Machine learning for the identification of competent project managers for construction projects in Nepal

Abstract

Purpose Project manager’s competency is crucial in the construction sector for the successful completion of projects, particularly in the case of developing countries like Nepal. Therefore, it is very essential to select competent project managers by finding the competency factors required by them. Hence, this study aims to identify the characteristics of competent project managers by expert opinion method and to evaluate their competency level by a questionnaire survey to develop a prediction model using a supervised machine learning approach via Waikato Environment for Knowledge Analysis (WEKA), a machine learning tool which predicts Project manager’s performance as “Higher than expected,” “Expected” or “Lower than expected” for the medium complexity construction projects of Nepal (from US$200,000 up to US$10M). Design/methodology/approach The data collection procedure for this research is based on an expert opinion method and survey. Expert opinion method is conducted to find the characteristics of a competent project manager by validating the top 15 competency factors based on literature review. The survey is conducted with the top management to assess their project manager’s competency level. Both qualitative and quantitative approaches are used to collect data for classification and prediction in WEKA, a machine learning tool. Findings The results illustrate that the project managers in Nepal have a high score in leadership skills, personal characteristics, team development and delegation, communication skills, technical skills, problem-solving/coping with situation skills and stakeholder/relationship management skills. Furthermore, among the seven classifiers (naïve Bayes, sequential minimal optimization [SMO], multilayer perceptron, logistic, KStar, J48 and random forest), the accuracy given by the SMO algorithm is highest of all in both the percentage split and k-folds cross validation method. The model developed using SMO classifier by k-folds cross-validation (k = 10) is acknowledged as a final model. Research limitations/implications This research focuses to develop a prediction model to predict and analyze the competency of project managers by applying a supervised machine learning approach. Seven extensively used algorithms (Naïve Bayes, SMO, multilayer perceptron, logistic, KStar, J48, random forest) are used to check the accuracy of models and an algorithm that gives the highest accuracy is adopted. Data collection for this research is carried out by expert opinion method to validate the characteristics (factors) essential for competent project managers in the first round and the description of each factor as high, medium and low is inquired with the same experts in the second round. After an expert opinion, a structured questionnaire is prepared for the survey to assess the competency level of project managers (PMs). The competency level of PMs working under government funded, foreign aided or private projects from the contractor’s side is measured. This research is limited to the medium scale construction projects of Nepal. Practical implications This model can be a huge asset in the human resource department of construction companies as it helps to know the performance level of project managers in terms of “Higher than expected,” “Expected” or “Lower than expected” for the medium complexity construction projects of Nepal. Also, the model will assist human intelligence to make the decision while recruiting a new project manager/s for different types of projects at a time. Moreover, the model can be used for self-assessment of project manager/s to know their performance level. The model can be used to develop a user friendly interface system or an application such that it can be conveniently used anywhere any time. Social implications This research shows that most of the project managers working in a medium complexity construction project of Nepal are male, maximum of them hold bachelor’s degree and study for road projects. Furthermore, most of the project managers scored high in leadership skills, personal characteristics, communication skills, technical skills, problem-solving/coping with situation skills, team development and delegation and stakeholder/relationship management skills. The model has given the “Personal characteristics” attribute the highest weightage. Likewise, other attributes having high weightage are communication skills, analytical abilities, project budget, stakeholder/relationship management, team development and delegation and time management skills. Originality/value This research was conducted to find the competency factors and to study the competency level of project managers in Nepal to develop a prediction model to predict the PM’s performance using a machine learning approach in medium scale construction projects. There is a lack of research to develop a model that predicts project manager’s competency using the machine learning approach. Therefore, the predictive model developed here helps in the identification of a competent project manager as it will be advantageous for project completion with a high success rate.

Competence of project management professionals according to type of project: a systematic literature review

“…In this study, two competence gaps were identified in the PMCDF guide, they are: Information Technology Skills and Analytical Thinking [64]. For Karki and Hadikusumo [65] and Pereira and Freitas [64], Analytical Thinking is the ability to develop an understanding of a situation or problem, dividing it into smaller parts to trace the cause and implications of the situation or problem.…”

“…[100]- [101]; Environmental Legislation and Administration [12], [77]; Continuous Improvement [49], [77], [92], [94]; Agile Mindset [31], [70]; Multiple Project Management [38]; Analytical Thinking [16], [32], [55], [65], [70]; Critical Thinking [55], [94], [104]; Strategic Thinking [70], [71], [77], [81], [90]; Self-Taught [88], [94]; [Strategic Planning [91].…”

“…Moradi et al [14] add to it the fulfillment of promises to complete the agreed work. Among the competences not mentioned in the PMDCF guide are: Coaching [112]; Configuration Management [70], [77]; Manage Ambiguity [56]; Information Technology Skills [70], [71], [91], [92], [95], [96]; Multitasking [78]; Analytical Thinking [16], [32], [55], [65], [70] and Critical Thinking [55], [94], [102]. In the IPMA guide, it is not mentioned the competence Critical Thinking [55], [94], [102].…”

“…For this type of project, the relevance of this competence is given by the global concerns related to climate change and sustainable development, which has stimulated the need for project professionals with this competence due to their important role in the execution and delivery of projects [114], even complying with environmental and safety standards [65].…”

“…In this type of category, 64 competences were identified, 52 of which are common to the PMCDF, ICB and APM guides, presented in Table 15. The competence gaps found in the PMCDF guide are: Open to New Experiences [77], [12], [92], [35]; Self-taught [42]; Certification [7], [31], [71], [74]; Conscientiousness [18]; Curiosity [12], [93], [55]; Change Management [118]; Manage Ambiguity [56]; Marketing Skills [76]; Information Technology Skills [95], [96], [70], [71], [92], [91]; Innovation [51], [52]; Multitasking [78]; Analytical Thinking [16], [70], [32], [65], [55].…”