Fourth-Party Logistics (4PL) transaction center aggregates trading partner competencies to provide comprehensive supply chain solutions. Since the 4PL transaction center deals with multiple category of trading partners, it offers both opportunities and risks. Especially, estimating risk in 4PL network involves collecting information from different combination of subjective and objective parameters which lacks predictive analytics. Hence, little work is carried out in synchronizing different metric scores to predict risk for managing transaction center effectively. In the first phase, risk assessment was carried out using Cormack’s model. By combining individual scaling factors and probability arrived through request for information, risk probability index was estimated. Consequently, supply chain risk was determined considering total financial impact. Subsequently, risk evaluation of all trading partners with respect to high, moderate and low categories was performed utilizing prioritization matrix. In the second phase, predictive model was synthesized using Neural Network (NN) methodology. Moreover, optimal number of predictors was attained through Partial Least Square (PLS) regression. Finally, the NN was evaluated using verification dataset to ensure model adequacy. After achieving significant predictive accuracy, the developed model can be used by the coordinator to estimate risk proactively before conducting cross-segment integration. In addition, the model helps 4PL service provider to reduce supply disruption risks in the distribution network.

Globalization led to increase in demand for Fourth-Party Logistics (4PL) which emphasizes on enhancing value proposition compared to cost reduction in Third-Party Logistics (3PL). In particular, 4PL development has been dependent on transaction center which integrates cross-segment (for example: suppliers and logistics service providers) trading partners working towards common goal. As the strength of transaction center lies in selecting and coordinating cross-segment trading partners (Kumar et al., 2013), prior information of risk can help the coordinator to minimize supply disruptions. According to Aberdeen research, 80% of the executives faced supply disruptions to manage their distribution network efficiently (McCormack, 2007). Moreover, disruption risk acts as one of the sources for bullwhip effect in a supply chain. Additionally, individual trading partners synthesize their own metrics and procedures for assessing and predicting risk.Therefore, the transaction center coordinator needs to assess risk before performing crosssegment integration in order to provide optimal 4PL solutions. Hence, assessment of risk in a proactive manner ensures consistent supply. Taking a cue from this, proactive riskpredictive model using Partial Least Square (PLS) regression and Neural Network (NN) approach was proposed. The NN’s ability to model linear and nonlinear relationships, irrespective of the dataset category, was considered as the rationale for application of this methodology. In the process of building NN, datasets were normalized and optimized to match actual and predictive Risk Probability Index (RPI). In particular, this index was estimated by multiplying scaling factors of discrete risk event categories and probability of occurrence. In principle, the model was developed in two phases. Firstly, risk assessment was carried out using Cormack’s model with six different risk enablers. In the second phase, predictive model was synthesized using NN methodology. Furthermore, the network was trained till actual and predictive RPI match through feedforward and back propagation techniques (Glenn, 2007). Lastly, viability of the recommended risk model was verified considering casting suppliers of a leading tiller and tractor manufacturing company in India. In summary, estimation of risk in a proactive manner for 4PL transaction center was highlighted.

Supply Chain Management Journal, Development of Proactive Risk-Predictive Model, 4PL Transaction Center, PLS Regression, Neural Networks, Fourth-Party Logistics (4PL), Neural Network (NN), Partial Least Square (PLS), Third-Party Logistics (3PL).