•A hybrid model for monitoring a project with a GERT-type network is proposed.•The EDM analysis for a project with the GERT-type network is conducted.•The synergistic effect of multiple control ...points is considered.•Several regression algorithms are utilized to estimate project duration.
Project monitoring is an important topic in the field of project management. This paper proposed a hybrid model of stochastic EDM (Earned Duration Management) and machine learning for a complex project with a GERT-type (Graphical Evaluation Review Technique) network. First, an EDM analysis for a GERT-type network is conducted based on the Monte Carlo simulation. Then, considering the synergistic effect of multiple control points, a new project monitoring algorithm is designed to identify deviations and generate early warning signals. Consequently, several regression algorithms are utilized to estimate the expected project completion time. Besides, the effect of different control points, different project due dates and machine learning algorithms on model performance is explored. An illustrative case study is used to demonstrate the effectiveness of the proposed model.
This paper reviews the problems, approaches and analytical models on project control systems and discusses the possible research extensions. We focused on literature in Earned Value Analysis (EVA), ...optimization tools, and the design of decision support systems (DSS) that will contribute to helping project managers in planning and controlling under uncertain project environments. The review reveals that further research is essential to develop analytical models using EVA metrics to forecast project performance. It also suggests that DSS should be model driven, function as early warning systems and should be integrated to commercial project management software.
•We explore problems, analytical models, and algorithms on project monitoring and control.•We summarize DSS tools and emphasize integration to project management.•This review differs from the previous ones on project management; the scope is narrower.•We discuss the possible research extensions.•Our conclusion serves as a basis to develop efficient decision support systems.
This article analyzes the relationship between project cost and time performance indicators and monitoring activities, namely, tracking frequency and regularity with real project data. The existing ...literature on project monitoring and control remains scant, mainly based on self-reported, simulation-based artificial data for a single project, and somewhat inconclusive. Data from 60 projects managed in Belgium between 2011 and 2019 with different project duration and sizes were first used to reveal associations of regular monitoring with project performance with linear probability models; then, to dissect nonlinear associations between monitoring frequency and project performance indicators using random effects models. Earned value management technique with performance indicators is adopted to assess the project performance. Empirical findings indicate that regularly tracked projects are less likely to be late. Tracking frequency displays a U-shaped association with the likelihood of late completion. Moreover, tracking frequency has inverted U-shaped relationships with cost performance and schedule performance indexes. Moving beyond the direct effects, this article is the first to analyze a nonlinear relationship between monitoring and project performance. Our results also validate prior studies' findings on regular and frequent tracking effects using real-life multiple-project data and assess the EVM metrics and their behavior in project management.
Project managers need reliable predictive analytics tools to make effective project intervention decisions throughout the project life cycle. This study uses Machine learning (ML) to enhance the ...reliability in project cost forecasting. A XGBoost forecasting model is developed and computational experiments are conducted using real data of 110 projects representing 1268 cost data points. The developed model performs better than some Earned value management (EVM), ML (Random forest, Support vector regression, LightGBM, and CatBoost), and non-linear growth (Gompertz and Logistic) models. The model produces more accurate estimates at the early, middle, and late stages of the project execution, allowing for early warning signals for more effective cost control. In addition, it shows more accurate estimates in most projects tested, suggesting consistency when repeatedly used in practice. Project forecasting studies mainly used ML to estimate the project duration; a few ML studies estimated the project cost at the project's conceptual stage. This study uses real data and EVM metrics, proposing an effective XGBoost model for forecasting the cost throughout the project life cycle.
•AI system design for auto tunneling construction project monitoring.•The interpretable system is capable on anomaly detection.•Combine domain expertise with AI algorithms improves system accuracy.
...Finding a reliable and cost-effective approach to monitor the activities of the New Austrian Tunneling Method (NATM) tunnel construction automatically is a challenging yet important task. This study presents an interpretable artificial intelligence (AI) framework that automatically identifies NATM construction works using low-cost site surveillance images. The framework adopts the Bayesian statistics to combine the prior NATM construction knowledge with the visual evidence extracted by deep learning (DL) based computer vision models. The analysis results of Site CCTV surveillance videos of four NATM tunneling projects are presented to demonstrate its ability (i) to label NATM work cycles from the work timeline, (ii) to identify NATM work categories inside each work cycle, and (iii) to estimate the degree of plan-work deviation at the construction cycle level. The proposed framework yields promising results on a real NATM tunneling project.
Uncertainty, risk, and rework make it extremely challenging to meet goals and deliver anticipated value in complex projects, and conventional techniques for planning and tracking earned value do not ...account for these phenomena. This article presents a methodology for planning and tracking cost, schedule, and technical performance (or quality) in terms of a project’s key value attributes and threats to them. It distinguishes four types of value and two general types of risks. The “high jumper” analogy helps to consider how high the “bar” is set for a project (its set goals) and therefore how challenging and risky it will be. A project’s capabilities as a “jumper” (to clear the bar and meet its goals) determine the portion of its value at risk (VaR). By understanding the amounts of value, risk, and opportunity in a project, project managers can design it for appropriate levels of each. Project progress occurs through reductions in its VaR: Activities “add value” by chipping away at the project’s “anti-value”—the risks that threaten value. This perspective on project management incentivizes generating results that eliminate these threats, rather than assuming that value exists until proven otherwise.
It has been reported via several researches that the sponsorship involvement is a major factor influencing project success. These projects which may vary in their benefits, types, sizes, and ...complexity levels; generate some sort of difficulty for many government organizations managing hundreds of projects in selecting projects to be monitored. The initial selection of those projects which are being monitored through organization’s dashboards is usually drafted via some criteria that comprise a meaningful group (s) to the top management; and then this selection is altered by forcing few projects in and out. This study aim is to replace the initial existing manual selection process by an intelligent model. The proposed model is based on ANN (Artificial Neural Networks) that uses the databases of more than 300 projects out of which are 48 projects that were actually selected to be in the top management monitoring dashboards. The ANN model was built and tested for accuracy via examining the deviation between the model results and the actual selection. The test results showed acceptable confidence level in the model results where accuracy was proven to be initially accepted. The ANN model is expected to evolve and gains more maturity by including more projects that will be introduced in the coming years plans.
As timely information about a project’s state is key for management, we developed a data toolchain to support the monitoring of a project’s progress. By extending the Measurify framework, which is ...dedicated to efficiently building measurement-rich applications on MongoDB, we were able to make the process of setting up the reporting tool just a matter of editing a couple of .json configuration files that specify the names and data format of the project’s progress/performance indicators. Since the quantity of data to be provided at each reporting period is potentially overwhelming, some level of automation in the extraction of the indicator values is essential. To this end, it is important to make sure that most, if not all, of the quantities to be reported can be automatically extracted from the experiment data files actually used in the project. The originating use case for the toolchain is a collaborative research project on driving automation. As data representing the project’s state, 330+ numerical indicators were identified. According to the project’s pre-test experience, the tool is effective in supporting the preparation of periodic progress reports that extensively exploit the actual project data (i.e., obtained from the sensors—real or virtual—deployed for the project). While the presented use case concerns the automotive industry, we have taken care that the design choices (particularly, the definition of the resources exposed by the Application Programming Interfaces, APIs) abstract the requirements, with an aim to guarantee effectiveness in virtually any application context.
Abstract Risk management (RM) plays a role in project management in the software development field. As information technology (IT) systems become more essential across industries and IT projects ...continue to face failure rates effective project management becomes crucial. However, the utilization of methodologies in risk management is not widely considered, specifically in Malaysia. This study aims to investigate how software practitioners in Malaysia have implemented risk management and discover strategies that can enhance risk management for agile contexts. The main focus of this study is the limited integration of methodologies into risk management practices, which has created a gap within the software risk domain. Successful risk management is essential for the achievement of software projects, and the findings from this study can offer insights for software development organizations to make informed decisions and improve project outcomes. By utilizing a quantitative approach and adapted questionnaires, this comprehensive study collected data from 60 practitioners and conducted descriptive analysis to identify key risk elements that have significant potential to affect project performance. The findings highlight these risk elements that can significantly impact project success. Agile methodologies, with their emphasis on collaboration, communication within teams, and engagement with stakeholders, including top management, are instrumental in aligning project objectives, identifying potential risks, and resolving issues promptly. This study provides empirical insights into the risk management practices of agile practitioners in Malaysia, which can equip software development organizations with valuable knowledge for informed decision‐making. By enhancing project outcomes and guiding future strategic actions, the findings of this study can contribute to the improvement of agile risk management in the software development industry, particularly in the Malaysian context.