Optimizing Operational Efficiency Enhancement via Sensitivity Analysis and Supply Chain Simulation
DOI:
https://doi.org/10.15662/IJEETR.2025.0701008Keywords:
Supply Chain Simulation, Sensitivity Analysis, Operational Efficiency, Lead Time, Inventory Management, Demand Variability, Cost Optimization, Performance Metrics, Supply Chain StrategyAbstract
In today's fast-paced and competitive corporate world, supply chains need to run smoothly in order to stay profitable and keep customers happy. This study looked into how sensitivity analysis and supply chain simulation could be used together to find and fix problems. We created a simulated multi-echelon supply chain model and changed important variables including demand rate, lead time, and transportation cost in a controlled way to see how they affected total operational cost, service level, inventory turnover, and lead time. The results showed that even little adjustments in these variables had a big effect on overall performance. Sensitivity analysis showed which important aspects needed strategic attention, and simulation let us test multiple reaction scenarios without any risk. The integrated approach gave decision-makers useful information that would help them make the supply chain more resilient and responsive. This study showed how important predictive modeling is for making supply chain operations run smoothly and react to changes
References
Optimizing Operational Efficiency Enhancement via Sensitivity Analysis and Supply
Chain Simulation
Saurabh Kumar
Senior Technology Architect (Independent Researcher), IBM, Portland, OR, USA
skumarsecom@gmail.com
ORCID: 0009-0008-4231-7934
ABSTRACT: In today's fast-paced and competitive corporate world, supply chains need to run smoothly in order to stay profitable and keep customers happy. This study looked into how sensitivity analysis and supply chain simulation could be used together to find and fix problems. We created a simulated multi-echelon supply chain model and changed important variables including demand rate, lead time, and transportation cost in a controlled way to see how they affected total operational cost, service level, inventory turnover, and lead time. The results showed that even little adjustments in these variables had a big effect on overall performance. Sensitivity analysis showed which important aspects needed strategic attention, and simulation let us test multiple reaction scenarios without any risk. The integrated approach gave decision-makers useful information that would help them make the supply chain more resilient and responsive. This study showed how important predictive modeling is for making supply chain operations run smoothly and react to changes.
KEYWORDS: Supply Chain Simulation, Sensitivity Analysis, Operational Efficiency, Lead Time, Inventory Management, Demand Variability, Cost Optimization, Performance Metrics, Supply Chain Strategy.
I. INTRODUCTION
Supply chains have gotten more complicated and more likely to break down because of globalization, unexpected demand patterns, and markets that change quickly. As a result, making operations as efficient as possible has become a top focus for businesses that want to stay competitive, cut expenses, and make customers happier. When it comes to dealing with the variety and uncertainty that come with real-world systems, traditional supply chain management methods generally don't work. We need a more dynamic and predictive method to deal with these problems.
This study looks into how sensitivity analysis and supply chain simulation may work together as a strategic framework to make supply chain performance better. Sensitivity analysis helps decision-makers see how changes in important factors like demand, lead time, and transportation costs affect how well things work. Organizations may test different scenarios in a safe digital environment and come up with data-driven strategies without any dangers in the actual world when they use simulation modeling, which mimics how complex systems behave over time.
This study's goal is to find the most important aspects that affect supply chain efficiency and provide optimization solutions that are both strong and flexible by combining these two methods. The goal is to give a full picture of how integrated analytical tools can improve visibility, help with improved planning, and eventually lead to operational excellence in today's supply chain systems.
II. LITERATURE REVIEW
Silalahi et al. (2024) did a case-based study that showed how important sensitivity analysis is for operations research mathematical modeling. Their research showed that sensitivity analysis let decision-makers see how changes in input factors affected the best solutions. This made mathematical models more reliable and easier to understand in complicated operational settings.
Gunay et al. (2019) used sensitivity analysis and optimization methods on building operations to show how changes in operational parameters affected performance indicators like energy efficiency and occupant comfort. Their study created a methodological framework that could be used in other areas, such logistics and supply chain operations, where optimization under uncertainty was very important.
Chen et al. (2023) did a comprehensive review that looked at uncertainty analysis and optimization modeling in supply chain management. Their research showed many ways to deal with changes in demand, supply, and lead time, such as stochastic modeling, robust optimization, and fuzzy logic. The review showed that combining optimization with sensitivity analysis helped supply chain managers find important control parameters and change their plans on the fly.
Pang et al. (2020) gave a thorough review of sensitivity analysis methods in the context of analyzing building performance. Their research divided methods into local and global sensitivity techniques and underlined how important it is to choose the right one based on how hard the challenge is. The analytical techniques they used to design systems were also useful in operational situations like logistics and inventory networks.
Oliveira et al. (2019) looked into how to use simulation and optimization techniques to manage risks in the supply chain. They stressed that simulation made it possible for professionals to model complicated, random environments and see how different risk factors affected performance indicators. Their results showed how important simulation is for figuring out how a system would behave in different situations and determining the best settings when things aren't clear.
III. RESEARCH METHODOLOGY
With businesses operating on a worldwide scale and customers' needs changing all the time, operational efficiency had become a key part of strategic supply chain management. Traditional supply chain models worked well when things didn't change much, but they typically had trouble dealing with the high levels of unpredictability that are common in current logistics networks. So, combining sensitivity analysis with supply chain simulation became a full-fledged way to find out how modest changes in important variables could affect the operation of the whole system. The goal of this study was to find out how combining these two methodologies helped companies better understand operational bottlenecks and improve their supply chain setups to make them more efficient.
3.1 Research Design
The main goal of this work was to create a simulated supply chain model using a quantitative experimental research design. The architecture made it possible to test different operational situations in a controlled digital environment. The simulation system was set up to seem like how suppliers, warehouses, distribution centers, and stores interact in the actual world. By adding random elements to demand, lead time, and transportation considerations, the study was able to mimic the real-world uncertainties that supply chain systems face.
3.2 Data Collection
Since the study was based on a theory, secondary data were taken from published literature, industry reports, and case studies. Input factors were the number of orders, lead times, holding and transportation costs, stockout penalties, and demand rates. These data points were used to construct a realistic supply chain model that could be tested in different situations with simulation tools.
3.3 Model Development
Software like Arena, Simul8, or Any Logic was used to construct a discrete-event simulation model. The model showed a three-tier supply chain including suppliers, warehouses, and retail stores, as well as client demand at the last node. The simulation used probabilistic distributions to deal with variables that aren't definite, such changes in demand and delays in transportation. Feedback loops were built in so that you could see how different nodes in the system interacted with each other in real time.
3.4 Sensitivity Analysis
We did a sensitivity study to see how the supply chain reacted to changes in the input parameters. At first, the One-Factor-at-a-Time (OFAT) method was used to change only one parameter, such as lead time or demand rate, while keeping the others the same. We also used a Monte Carlo simulation to create probabilistic distributions of outcomes when many parameters were changed at the same time. This made it possible to find the most important parameters that had the biggest impact on operational performance measures.
3.5 Evaluation Metrics
The model's outputs were evaluated using several key performance indicators (KPIs) such as:
• Total Operational Cost (INR)
• Service Level (%)
• Inventory Turnover Ratio
• Average Lead Time (days)
Each KPI was recorded under baseline conditions and compared with outputs generated under varied input parameters. This helped determine which variables had the greatest impact on efficiency and cost optimization.
3.6 Model Validation
against make sure the model was correct, it was compared against well-known benchmark data and outcomes from past academic investigations. We also asked logistics managers and supply chain experts for their expert judgments on the accuracy and relevance of the simulation setup and its assumptions. We fixed any problems or differences by making small changes to the model over and over again.
IV. RESULT AND DISCUSSION
The simulated model and sensitivity analysis gave us a full set of findings that showed how important operational variables affect the overall performance of the supply chain. The study looked at how each component affected cost efficiency, service levels, and inventory management by changing parameters including demand rate, lead time, and transportation cost in a methodical way. The discussion explains what these results mean and offers strategic advice on how to improve operational efficiency through specific actions. The results are shown in a table that compares baseline values to situations that have been adjusted for sensitivity.
4.1 Baseline Performance Results
We used average parameter values from secondary data to run the baseline simulation. The model assumed that demand would be the same at 1,000 units each week, that the typical wait time would be 5 days, and that the costs of inventory and shipping would be the same as usual.
Table 1: Baseline Performance Metrics
Metric Baseline Value
Total Operational Cost (INR) ₹1,200,000
Average Inventory Level (units) 3,500
Service Level (%) 94.5%
Inventory Turnover Ratio 4.2
Average Lead Time (days) 5.0
The baseline performance measures showed that the supply chain system was somewhat effective. The model kept a balance between service quality and cost, with an overall operational cost of ₹1,200,000. However, the relatively high cost revealed that there was still potential for improvement. The average inventory level of 3,500 units showed that the company had a cautious stock policy that aimed to maintain a high service level of 94.5%. This approach worked to keep stockouts to a minimum and keep customers happy. But this plan also led to higher holding expenses. With an inventory turnover ratio of 4.2, it meant that inventory was restocked a little more than four times a year. This was fine, but it could be better to speed up the process and free up working capital. Finally, the average lead time of 5.0 days showed that the company was somewhat responsive, which means that it may become more efficient by streamlining the supply chain or improving its suppliers.
4.2 Sensitivity Analysis: Demand Variability
Demand was increased and decreased by 20% to test the system's robustness. The following outcomes were observed:
Table 2: Impact of Demand Fluctuation on Performance
Demand Scenario Operational Cost (INR) Service Level (%) Inventory Turnover
-20% Demand (800 units/week) ₹1,080,000 98.3% 3.5
Baseline (1,000 units/week) ₹1,200,000 94.5% 4.2
+20% Demand (1,200 units/week) ₹1,450,000 89.2% 5.3
Figure 1: Impact of Demand Fluctuation on Performance
The sensitivity analysis on changes in demand showed a clear link between levels of demand and supply chain performance metrics. When demand dropped by 20% to 800 units per week, the operational cost fell to ₹1,080,000, and the service level rose to 98.3%. However, the inventory turnover fell to 3.5, which meant that the inventory moved more slowly since it was overstocked. The system kept up a steady level of service (94.5%) and a reasonable level of performance at a baseline demand of 1,000 units per week. But when demand went up by 20% to 1,200 units per week, operational costs shot up to ₹1,450,000, and the service quality plummeted to 89.2%. This showed that the system was less able to meet consumer needs when things got tough. Even if the inventory turnover went up to 5.3 because of increasing demand, the system had trouble keeping costs down and providing reliable service. This shows how important it is to have flexible replenishment plans during times of high demand.
4.3 Sensitivity Analysis: Lead Time Variation
The sensitivity analysis on lead time variation showed that shorter lead times significantly improved supply chain performance, while longer lead times had adverse effects. When the lead time was reduced to 3 days, operational costs decreased to ₹1,050,000, service levels improved to 97.6%, and average inventory levels dropped to 2,900 units, indicating a more responsive and cost-efficient system with lower holding costs.
Table 3: Impact of Lead Time on Supply Chain KPIs
Lead Time (days) Operational Cost (INR) Service Level (%) Avg Inventory (units)
3 Days ₹1,050,000 97.6% 2,900
Baseline (5 Days) ₹1,200,000 94.5% 3,500
7 Days ₹1,410,000 89.0% 4,200
Figure 2: Impact of Lead Time on Supply Chain KPIs
At the 5-day lead time, the system kept a good balance between cost and service, with a 94.5% service level and 3,500 units in stock. But when the lead time went up to 7 days, operational costs went up to ₹1,410,000, service level went down to 89.0%, and average inventory went up to 4,200 units. This showed that the company was relying more on buffer inventories and was less responsive. These results showed that reducing lead time might greatly improve service quality and lower both inventory levels and total operational expenses.
4.4 Sensitivity Analysis: Transportation Cost Change
Transportation cost per unit was adjusted by ±15% to examine its influence on the total cost structure.
Table 4: Effect of Transportation Cost Variation
Cost Adjustment Transportation Cost/Unit (INR) Total Cost (INR)
-15% ₹8.50 ₹1,080,000
Baseline ₹10.00 ₹1,200,000
+15% ₹11.50 ₹1,345,000
The results showed that transportation cost had a linear effect on the overall cost, indicating a direct opportunity for cost savings through route optimization and carrier negotiation.
4.5 Discussion and Strategic Implications
The sensitivity analysis provided key insights:
• Demand Variability: Required agile inventory and replenishment policies to avoid stockouts during demand surges.
• Lead Time Management: Shorter lead times improved service levels and reduced holding costs, validating the value of local sourcing or efficient logistics.
• Transportation Costs: Affected total cost significantly; firms could benefit from integrating TMS (Transportation Management Systems) for cost control.
These findings confirmed the effectiveness of combining supply chain simulation with sensitivity analysis. This convergence allowed stakeholders to visualize the performance under multiple scenarios, supporting better-informed strategic decisions.
V. CONCLUSION
Combining sensitivity analysis with supply chain simulation turned out to be a very effective way to improve operational efficiency. The study showed that changes in important factors like demand, lead time, and transportation cost had big effects on overall performance measures including total cost, service level, and inventory turnover. By simulating these changes, businesses could find weaknesses ahead of time and improve their supply chain plans to deal with uncertainty more effectively. The results showed how important it is to make decisions based on data and how simulation-based analysis may help make supply chains more flexible, cost-effective, and strong.
REFERENCES
1. M. Fathollahi-Fard, K. Govindan, M. Hajiaghaei-Keshteli, and A. Ahmadi, “A green home health care supply chain: New modified simulated annealing algorithms,” Journal of Cleaner Production, vol. 240, p. 118200, 2019.
2. M. Adams et al., “Dakota, a multilevel parallel object-oriented framework for design optimization, parameter estimation, uncertainty quantification, and sensitivity analysis: version 6.13 user’s manual,” Sandia National Laboratories, Albuquerque, NM, USA, Tech. Rep. SAND2020-12495, 2020.
3. F. Goodarzian, A. Navaei, B. Ehsani, P. Ghasemi, and J. Muñuzuri, “Designing an integrated responsive-green-cold vaccine supply chain network using Internet-of-Things: artificial intelligence-based solutions,” Annals of Operations Research, vol. 328, no. 1, pp. 531–575, 2023.
4. F. Goodarzian, V. Kumar, and A. Abraham, “Hybrid meta-heuristic algorithms for a supply chain network considering different carbon emission regulations using big data characteristics,” Soft Computing, vol. 25, pp. 7527–7557, 2021.
5. H. B. Gunay, M. Ouf, G. Newsham, and W. O’Brien, “Sensitivity analysis and optimization of building operations,” Energy and Buildings, vol. 199, pp. 164–175, 2019.
6. H. Huang, H. Wang, J. Gu, and Y. Wu, “High-dimensional model representation-based global sensitivity analysis and the design of a novel thermal management system for lithium-ion batteries,” Energy Conversion and Management, vol. 190, pp. 54–72, 2019.
7. J. B. Oliveira, M. Jin, R. S. Lima, J. E. Kobza, and J. A. B. Montevechi, “The role of simulation and optimization methods in supply chain risk management: Performance and review standpoints,” Simulation Modelling Practice and Theory, vol. 92, pp. 17–44, 2019.
8. J. Gou et al., “Sensitivity analysis‐based automatic parameter calibration of the VIC model for streamflow simulations over China,” Water Resources Research, vol. 56, no. 1, p. e2019WR025968, 2020.
9. L. Chen, T. Dong, J. Peng, and D. Ralescu, “Uncertainty analysis and optimization modeling with application to supply chain management: A systematic review,” Mathematics, vol. 11, no. 11, p. 2530, 2023.
10. M. Dabbaghjamanesh, A. Kavousi-Fard, S. Mehraeen, J. Zhang, and Z. Y. Dong, “Sensitivity analysis of renewable energy integration on stochastic energy management of automated reconfigurable hybrid AC–DC microgrid considering DLR security constraint,” IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 120–131, 2019.
11. M. Silalahi, E. Fatmawati, L. Judijanto, N. Saputra, and H. Herman, “Sensitivity Analysis In Operations Research Decisions: A Case Study On A Mathematical Model,” Library of Progress-Library Science, Information Technology & Computer, vol. 44, no. 2, 2024.
12. N. Ghadimi et al., “An innovative technique for optimization and sensitivity analysis of a PV/DG/BESS based on converged Henry gas solubility optimizer: A case study,” IET Generation, Transmission & Distribution, vol. 17, no. 21, pp. 4735–4749, 2023.
13. P. Borisut and A. Nuchitprasittichai, “Methanol production via CO₂ hydrogenation: sensitivity analysis and simulation—based optimization,” Frontiers in Energy Research, vol. 7, p. 81, 2019.
14. Y. Pan, M. Zhu, Y. Lv, Y. Yang, Y. Liang, R. Yin, and X. Yuan, “Building energy simulation and its application for building performance optimization: A review of methods, tools, and case studies,” Advances in Applied Energy, vol. 10, p. 100135, 2023.
15. Z. Pang, Z. O’Neill, Y. Li, and F. Niu, “The role of sensitivity analysis in the building performance analysis: A critical review,” Energy and Buildings, vol. 209, p. 109659, 2020.
