Search

Assessing project portfolio risk (PPR) is essential for organizations to grasp the overall risk levels of project portfolios (PPs) and realize PPR mitigation. However, current research is inadequate to effectively assess PPR, which brings challenges to managing PPR. In this context, the purpose of this study is to develop a PPR assessment model via an enhanced backpropagation neural network (BPNN). First, PPR assessment criteria considering project interdependencies are determined. Second, fuzzy logic is used to obtain original data for assessment criteria. Principal component analysis (PCA) is then employed to reduce the dimensionality of assessment criteria and derive the input and output of BPNN. Third, an improved genetic algorithm (IGA) is designed to optimize the initial weights and thresholds of BPNN. On this basis, the PCA-IGA-BPNN assessment model is constructed, followed by training and testing, possessing a test accuracy of 98.6%. Finally, comparison experiments are conducted from both internal and external perspectives. For internal comparison, the proposed model yields less mean absolute percentage error (MAPE), mean square error (MSE), and root mean square error (RMSE) than PCA-GA-BPNN, IGA-BPNN, PCA-BPNN and BPNN and offers the largest convergence speed (γ). As for external comparison, the presented model produces lower MAPE, MSE, and RMSE than Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN) and has the largest coefficient of determination (R 2). Results indicate that the established model performs more satisfactorily in assessing PPR. This research enriches PPR assessment methods and provides managers with a useful tool to evaluate PPR. • A hybrid project portfolio risk assessment model based on an enhanced BPNN is established. • GA is improved by adaptively adjusting the probability of crossover and mutation operations. • PCA and improved GA are integrated with BPNN to enhance its evaluation performance. • The effectiveness and superiority of the proposed model are validated through experiments. [ABSTRACT FROM AUTHOR]

Project portfolio benefit (PPB) prediction can effectively help managers monitor the acquisition of PPBs, thereby better achieving their target benefits. However, no valid model is available for PPB prediction. To narrow this research gap, we develop a model based on a backpropagation neural network improved with a genetic algorithm (GA-BPNN) to quantitatively forecast PPBs. First, the evaluation criteria for benefits are determined. Second, the input and output variables of the model are determined and calculated. Third, the initial weights and thresholds of the BPNN are improved by the GA. Fourth, based on the above optimization results, the GA-BPNN model is trained and tested. Last, the numerical example is provided to demonstrate the application of the proposed model. The results indicate that the established model is feasible and effective in predicting PPBs, with an average prediction accuracy rate of 98.64 %, which is 18.24 % better than that of the base BPNN. The model proposed in this paper effectively realizes the quantitative prediction of PPBs, enriching the research on project portfolio management (PPM) and providing managers with a tool to effectively predict PPBs. • Project portfolio benefits are divided into project benefits and synergy benefits. • A hybrid model via GA-BPNN is proposed to predict project portfolio benefits. • The applicability of the proposed model in uncertain environments is verified. • BPNN and GA are combined and first adopted into the project portfolio field [ABSTRACT FROM AUTHOR]

Urban rail transit (URT) is under accelerated construction worldwide, which exerts important effects on the ridership of existing stations. However, few studies evaluated the determinants of station ridership considering the development of URT system. By employing the spatial difference-in-differences (SDID) model, this paper evaluates the impacts of a new line on the ridership of existing stations and analyzes its spatial heterogeneity. Combined with a geographically weighted regression (GWR) model, an interaction analysis is performed to understand the spatial variations of the impacts of the new line and surrounding land use on the ridership of existing stations. The results show that the operation of a new line can effectively share the ridership of existing stations and has spatial spillover effects. For different lines and different areas, the impacts can be heterogeneous. Additionally, the coordinated development of the new line and residential land accelerates the ridership growth of existing stations. Conversely, business development around the new line can attenuate the ridership of existing stations. The findings of this paper can help to make proactive planning of URT and provide policy implications for the integrated development of URT and surrounding land use. • Evaluates the impacts of a new urban rail transit line on the ridership of existing stations. • Explores the interaction effects of the new line and surrounding land use on the station ridership. • The operation of the new line can share the ridership of existing stations and has spatial spillover effects. • The interaction effects vary across the space. • Provides policy implications for the proactive planning of urban rail transit systems. [ABSTRACT FROM AUTHOR]

This paper considers a prefabricated construction supply chain (PCSC) consisting of a project contractor who shoulders the on-site assembly task and orders prefabs from a prefabricated factory. To mitigate the heavy double handling costs associated with early and late delivery of prefabs, the project contractor requires the right quantity and exact type of prefabs are carried to construction sites according to its assembly schedule. This is known as just-in-time purchasing (JITP). However, JITP may increase the pressure on the prefabricated factory to hold excessive inventory or to compress production time. For these reasons, the prefabricated factory may be reluctant to switch to JITP. To initiate the operation of JITP and establish a win-win outcome, side-payment contracts including a delivery-time dependent subsidy and two constant transfer terms are designed as coordinate schemes. Employing Stackelberg, we explore participants' optimal decisions. The results show that the JITP yields higher profit for PCSC, and the proposed contracts are capable of achieving a win-win coordination. In particular, the constant transfer cost term is relatively equitable to participants, while the constant cost-sharing transfer term outperforms the constant transfer cost term under a high double handling cost. Moreover, the prefabricated factory earns more profit when the double handling cost for early or late delivery is high. Some managerial implications are also obtained and help to strengthen cooperation among participants and promote the sustainable development of the PCSC. • The effect of just-in-time purchasing on double handling costs is investigated by mathematical model. • Information sharing between participants under just-in-time purchasing is considered and quantified. • The different contract combinations are employed to provide participants with various coordination schemes. • Just-in-time purchasing yields higher profits for the prefabricated construction supply chain. • Side-payment contracts can resolve profit conflicts between participants arising from just-in-time purchasing. [ABSTRACT FROM AUTHOR]

Identifying the determinants of metro ridership is essential for metro planning and passenger flow management. However, few studies to date have empirically examined how accessibility affects metro ridership and even fewer have emphasized the non-linear impacts from a spatiotemporal perspective. This study demarcates station areas via the network-distance method and precisely quantifies the accessibility of metro stations both internally and externally. This is combined with a gradient boosting regression trees (GBRT) model and a Shapley additive explanations (SHAP) model to understand the non-linear impacts of accessibility on metro ridership from a spatiotemporal perspective. The results show that accessibility indicators collectively contribute more than 60% of the predictive power for metro ridership at different times and the external accessibility has a greater impact on metro ridership than internal accessibility. Some indicators, such as the shortest path and population density show threshold effects on metro ridership. More importantly, the results demonstrate significant spatial heterogeneity in the effects of accessibility indicators on metro ridership and geographic trends generally from urban to suburban areas. The findings are expected to help planning departments and transit agencies improve the coordinated development of metro systems. [ABSTRACT FROM AUTHOR]