Enhancing The Inventory Management Through Demand Forecasting

Enhancing the Inventory Management through Demand Forecasting

Afif Zuhri Muhammad Khodri Harahap^*1, Mohd Kamarul Irwan Abdul Rahim², Noor Malinjasari³, Suzila Mat Salleh⁴, Rabiatul Adawiyah Ma’arof⁵

^1,3,4,5Universiti Teknologi MARA (UiTM) Cawangan Terengganu Kampus Dungun, 23000 Sura Hujung Dungun, Terengganu, MALAYSIA

²School of Technology Management and Logistics, Universiti Utara Malaysia, 06010 UUM Sintok Kedah, MALAYSIA

^*Corresponding Author

DOI: https://dx.doi.org/10.47772/IJRISS.2025.9010221

Received: 12 January 2025; Accepted: 16 January 2025; Published: 13 February 2025

ABSTRACT

Effective inventory management is a cornerstone of successful supply chain operations, ensuring the alignment of stock levels with fluctuating customer demands. Central to this is demand forecasting, a process that utilizes historical data, statistical tools, and market analysis to predict future demand patterns. This paper explores the role of demand forecasting in optimizing inventory levels, reducing operational costs, and improving supply chain performance. Through a detailed review of existing literature, various forecasting techniques—including exponential smoothing, regression models, and bootstrapping approaches—are categorized and analyzed based on their functionalities and applications. Forecasting serves as a fundamental tool for optimizing inventory levels, mitigating the impact of stochastic demand rates, and minimizing associated costs in supply chain management. Key findings emphasize the significance of accurate demand forecasting in mitigating challenges posed by stochastic demand rates, market uncertainties, and extended lead times. The benefits of effective forecasting, such as enhanced inventory management, cost reduction, improved customer service, and strategic resource allocation, are outlined. Furthermore, this study underscores the importance of adapting forecasting methodologies to dynamic market conditions and integrating innovative approaches to sustain competitive advantage. The research concludes by advocating for the continuous advancement of forecasting techniques to address evolving supply chain complexities and support strategic decision-making in a competitive global market. The paper categorizes various forecasting techniques based on their applications, highlighting their significance in addressing challenges posed by fluctuating market demands and lead times. Thus, this research underscores the importance of accurate forecasting in achieving optimal inventory management and operational efficiency within complex supply chains.

Keywords— Supply chain management, Inventory management, Demand, Forecasting

INTRODUCTION

In today’s highly competitive and dynamic market environment, effective inventory management is crucial for the success and sustainability of businesses. Inventory management involves the supervision of non-capitalized assets, or inventory, and stock items. It plays a pivotal role in ensuring that the right quantity of products is available at the right time to meet customer demand while minimizing costs associated with holding and ordering inventory. One of the most significant challenges in inventory management is accurately predicting future demand. Demand forecasting is the process of making estimations about future customer demand using historical data, market analysis, and statistical tools. Accurate demand forecasting enables businesses to optimize their inventory levels, reduce excess stock, avoid stockouts, and improve overall supply chain efficiency.

Inventory management presents multifaceted challenges in supply chain management, necessitating effective forecasting techniques to optimize inventory levels and operational costs. As highlighted in prior research, forecasting plays a pivotal role in anticipating demand fluctuations, thereby enabling proactive decision-making and resource allocation. This paper explores the types of demand forecasting within the context of inventory management, emphasizing its significance in addressing dynamic market conditions and uncertainties. By reviewing existing literature and categorizing forecasting techniques based on their functionalities, this study aims to contribute to the academic discourse on supply chain optimization and operational planning. Through a comprehensive analysis of forecasting methodologies and their implications, this research seeks to offer insights into enhancing inventory management practices and achieving sustainable supply chain performance. By leveraging accurate demand forecasting, businesses can enhance their inventory management practices, leading to improved customer satisfaction, reduced operational costs, and increased profitability.

LITERATURE REVIEW

Forecasting is a critical process that involves predicting future events based on historical data and current trends [1]. It plays a vital role across various sectors, including municipal planning, business strategy, and financial markets [2]. The integration of advanced technologies has significantly enhanced the accuracy and efficiency of forecasting methods, allowing organizations to make informed decisions and respond proactively to changes. Forecasting and optimization are an important part of demand response and in the operation and planning system [3].

Inventories are unknown values related to the situation of stochastic demand rates, forecasting and inventory control are essential to achieve the optimal level of inventory. In implementing vendor managed inventory (VMI) apply the forecasting technique [4]. Forecasting is one of the popular techniques used to solve the inventory management for a different proposed as well as in a manufacturing problem [5]. This technique is usually used to calculate the mean and the standard deviation for customer demands [6]. Another study by [7] apply the saving concepts which also include the forecasting technique in managing the supply chain.

Forecasting techniques have been an essential part of inventory management [5]. This technique is commonly used in the planning of production and supply chains. Forecasting is utilized to obtain the expected demands which is the basic requirement to manage the inventory. The inventory levels are affected by the accuracy of the expected demand and other related costs during the planning horizon. [8] forecast on multi period in determining the inventory. The estimation in forecasting is usually by referring to the secondary data which is historical data from the past [9]. Hence, most of the related studies focused on the stochastic demand during a period [10]; [11]; [12]; [13]. The demand can be less accurate when estimating the forecast for long-term plans and demand is more uncertain. To reduce the total inventory costs, transportation costs and service levels are the elements affected by inventory optimization over the period  [14]. Finally, forecasting techniques should be used to estimate the probability and uncertainty of the demand data to achieve the optimum outcome in the supply chain.

ELEMENT IN FORECASTING

Forecasting is the process of estimating the values for the variables in the future that are unknown [15]. When it comes to forecasting, it is not simply about guessing the amount. However, using previous data to estimate the related variables for future demand required the use of mathematics [16]. So, it is necessary to follow the procedures and policies to avoid the risks. However, the benefit of forecasting inventory management is because of the changes in market demand, length of lead times, and explosive changes in consumption volume [17].

• A change in requirements is once the variable rate is not revolving around a constant average value. Otherwise, it will extract the reserve to deal with the fluctuation.
• The waiting time taken is referred to as the time needed to receive the order data. Changes in consumption may occur if orders take a longer time to arrive. This implies that if the forecasts of consumption throughout this certain period are not done, both compensation and consumption will not achieve the balance.
• The changes in consumption volume are where they are principally due to uncommon circumstances, enabling approximate estimation. The changes might be a step-up in financial gain or similar or a lot of provision of services.

Previous papers implemented forecasting techniques to determine the demand probability distribution [18] [19] [20]. Exponential smoothing is the forecasting technique usually used. This technique is used to estimate the means and the standard deviation (Synder et al., 2004). These two parameters are based on the data trends in which the demand data can be stationary, increase or decrease over time. Usually in the long-term data has a stationary fluctuation. In that case, implementing the exponential smoothing method is the best way to do the estimation [21].

Another technique proposed by [22], is the third-order exponential smoothing forecast. This technique is used to reduce the costs of the bullwhip effect in the supply chain. The researchers proposed a new technique to forecast the inventory policy demand which is using a multi-regression based on forecasting models. The model is used to forecast the total profit for the supplier in a two-echelon supply chain. In this technique, they assumed that the model was developed using the weighing of the element’s method and data transformation. As a result, this technique obtained a higher prediction precision than traditional regression models [23].

TYPES OF FORECASTING TECHNIQUE

The forecasting method has become a popular method for determining the inconsistent value. There are various forecasting methods which are based on their function and the requirements of each forecasting method. Table 1 provides a comprehensive overview of various forecasting techniques and their applications in addressing different aspects of demand forecasting.

TABLE I Technique and Application for Forecasting Demand

Adopted from: Sharif et al., (2016)

Several techniques stand out for their specific applications. For instance, the modification of Holt and Holt Winters methods as highlighted by Altay et al. and Bermudez et al. proves effective in forecasting intermittent demand, considering trends and seasonality. [14] disaggregate time series approach is notable for filtering demand data, separating stable data from uncertain data, and applying single exponential smoothing to stable demand data. Willemain’s modification of the bootstrapping approach demonstrates higher accuracy in forecasting intermittent demand by considering autocorrelation and frequently repeated values.

Furthermore, certain methods like the adjusted method from [37], highlighted by [30], and the exponentially weighted moving average emphasized by [33] focus on forecasting intermittent demand with improved performance metrics, showcasing advancements in addressing this challenging aspect of demand forecasting.

Moreover, the table also outlines traditional methods such as the time series method of exponential smoothing, as highlighted by [38] and the moving average method as noted by [31]. These methods are still relevant in business practice, especially for estimating the level of demand’s mean. Thus, the table illustrates a diverse range of forecasting techniques tailored to specific demands and challenges within supply chain management, emphasizing the importance of selecting appropriate methods based on the nature of demand patterns and objectives in achieving optimal inventory management and operational efficiency.

THE BENEFITS OF FORECASTING

Accurate demand forecasting offers numerous advantages to organizations seeking to optimize their supply chain operations. Fig. 1 shows the benefit of using a forecasting technique to identify the demand needed in the market.

Fig. 1 The benefits of Forecasting

Improved Inventory Management

Accurate demand forecasting enables organizations to maintain optimal inventory levels, reducing the risk of stockouts or excess inventory. This, in turn, leads to cost savings by minimizing carrying costs and obsolescence.

Enhanced Customer Service

By accurately predicting demand, organizations can ensure product availability, thereby improving customer satisfaction and loyalty. Timely delivery of products leads to increased customer trust and repeat business.

Cost Reduction

Effective demand forecasting helps streamline production, procurement, and distribution processes, leading to cost savings across the supply chain. By aligning inventory levels with actual demand, organizations can minimize storage and transportation costs.

Efficient Resource Allocation

With accurate forecasts, organizations can allocate resources such as labor, equipment, and storage space more efficiently. This prevents underutilization or overutilization of resources, optimizing operational efficiency.

Proactive Decision-Making

Accurate demand forecasts provide valuable insights into future market trends and consumer preferences. Organizations can use this information to make proactive decisions regarding production planning, inventory management, and market positioning.

Risk Mitigation

By anticipating demand fluctuations and market uncertainties, organizations can mitigate risks associated with inventory management, production scheduling, and supply chain disruptions. This helps in enhancing the resilience of the supply chain and minimizing potential losses.

Competitive Advantage

Organizations that excel in demand forecasting can respond more effectively to changes in market conditions, gaining a competitive edge over their peers. By consistently meeting customer demand with the right products at the right time, organizations can establish themselves as market leaders.

Strategic Planning

Accurate demand forecasts serve as a foundation for strategic planning and decision-making. Organizations can use this information to set realistic goals, allocate resources efficiently, and develop long-term growth strategies.

CONCLUSIONS

In conclusion, this study has underscored the pivotal role of forecasting techniques in inventory and broader supply chain management contexts. Through an exploration of various forecasting methodologies and their applications, it has become evident that accurate demand forecasting is essential for optimizing inventory levels, minimizing costs, and enhancing operational efficiency. The analysis has revealed that forecasting serves as a cornerstone in mitigating the impact of stochastic demand rates and addressing the challenges posed by fluctuating market demands and lead times. Techniques such as exponential smoothing and regression-based models have emerged as valuable tools for estimating future demand probabilities and uncertainties, enabling organizations to make informed decisions and adapt to dynamic market conditions. Moreover, this study has highlighted the need for continuous research and innovation in forecasting methodologies to meet the evolving demands of modern supply chain environments. By categorizing forecasting techniques based on their functionalities and applications, this research has contributed to the academic discourse on supply chain optimization and operational planning.

Considering the findings presented in this paper, it is evident that accurate forecasting remains essential for achieving optimal inventory management and sustaining competitive advantage in today’s complex business landscape. Future research endeavors should focus on exploring emerging technologies and methodologies to further enhance the accuracy and efficiency of demand forecasting, thereby enabling organizations to navigate uncertainties and achieve resilience in their supply chain operations.

ACKNOWLEDGMENT

We wish to acknowledge Universiti Teknologi MARA, Terengganu Branch for their support and resources that have facilitated this study. The institutional support, including access to academic databases and research facilities, has been instrumental in carrying out this comprehensive information.

REFERENCES

1. M. K. Sandhya Arora, “Forecasting the Future: A Comprehensive Review of Time Series Prediction Techniques,” J. Electr. Syst., vol. 20, no. 2s, pp. 575–586, 2024, doi: 10.52783/jes.1478.
2. W. Salet, R. Vermeulen, F. Savini, and S. Dembski, “Planning for the New European Metropolis: Functions, Politics, and Symbols,” Plan. Theory Pract., vol. 16, no. 2, pp. 251–275, 2015, doi: 10.1080/14649357.2015.1021574.
3. M. Lee et al., “Forecasting Air Quality in Taiwan by Using Machine Learning,” Sci. Rep., vol. 10, no. 1, pp. 1–13, 2020, doi: 10.1038/s41598-020-61151-7.
4. A. Z. M. K. Harahap and M. K. I. Abdul Rahim, “A Single Period Deterministic Inventory Routing Model for Solving Problems in the Agriculture Industry,” J. Appl. Sci. Eng., vol. 25, no. 6, pp. 945–950, 2022, doi: 10.6180/jase.202212_25(6).0005.
5. J. P. Carvallo, P. H. Larsen, A. H. Sanstad, and C. A. Goldman, “Long Term Load Forecasting Accuracy in Electric Utility Integrated Resource Planning,” Energy Policy, vol. 119, pp. 410–422, 2018, doi: 10.1016/j.enpol.2018.04.060.
6. P. Wallström and A. Segerstedt, “Evaluation of Forecasting Error Measurements and Techniques for Intermittent Demand,” Int. J. Prod. Econ., vol. 128, no. 2, pp. 625–636, 2010, doi: 10.1016/j.ijpe.2010.07.013.
7. A. Z. M. Khodri Harahap and M. K. I. Abdul Rahim, “Saving Concepts in Supply Chain Management: A Study on Inventory and Transportation Costs,” Int. J. Acad. Res. Bus. Soc. Sci., vol. 13, no. 6, 2023, doi: 10.6007/ijarbss/v13-i6/17088.
8. M. K. I. A. Rahim, A. Z. M. K. Harahap, B. H. Bolaji, and A. N. A. Ahmad, “Optimizing a Multi-Period Deterministic Inventory Routing Problem in Agriculture Industries,” Pap. Asia, vol. 39, no. 5, pp. 40–47, 2023, doi: 10.59953/comp.by.paperasia.v39i5(b).35.
9. F. Petropoulos et al., “Forecasting: Theory and Practice,” Int. J. Forecast., vol. 38, no. 3, pp. 705–871, 2022, doi: 10.1016/j.ijforecast.2021.11.001.
10. M. K. I. A. Rahim, Y. Zhong, E. H. Aghezzaf, and T. Aouam, “Modelling and Solving the Multi-Period Inventory-Routing Problem with Stochastic Stationary Demand Rates,” Int. J. Prod. Res., vol. 52, no. 14, pp. 4351–4363, 2014, doi: 10.1080/00207543.2014.883470.
11. L. Bertazzi, A. Bosco, and D. Laganà, “Managing Stochastic Demand in an Inventory Routing Problem with Transportation Procurement,” Omega (United Kingdom), vol. 56, pp. 112–121, 2015, doi: 10.1016/j.omega.2014.09.010.
12. F. Niakan and M. Rahimi, “A Multi-Objective Healthcare Inventory Routing Problem: A Fuzzy Possibilistic Approach,” Transp. Res. Part E Logist. Transp. Rev., vol. 80, pp. 74–94, 2015, doi: 10.1016/j.tre.2015.04.010.
13. E. Yadollahi, E. H. Aghezzaf, J. Walraevens, and B. Raa, “Inventory Routing Problem with Non-Stationary Stochastic Demands,” Proc. Int. Conf. Informatics Control Autom. Robot., vol. 2, no. Icinco, pp. 658–665, 2019, doi: 10.5220/0007948506580665.
14. M. Kalchschmidt, G. Zotteri, and R. Verganti, “Inventory Management in a Multi-Echelon Spare Parts Supply Chain,” Int. J. Prod. Econ., vol. 81, no. 82, pp. 397–413, 2003, doi: 10.1016/S0925-5273(02)00284-0.
15. Z. Sazvar, S. M. J. Mirzapour Al-E-Hashem, A. Baboli, and M. R. Akbari Jokar, “A Bi-Objective Stochastic Programming Model for a Centralized Green Supply Chain with Deteriorating Products,” Int. J. Prod. Econ., vol. 150, pp. 140–154, 2014, doi: 10.1016/j.ijpe.2013.12.023.
16. L. Hernandez et al., “A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings,” IEEE Commun. Surv. Tutorials, vol. 16, no. 3, pp. 1460–1495, 2014, doi: 10.1109/SURV.2014.032014.00094.
17. A. A. Syntetos, J. E. Boylan, and S. M. Disney, “Forecasting for Inventory Planning: A 50-Year Review,” J. Oper. Res. Soc., vol. 60, no. SUPPL. 1, 2009, doi: 10.1057/jors.2008.173.
18. Y. Wang, Q. Xia, and C. Kang, “Secondary Forecasting Based on Deviation Analysis for Short-Term Load Forecasting,” IEEE Trans. Power Syst., vol. 26, no. 2, pp. 500–507, 2011, doi: 10.1109/TPWRS.2010.2052638.
19. J. H. Choi, L. A. Myers, Y. Zang, and D. A. Ziebart, “Do Management EPS Forecasts Allow Returns to Reflect Future Earnings? Implications for the Continuation of Management’s Quarterly Earnings Guidance,” Rev. Account. Stud., vol. 16, no. 1, pp. 143–182, 2011, doi: 10.1007/s11142-010-9131-6.
20. Q. J. Wang, D. E. Robertson, and F. H. S. Chiew, “A Bayesian Joint Probability Modeling Approach for Seasonal Forecasting of Streamflows at Multiple Sites,” Water Resour. Res., vol. 45, no. 5, pp. 1–18, 2009, doi: 10.1029/2008WR007355.
21. M. M. Neves and C. Cordeiro, “Exponential Smoothing and Resampling Techniques in Time Series Prediction,” Discuss. Math. Probab. Stat., vol. 30, pp. 87–101, 2010.
22. T. Jia, X. Li, N. Wang, and R. Li, “Integrated Inventory Routing Problem with Quality Time Windows and Loading Cost for Deteriorating Items Under Discrete Time,” Math. Probl. Eng., vol. 2014, 2014, doi: 10.1155/2014/537409.
23. Z. Wang et al., “Selection of Optimal Models for Predicting Growth Stress in Artemisia desertorum by Comparison of Linear Regression and Multiple Neural Networks: Take the Construction of a Green Mine in the Bayan Obo Mine as an Example,” Ecotoxicol. Environ. Saf., vol. 235, no. November 2021, p. 113400, 2022, doi: 10.1016/j.ecoenv.2022.113400.
24. N. Altay, F. Rudisill, and L. A. Litteral, “Adapting Wright’s Modification of Holt’s Method to Forecasting Intermittent Demand,” Int. J. Prod. Econ., vol. 111, no. 2, pp. 389–408, 2008, doi: 10.1016/j.ijpe.2007.01.009.
25. J. D. Bermúdez, J. V. Segura, and E. Vercher, “A Decision Support System Methodology for Forecasting of Time Series Based on Soft Computing,” Comput. Stat. Data Anal., vol. 51, no. 1, pp. 177–191, 2006, doi: 10.1016/j.csda.2006.02.010.
26. M. Kalchschmidt, R. Verganti, and G. Zotteri, “Forecasting Demand from Heterogeneous Customers,” Int. J. Oper. Prod. Manag., vol. 26, no. 6, pp. 619–638, 2006, doi: 10.1108/01443570610666975.
27. A. A. Syntetos and J. E. Boylan, “The Accuracy of Intermittent Demand Estimates,” Int. J. Forecast., vol. 21, no. 2, pp. 303–314, 2005, doi: 10.1016/j.ijforecast.2004.10.001.
28. T. R. Willemain, C. N. Smart, and H. F. Schwarz, “A New Approach to Forecasting Intermittent Demand for Service Parts Inventories,” Int. J. Forecast., vol. 20, no. 3, pp. 375–387, 2004, doi: 10.1016/S0169-2070(03)00013-X.
29. R. Snyder, “Forecasting Sales of Slow and Fast Moving Inventories,” Eur. J. Oper. Res., vol. 140, no. 3, pp. 684–699, 2002, doi: 10.1016/S0377-2217(01)00231-4.
30. A. A. Syntetos and J. E. Boylan, “On the variance of intermittent demand estimates,” Int. J. Prod. Econ., vol. 128, no. 2, pp. 546–555, 2010, doi: 10.1016/j.ijpe.2010.07.005.
31. S. Makridakis, “Time-Series Analysis and Forecasting: An Update and Evaluation,” Int. Stat. Rev. / Rev. Int. Stat., vol. 46, no. 3, p. 255, 1978, doi: 10.2307/1402374.
32. R. Verganti, “Order overplanning with uncertain lumpy demand: A simplified theory,” Int. J. Prod. Res., vol. 35, no. 12, pp. 3229–3248, 1997, doi: 10.1080/002075497194057.
33. M. Taillard, E. D., Laporte, G., & Gendreau, “Operational Research Society is collaborating with JSTOR to digitize, preserve, and extend access to Journal of the Operational Research Society. ® www.jstor.org,” J. Oper. Res. Soc., vol. 47, no. 8, pp. 1065–1070, 1996.
34. M. Fisher, “Reducing the Cost of Demand Uncertainty through Accurate Response to Early Sales Author(s): Marshall Fisher and Ananth Raman Source: Operations Research, Vol. 44, No. 1, Special Issue on New Directions in Operations Published by: INFORMS Stable,” vol. 44, no. 1, pp. 87–99, 2016.
35. M. L. Fisher, J. H. Hammond, W. R. Obermeyer, and A. Raman, “Making Supply Meet Demand in an Uncertain World,” Harv. Bus. Rev., pp. 83–93, 1994, [Online]. Available: http://prof.usb.ve/nbaquero/03 – Making Supply meet Demand – HBR.PDF
36. D. J. Wright, G. Capon, R. Pagé, J. Quiroga, A. A. Taseen, and F. Tomasini, “Evaluation of forecasting methods for decision support,” Int. J. Forecast., vol. 2, no. 2, pp. 139–152, 1986, doi: 10.1016/0169-2070(86)99002-3.
37. W. A. Donaldson, “Operational Research Society is collaborating with JSTOR to digitize, preserve, and extend access to Operational Research Quarterly (1970-1977),” Oper. Res. Q., vol. 28, no. 3, pp. 663–670, 1977.
38. M. Brown and P. Taubman, “A Forecasting Model of Federal Purchases of Goods and Services,” J. Am. Stat. Assoc., vol. 57, no. 299, pp. 633–647, 1962, doi: 10.1080/01621459.1962.10500552.