Claim Missing Document
Check
Articles

Found 2 Documents
Search

Predictive Models of Construction Project Success Rating Using Regression and Artificial Neural Network Tamayo, Clyde L.; Famadico, Jerome Jordan F.
International Journal of Multidisciplinary: Applied Business and Education Research Vol. 5 No. 7 (2024): International Journal of Multidisciplinary: Applied Business and Education Rese
Publisher : Future Science / FSH-PH Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11594/ijmaber.05.07.27

Abstract

This research addresses the gap in comprehensive predictive models for construction project success rating by exploring the potential of regression models to evaluate project success rating. By analyzing 130 datasets from the National Capital Region, the study utilizes Support Vector Regression (SVR), Multiple Linear Regression (MLR), and Artificial Neural Network (ANN) with a 22-30-1 configuration (22 input neurons, 30 neurons in a single hidden layer, and 1 output neuron). The input variables represent critical success factors rated on a scale of 1-5, while the output variable represents the predicted project success percentage rating. Various statistical tools, including ANOVA, Lasso Regression, R², MAE, and MSE, are utilized for evaluation. The findings reveal that SVR achieved the highest accuracy (R² = 0.881, MAE = 2.172, MSE = 7.054), followed closely by MLR (R² = 0.874, MAE = 2.180, MSE = 7.470), while ANN (R² = 0.743, MAE = 3.076, MSE = 15.239) may require refinement. Lasso Regression identified 22 critical success factors, with Financial Condition, Effectiveness in Decision-Making, and Compliance to Quality Standards ranking as the top three. This research contributes to the advancement of construction predictive analytics, which can lead to improved decision-making and more efficient, effective, and ethical construction practices.
Cost and Time Overrun of Public Infrastructure Project in The Philippines: Inhibiting Factors and Mitigating Measures Layno, Jim Davis J.; Famadico, Jerome Jordan F.
International Journal of Multidisciplinary: Applied Business and Education Research Vol. 5 No. 12 (2024): International Journal of Multidisciplinary: Applied Business and Education Res
Publisher : Future Science / FSH-PH Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11594/ijmaber.05.12.30

Abstract

Time and cost overruns in the implementation of infrastructure pro-jects are endless, as appears in all the implementing agencies of the government. According to the recent report of the state auditor, pro-jects were not completed within the specific contract time, while the socioeconomic planning body reported cost overruns on several big-ticket projects. This study proposes a frame of factors influencing overruns and mitigation actions as a contribution to the risk analy-sis of the implementation of projects as well as the project manage-ment initiative in monitoring and control of projects. By analyzing the datasets from Metro Manila, this study identified the most prevalent influencing factor of cost and time overruns faced in the implementation of infrastructure projects and developed measures to mitigate overruns. A total of 196 professionals responded to a questionnaire, and 12 participants were involved in unstructured interviews, which supported the data and results. To interpret and validate the data gathered, a relative importance index and a one-way analysis of variance test were used. The study revealed that the influencing factors leading to time overruns are inaccurate budget-ing, location of site, suspension of work, land acquisition, and varia-tion order, while for the cost overrun factors, inaccurate budgeting, variation order, inadequate project planning, market conditions, and inadequate site investigations prevail. A relationship between the perceptions of the 3 groups, namely the contractor, consultant, and implementing agency, with regards to the cost overrun factors was significant. However, with regards to the time overrun factors, they are not significant.