various responsive strategies for survival. However, previous research efforts have overlooked the three success indices (output, profitability and employment conditions), which have been found to be the major areas affected by recession which can lead to the total collapse of a firm. The aim of the research is to assess the influence of survival strategies on the growth or decline of profitability of construction firms. The study then established the relationship between the experience and profitability of the firms. A quantitative approach using an online questionnaire survey was adopted for this study. One hundred (100) of the top customers of some selected banks were contacted and sixty-seven (67) of those firms agreed to participate in the survey and had the survey links sent to them. Forty-two (42) filled questionnaires were retrieved. The SPSS (version 23) statistics software package was used to assess the mean scores and Pearson’s chi-square test to assess the relationship between a firm’s profitability and the firm’s years of experience. The study found optimum utilization of workforce (Minimizing staff redundancies) to be the most used strategy; placing greater emphasis on marketing, building relationships, effective planning and management was rated as most important strategy; while trying new methods and technologies to improve productivity had the highest influence on growth in profitability. The study recommended that construction firms should make marketing to new clients and establishing a bond with existing clients a core job function while putting more efforts on understanding methods of optimally utilizing their existing workforce and eliminating staff redundancies.

Variations in construction projects are inevitable. These variations, unless properly managed, can lead to serious cost and time overruns, which affect the overall success of construction projects. Over the years, research on variations management within the construction domain has been recording a tremendous upsurge. Monitoring this research progress is crucial to identifying topics that need more investigation. This study, therefore, conducted a scientometric review using the bibliometric data from 897 research articles on variations management in the area of construction projects with the aid of the VOS viewer software. The analysis revealed that from 1982 to 2023, variations research publications grew steadily. This demonstrates the growing dedication of efforts towards the management of variations in construction projects. The study reveals leading outlets, authors and studies in variations management research. The study consequently contributes to the body of knowledge by providing early career researchers, funding bodies, construction project policymakers, as well as industry professionals with a useful reference point on the scientific research advancements in variations management research.

Public procuring entities globally have been adopting the digitised approach in order to improve efficiency. However, existing systems have been found to be fragmented and cannot be generalised as they are country-specific. This study, therefore, designed and developed a web-based e-procurement system capturing the entire public procurement lifecycle including a machine learning component. The study adopted the RIPPLE and unified process methodologies of the system development lifecycle and developed one domain conceptual model, covering the entire procurement lifecycle. Then, static analysis conceptual models were developed to capture different processes of the procurement lifecycle. The study designed and developed the system architecture capturing physical architecture and user interface, and machine learning models for automated searching and classification of tender and spends using UNSPSC taxonomy. This study provides a fundamental step toward the automation of e-procurement systems for public procuring entities.

Basic/core competencies alone rarely translate into gainful employment for fresh graduates in today’s highly competitive labour market. Accordingly, assessing employability skills desired in addition to basic/core competencies by employers of fresh graduates, has become the focus of researchers and education authorities of disciplines/majors. This study assessed the most influential employability skills for gainful employment of graduate Quantity Surveyors (QS). A questionnaire was self-administered to a sample of 108 QS consultancy firms. Statistical analysis was conducted using Pearson correlation and multiple regression. Results revealed industry interaction, self-motivation skills and entrepreneurial skills with respective standardized coefficient of 0.406, 0.341 and 0.215 to be employability skills most influential in addition to basic/core competencies, for gainful employment of QS graduates. As previous attempts to improve employability of QS graduates focused largely on basic/core competencies only, this finding present QS education authorities with most important skills to consolidate on other than core competencies in order to ensure QS graduates are gainfully employable. From a practical perspective, the study’s findings can be used by quantity surveying education authorities as a basis to further consolidate their teaching plans and ensure fresh quantity surveying graduates are fully work ready and gainfully employable. 

Nigerian public procuring entities are gradually transitioning from manual-based procurement processes to digital-based processes. One of the key processes being automated is the notification of tenders which traditionally has been done through newspapers. Given the growing volume of digital advertisements, it is very imperative to automate the process of classification of tender titles/descriptions into appropriate categories using standard procurement taxonomy such as the United Nations Standard Product and Service Code (UNSPSC). Natural language processing (NLP) methodology was applied to automatically classify tender titles/descriptions into appropriate UNSPSC. Multiple machine learning algorithms were employed to develop the classification models. Given a tender title/description, the models can predict the correct code to apply at the segment, family, class, and commodity levels of the UNSPSC. The algorithms with the best performance under the train-test split validation and K-fold cross-validation methods are support vector machines.

The manual approach to public procurement of works, goods, and services is characterised by many inefficiencies. To address these inefficiencies, public procuring entities globally adopt web-based e-procurement systems developed based on requirement models, for enhanced efficiency. However, existing developed requirement models and hence, resulting web-based e-procurement systems in Nigeria are fragmented, and limited to only some components of the procurement lifecycle. This study aims to develop a requirement model capturing the entire procurement lifecycle with a view to providing a basis for the development of a holistic web-based e-procurement system for public procuring entities in Nigeria. A qualitative approach was adopted, where literature review was conducted to identify the existing manual public procurement process. A requirement model comprising of a “business requirement model (BRM) with 14 actors performing 38 business use cases and a system requirement model carrying out 91 different use cases”, was developed.

The construction sector faces unique challenges resulting from the impact of climate change that have significant consequences on overall project delivery. While these challenges are prevalent across the global construction sector, a contrast exists in coping mechanisms and strategies adopted to mitigate the impact across emerging and more developed economies. Employing a qualitative approach, the study utilised the 4R resilience framework for project delivery to explore resilience and adaptation strategies for the intersection of extreme weather conditions, health and safety concerns, and overall project delivery within the construction sector. The chapter identified common challenges affecting the resilience strategies of emerging economies, including inadequate infrastructure, lack of regulatory frameworks, financial constraints, and reliance on outdated engineering practices. The study also found varying resilience approaches across different contexts employed to mitigate risks and enhance project resilience in emerging and developed construction environments. Finally, the study found that global south countries like Nigeria and South Africa fight with other auxiliary challenges that further limit their ability to adopt resilience strategies for sustainable construction project delivery. Recommendations in the chapter are poised to facilitate the development of robust strategies for navigating climate change impact on construction project delivery in emerging economic environments, contributing to the discourse on climate resilience in the global construction sector.

The catastrophic effect of fire incidents such as loss of lives, damage to building structures and economic loss, underscore the need for efficient fire safety in buildings, which has been a major subject of discussion in the UK. In this study, a comprehensive review of literature pertinent to building fire safety in the UK is presented. The study adopts systematic review approach, collected data from Scopus and analysed 51 qualified articles quantitively and qualitatively. The review shows a rise in publication since 2004, revealing prominent authors and keywords in building fire safety research. The review further identified the categories of fire safety practices in the UK, including technological innovations, mitigation, behavioural, and regulatory measures. Notable findings reveal the challenges in current practices including compliance and enforcement issues, maintenance of fire safety systems, public awareness and behavioural issues, technological adoption and integration challenges, and infrastructure and building design challenges. To address the challenges identified, proposed recommendations include fire safety training, simplifying and unifying regulations, maintenance and inspection of fire safety systems, fostering and upholding public trust, enhancing public awareness, integration of advanced technologies, and formulation of fire safety strategies. Additionally. the study further recommends more comparative research on international fire safety practices and social factors influence on fire regulations to effectively enhance fire safety practices in the UK.

Existing research on constructional professional attitudes towards fire safety and evacuation has predominantly employed traditional methodologies. While these methods have provided valuable insights, they are limited in their ability to capture the full spectrum of the stakeholders. Moreover, a significant gap exists in the literature regarding the broader population’s concerns about how the industry experts perceives and responds to building safety regulations, particularly in the context of new legislation like the Building Safety Act (BSA) 2022. To address these gaps, this study adopts a novel approach by analysing social media data, specifically YouTube, to capture a wider range of public sentiments towards the BSA 2022. A total of 3577 data points reflecting the general public’s views were gathered, processed, and examined using sentiment analysis, k-means clustering and Latent Dirichlet Allocation text mining techniques for topic modelling. Findings reveal nine clusters each for the positive and negative sentiments. The overall findings reveal that the public expressed positive sentiments (20 %), negative sentiments (4 %), and neutral sentiments (76 %) towards BSA 2022. The study posits recommendations from the public’s sentiments for policy makers to leverage.

Automated Compliance Checking (ACC) is continuously gaining traction in improving the efficiency and precision in regulatory compliances within the AEC sector. Thus, this research presents a comprehensive review of the current state of ACC emphasising its application domains, techniques, challenges and opportunities. The review reveal that ACC is currently being applied in multiple domains including building design analysis, energy efficiency, construction safety and fire safety. ACC systems currently employ techniques such as artificial intelligence (machine learning, neural networks, and natural language processing), graph-based methods, semantic enrichment and representation and general rule representation analysis. The review identifies technological constraints and integration difficulties as main challenges facing ACC implementation. The potential opportunities for ACC include integration with enhanced technologies, expanding application domains, collaborations and standardisations. This study addresses existing knowledge gaps and enhances the understanding of ACC's role and impact, steering future research towards innovative approaches and improved implementation strategies.