• International Journal of Technology (IJTech)
  • Vol 11, No 4 (2020)

Tactical Procurement Planning under Uncertainty in Aromatic Coconut Manufacturing

Tactical Procurement Planning under Uncertainty in Aromatic Coconut Manufacturing

Title: Tactical Procurement Planning under Uncertainty in Aromatic Coconut Manufacturing
Siraprapha Deepradit , Pornthipa Ongkunaruk, Roongrat Pisuchpen

Corresponding email:

Cite this article as:
Deepradit, S., Ongkunaruk, P., Pisuchpen, R., 2020. Tactical Procurement Planning under Uncertainty in Aromatic Coconut Manufacturing. International Journal of Technology. Volume 11(4), pp. 698-709

Siraprapha Deepradit Department of Industrial Engineering, Faculty of Engineering, Kasetsart University, 50 Ngam Wong Wan Rd, Lat Yao, Chatuchak, Bangkok 10900, Thailand
Pornthipa Ongkunaruk Department of Agro-Industrial Technology, Faculty of Agro-Industry, Kasetsart University, 50 Ngam Wong Wan Rd, Lat Yao, Chatuchak, Bangkok 10900, Thailand
Roongrat Pisuchpen Department of Industrial Engineering, Faculty of Engineering, Kasetsart University, 50 Ngam Wong Wan Rd, Lat Yao, Chatuchak, Bangkok 10900, Thailand
Email to Corresponding Author

Tactical Procurement Planning under Uncertainty in Aromatic Coconut Manufacturing

This article presents a tactical procurement plan for an aromatic coconut manufacturer located in Thailand using a mathematical model. Procurement planning is complex because many uncertainty factors are dependent upon the delivery schedule and season, which affect the price of the coconut and the quantity of the order. There were two alternatives for procurement: farmers and coconut collectors. The model used in this research study compared four scenarios: three deterministic models in which every parameter is constant under the worst-case, best-case, and average-case scenarios and a stochastic model simulation. For the deterministic models, the mixed-integer linear programming (MILP) was formulated in a spreadsheet and solved using the Frontline Premium Solver in Excel. In the second model, a Monte Carlo simulation-based MILP with three random variables—demand, price, and the number of coconuts—was solved optimally. The solution indicates how many coconuts will be purchased from farmers and collectors and which truck will be used to deliver the order to maximize total annual profit. The results were compared among four scenarios that could help decision-makers consider the range of profit. The results showed that the stochastic model resulted in less profits than the deterministic model. In the worst-case scenario, profit was lost; in the best-case scenario, profit was gained. In the stochastic model, profits were increasing, except in July. In summary, procurement planning helps factories and farmers realize the price, supply quantity, and demand uncertainties and organize to respond optimally. Proper farm management could increase the productivity of the farm and lessen the supply shortage, resulting in a higher profit. The findings of this research could be applied to assist coconut processors’ supply planning efforts; moreover, proper farm management could increase the farm’s productivity and lessen the supply shortage.

Agriculture; Aromatic coconut; Mixed integer linear programming; Monte Carlo simulation; Procurement


Aromatic coconut is a popular Thai export crop in the world market because its smell and taste are unique. The number of consumers of aromatic coconut is increasing rapidly due to its health benefits. Although the aromatic coconuts are ranked ninth in exports worldwide (Pipatkanaporn, 2016), and there is an increasing trend, supply still cannot satisfy the demand. The supply chain planning for agricultural products is complex due to several uncertainty factors, such as the quantity of the supply, the demand, and purchase prices. Most of these factors depend on seasonality. Moreover, there is a lack of production planning and marketing data in the aromatic coconut supply chain (Gajasuta et al., 2017). Procurement is one of the primary functions of planning, and it is related to purchasing decisions, such as when to procure the product, how many items to order, and from what sources (Bahinipati, 2014; Ogwang and Waweru, 2017). One of the procurement decisions is the make-or-buy decision. This decision helps reduce costs and improve return on assets when combined with heated competition from third-party suppliers. Onyango (2012) examined the effects of procurement planning, Miriti (2018) proposed the effect of procurement planning on supply chain performance in the Kenyan healthcare system, and Chepkesis et al. (2018) indicated the effects of procurement planning on suppliers’ performance in public institutions. Willy and Njeru (2014) investigated the effects of agricultural procurement planning in the agricultural supply chain.

        Many researchers have improved agri-food supply chain management using several tools, of which mixed-integer linear programming (MILP) is the most popular. For example, Chueprasert et al. (2016) identified and resolved the optimal raw milk blending problem for a milk collecting center in Thailand. Ongkunaruk and Ongcunaruk (2015) proposed using MILP to address the coconut sap pickup problem with time windows for a coconut sap juice manufacturer. Dems et al. (2016) studied a wood procurement planning problem in Eastern Canada using MILP. Limpianchob (2017) integrated the harvesting and production plan of aromatic coconut using MILP. Kostin et al. (2018) studied how to use MILP to plan the Brazilian bioethanol supply chains and optimize the net present value of the entire supply chains for the sugar and bioethanol sectors in Brazil. Vanzetti et al. (2019) used MILP to develop an integrated approach for bucking planning, such as the number of stems to be harvested and sawmill production planning, i.e. the used cutting patterns in the forest industry. In real-world situations, stochastic planning is more appropriate than deterministic planning because many factors are uncertain. Govindan and Cheng (2018) studied the advances in stochastic programming and robust optimization for supply chain planning, and Jareonkitpoolpol et al. (2018) determined the optimal blending problem of organic-chemical fertilizer using Monte Carlo simulation. Aziz et al. (2018) used Monte Carlo simulation to improve concrete composites for enhanced X-ray/gamma-ray radiation shielding. Wicaksono et al. (2019) presented the Monte Carlo simulation of net present value based on natural gas price uncertainty and production reservoir capacity. Yatmo et al. (2018) analyzed the occurrence of airborne transmission in healthcare waiting areas. Simulation is also a useful process improvement tool in agro-industry; for example, Pisuchpen and Ongkunaruk (2016) simulated the production of a large-sized frozen chicken manufacturer and proposed a new process for line balancing. Doungpattra et al. (2012) reduced the cost of pallet transport for a pet food manufacturer by simulation the process.

       The aromatic coconut supply chain of a factory consists of farmers, harvesters, collectors, manufacturers, retailers, wholesalers, and domestic consumers and importers for international trade, as shown in Figure 1. Supply chain management includes supply chain planning, procurement, transportation management from harvesting areas to the factory, production, and transportation for the product, distribution, and customer management.

Procurement planning is an important activity because it addresses the operation costs and helps a factory reduce costs. For aromatic coconut supply chains, procurement sources include harvesting at contracted farms and purchasing from local collectors. Each source has different advantages and disadvantages.

Figure 1 An aromatic coconut supply chain in Thailand

      Purchasing costs are lower when coconuts are procured from contracted farms instead of collectors, but this also entails transportation and harvesting costs. Although purchasing from collectors results in the highest purchasing prices, it is essential to do so when there is high demand and the supply from contract farms is insufficient.  Four-wheel trucks and six-wheel trucks are used to transport coconuts from contracted farms. A factory must plan when and how many coconuts to harvest from contracted farms located near its facility. Moreover, the factory needs to decide whether to purchase coconuts from collectors during the peak season. The challenge is that the number of available coconuts from contracted farms and collectors and the purchasing prices fluctuate. At present, the harvest plan is made based on experience, and it is impacted by unbalanced supply and demand. Thus, our objective is to solve the make-or-buy decision with the truck allocation problem to maximize profit under conditions of uncertainty.

       This paper extends the existing results from the deterministic model of Kanjanarat and Ongkunaruk (2014) by using the MILP and the simulation model planning of Deepradit et al. (2017, 2018) who studied the harvest plans for aromatic coconut manufacturing. In our study, we used the Monte Carlo simulation to determine the appropriate harvest age. The model sought the maximum annual profit for fixed period and varied period constraints. The objective was to improve the procurement planning methods under uncertainty factors for aromatic coconut manufacturing in the Ratchaburi Province of Thailand. The solution maximized the total profit. A deterministic model using the Frontline Premium Solver and the stochastic model using Oracle Crystal Ball were presented and compared.


At present, factories lack stochastic environment planning, which does not conform to real-world situations. In this research study, we proposed an optimal tactical procurement plan for aromatic coconut manufacturing using the MILP under the uncertainty simulation model. Aromatic coconut manufacturing faces planning problems due to supply shortages and unbalanced supply and demand. The procurement plan for aromatic coconuts is complex because it had some uncertainty factors, such as price, demand, and supply quantity. This study’s findings impact factory decision-makers and helps then manage uncertainty factors. These factors also significantly impact farm production planning. From May to July, factories face coconut shortage because the supply is insufficient. A factory needs to procure from both contracted farms and collectors. It should also extend the contracted areas to satisfy demand and reduce the risk of shortage, which results in a higher cost. In the future, the stochastic model will use an extended time horizon to plan procurement. The increasing time horizon will increase the variables, scenarios, and processing time. Therefore, future research will attempt to improve stochastic programming by separating it into two-stages or multiple stages (Sawik, 2017; Dillon et al., 2017; Ioannou et al., 2019) to solve larger problems and address more complex systems.


    The authors would like to thank the case study company representatives who generously provided us with details about the farmers’ processes and input data.

Supplementary Material
R2-IE-3897-20200625112902.jpg Figure 1
R2-IE-3897-20200625112916.jpg Figure 2

Andersen, N.J.H., Brandstrup, J., 2008. Monte Carlo Simulation in Crystal Ball 7.3. AARHUS University, Denmark: Analytic Group

Aromatic Coconut Price. Available Online at http://www.taladsimummuang.com, Accessed on December 31, 2019

Aziz, F., Panitra, M., Rivai, A.K., 2018. Synthesis and Monte Carlo Simulation of Improved Concrete Composites for Enhanced X-Ray/Gamma Ray Radiation Shielding. International Journal of Technology, Volume 9(4), pp. 695–706

Bahinipati, B.K., 2014. The Procurement Perspectives of Fruits and Vegetables Supply Chain Planning. International Journal Supply Chain Management, Volume 3(2), pp.  111–131

Banks, J., Carson, J.S., Nelson, B.C., Nicol, D.M., 2005. Discrete-Event System Simulation. 4th Edition. London: Pearson Education

Chepkesis, K., Keitany, P., Kiplel, M., 2018. Effect of Procurement Planning on Suppliers Performance in Public Institutions: A Case of Moi University. European Journal of Logistics, Purchasing and Supply Chain Management, Volume 6(2), pp. 1–9

Chueprasert, M., Ongkunaruk, P., Ongcunaruk, W., 2016. The Study of Business Process and Decision Support of Raw Milk Blending for a Collecting Centre in Thailand. International Food Research Journal, Volume 23(3), pp. 1233–1238

Deepradit, S., Ongkunaruk, P., Pisuchpen, R., 2020. The Study of Forecasting Techniques for Aromatic Coconut Monthly Prices using Individual and Hierarchical Forecasting. Thai Journal of Operations Research, Volume 8(2), pp. 1526

Deepradit, S., Pisuchpen, R., Ongkunaruk, P., 2017. The Harvest Planning of Aromatic Coconut by using Monte Carlo Simulation. In: The 2017 4th International Conference on Industrial Engineering and Applications (ICIEA), Nagoya, Japan, pp. 116–120

Deepradit, S., Pisuchpen, R., Ongkunaruk, P., 2018. The Harvesting Planning of Aromatic Coconut Manufacturing by Considering Uncertainty Harvest Age. In: The 2018 AS Conference, Bangkok, Thailand, pp. 193202 

Dems, A., Rousseau, L., Frayret, J., 2016. A Hybrid Constraint Programming Approach to a Wood Procurement Problem with Bucking Decisions. Constraints, Volume 21, pp. 303–317

Dillon, M., Oliveira, F., Abbasi, B., 2017. A Two-stage Stochastic Programming Model for Inventory Management in the Blood Supply Chain. International Journal of Production Economics, Volume 187, pp. 27–41

Doungpattra, N., Jarupan, L., Ongkunaruk, P., 2012. Simulation for Transport Pallet Cost Reduction in Pet Food Manufacturing: An Empirical Case Study. Packaging Technology and Science, Volume 25(6), pp. 311–319

Gajasuta, P., Aungsuratana, A., Saridnirun, P., 2017. Production Capability Enhancemence on Young Coconut Supply Chain for Exportation in Ratchaburi Provincial Areas. Veridian E-Journal, Volume 10(2), pp. 531–545

Govindan, K., Cheng, T.C.E., 2018. Advances in Stochastic Programming and Robust Optimization for Supply Chain Planning. Computers & Operations Research, Volume 100, pp. 262–269

Ioannou, A., Fuzuli, G., Brennan, F., Yudha, S.W., Angus, A., 2019. Multi-stage Stochastic Optimization Framework for Power Generation System Planning Integrating Hybrid Uncertainty Modelling. Energy Economics, Volume 80, pp. 760–776

Jareonkitpoolpol, A., Ongkunaruk, P., Janssens, G.K., 2018. Determination of the Optimal Blending Problem of Organic-Chemical Fertilizer under Uncertainty. Soil Use and Management, Volume 34(4), pp. 449–460

Jonkman, J., Barbosa-Póvoa, A.P., Bloemhof, J.M., 2019. Integrating Harvesting Decisions in the Design of Agro-food Supply Chains. European Journal of Operational Research, Volume 276(1), pp. 247–258

Kanjanarat, C., Ongkunaruk, P., 2014. Using Integer Programming Optimization for Aromatic Coconut Supply Planning: A Case Study of a Thai Manufacturer. In: 2014 International Conference on Economics and Management (ICEM2014), pp. 560–564

Kostin, A., Macowski, D.H., Pietrobelli, J.M.T.A., Guillén-Gosálbez, G., Jiménez, L., Ravagnani, M.A.S.S., 2018. Optimization-based Approach for Maximizing Profitability of Bioethanol Supply Chain in Brazil. Computers and Chemical Engineering, Volume 115, pp. 121–132

Limpianchob, C., 2017. Integrated of Harvesting and Production Planning in Aromatic Coconut Supply Chain using Mixed-integer Linear Programming. International Journal of Operational Research, Volume 30(3), pp. 360–374

Miriti, L.K., 2018. Effect of Procurement Planning on Supply Chain Performance of Kenya Medical Supplies Authority. Journal of International Business, Innovation and Strategic Management, Volume 1(4), pp. 1–19

Ogwang, A.O., Waweru, L., 2017. Influence of Procurement Planning on Performance of Kisumu Water and Sewerage Company Limited, Kenya. International Journal of Economics, Commerce and Management, Volume 5(5), pp. 767789

Ongkunaruk, P., Ongcunaruk, W., 2015. Coconut Sap Pickup Problem with Time Windows: A Case Study. International Food Research Journal, Volume 22(5), pp. 2088–2092

Onyango, C.J., 2012. Effects of Procurement Planning on Institutional Performance: A Case Study of Mombasa Law Court. International Journal of Science and Research (IJSR), Volume 3(358), pp. 2319–7064

Pipatkanaporn, K., 2016. An Overview of Thai Aromatic Coconut Exporting Industry. Master’s Thesis, Graduate Program, Thammasart University, Thailand

Pisuchpen, R., Ongkunaruk, P., 2016. Simulation for Production Line Balancing of a Large-sized Frozen Chicken Manufacturer. Actual Problems of Economics, Volume 177(3), pp. 397–406

Pradita, S.P., Ongkunaruk, P., Leingpibul, T.D., 2020. Utilizing an Intervention Forecasting Approach to Improve Reefer Container Demand Forecasting Accuracy: A Case Study in Indonesia. International Journal of Technology, Volume 11(1), pp. 144–154

Ratchaburi Provincial Agricultural Extension Office. Available Online at http://www.ratchaburi.doae.go.th, Accessed on June 17, 2020

Richard, O., Koehler, A., 2005. Forecasting, Time Series, and Regression by Bruce Bowerman. 4th Edition. USA: Thomson Brooks Cole

Sawik, T., 2017. Stochastic versus Deterministic Approach to Coordinated Supply Chain Scheduling. Mathematical Problems in Engineering, Volume 2017, pp. 1–15

Make Versus Buy a Decision Framework. Available Online at https://www.academia.edu/28619022/Make_Versus_Buy_A_Decision_Framework, Accessed on December 25, 2019

Vanzetti, N., Broz, D., Montagna, J.M., Corsano, G., 2019. Integrated Approach for the Bucking and Production Planning Problems in Forest Industry. Computers & Chemical Engineering, Volume 125, pp. 155–163

Wicaksono, F.D., Arshad, Y.B., Sihombing, H., 2019. Monte Carlo Net Present Value for Techno-Economic Analysis of Oil and Gas Production Sharing Contract. International Journal of Technology, Volume 10(4), pp. 829–840

Willy, K., Njeru, A., 2014. Effects of Procurement Planning on Procurement Performance: A Case Study of Agricultural Development Corporation, Nairobi. International Journal of Business and Commerce, Volume 3(12), pp. 58–68

Yatmo, Y.A., Putra, N., Harahap, M.M.Y., Saginatari, D.P., 2018. Evaluation of Spatial Layout in Health Care Waiting Areas based on Simulation of Droplet Movement Trace. International Journal of Technology, Volume 9(5), pp. 888–897