Page 1 of 9
Advances in Social Sciences Research Journal – Vol. 10, No. 7
Publication Date: July 25, 2023
DOI:10.14738/assrj.107.15043.
Harahap, A. Z. M. K., Nursal, A. T., Sahlan, K., & Sobry, S. C. (2023). The Characteristics of Demand Rates in Inventory Routing
Problem. Advances in Social Sciences Research Journal, 10(7). 76-84.
Services for Science and Education – United Kingdom
The Characteristics of Demand Rates in Inventory Routing
Problem
Afif Zuhri Muhammad Khodri Harahap
Faculty of Business and Management, Universiti Teknologi MARA (UiTM) Cawangan
Terengganu Kampus Dungun, 23000 Sura Hujung Dungun, Terengganu, MALAYSIA
Ahmad Taufik Nursal
Faculty of Industrial Management, Universiti Malaysia Pahang,
Lebuhraya Tun Razak, 26300, Gambang, Pahang, Malaysia
Khairulnizam Sahlan
Faculty of Technology Management and Technopreneurship,
Universiti Teknikal Malaysia (UTeM), Hang Tuah Jaya, 76100 Melaka, MALAYSIA
Suheil Che Sobry
School of Technology Management and Logistics,
Universiti Utara Malaysia, 06010 UUM Sintok, Kedah, MALAYSIA
ABSTRACT
In today's business landscape, demand variability plays a crucial role in
determining the success of companies across various industries. This article
explores the concept of demand variability, encompassing both deterministic and
stochastic demand patterns. We delve into the differences between these demand
types and their implications for businesses. The article emphasizes the significance
of accurate demand forecasting and its role in strategic decision-making.
Deterministic demand, characterized by predictable patterns, allows businesses to
forecast with certainty. On the other hand, stochastic demand introduces
uncertainty, requiring statistical methods and probability theory for estimation
and management. Furthermore, we explore the distinction between stochastic
stationary demand and stochastic nonstationary demand. While the former
maintains consistent statistical properties over time, the latter experiences
fluctuations in its characteristics due to external factors. We highlight the
challenges faced by businesses in forecasting and managing nonstationary demand
and the need for adaptive forecasting methods. To successfully navigate today's
dynamic market, companies must embrace advanced analytics and data-driven
approaches. By leveraging historical data, statistical models, and forecasting
techniques, businesses can gain valuable insights into demand patterns, optimize
inventory management, and make informed strategic decisions. Ultimately,
understanding and managing demand variability is paramount for businesses
seeking to improve customer satisfaction, optimize operations, and enhance their
competitive advantage. This article aims to provide a comprehensive
understanding of demand variability and equip readers with insights and strategies
to tackle the challenges posed by an ever-changing market landscape.
Page 2 of 9
77
Harahap, A. Z. M. K., Nursal, A. T., Sahlan, K., & Sobry, S. C. (2023). The Characteristics of Demand Rates in Inventory Routing Problem. Advances in
Social Sciences Research Journal, 10(7). 76-84.
URL: http://dx.doi.org/10.14738/assrj.107.15043
Keywords: Demand characteristic, deterministic, stochastic, forecasting, optimization.
INTRODUCTION
Today's marketplace is characterized by dynamic and unpredictable consumer behavior,
market fluctuations, and evolving economic conditions. Businesses could rely on simple trend
analysis or historical data to predict demand patterns. As a result, traditional forecasting
methods fall short in providing accurate insights into demand fluctuations, necessitating a
deeper understanding of different demand types and their implications.
Deterministic demand offers a semblance of certainty for businesses. It allows them to make
informed decisions and plan their operations accordingly. However, the real-world scenario
often presents a different picture, with demand patterns influenced by a myriad of factors,
resulting in stochastic demand. This introduces an element of uncertainty that businesses must
grapple with to maintain a competitive edge. Researchers have addressed stochastic demand
in the IRP by incorporating probabilistic models and simulation-based techniques. For instance,
[1] proposed a stochastic programming approach for the IRP that considers demand
uncertainty. They used scenario generation techniques to generate demand scenarios and
developed a solution algorithm to minimize costs and mitigate the risk of stockouts.
Within the realm of stochastic demand, we encounter two distinct categories: stochastic
stationary and stochastic nonstationary demand. The former exhibits consistent statistical
properties over time, albeit with random fluctuations. Businesses can leverage historical data
and statistical models to analyze and forecast such demand patterns. However, the latter
presents a greater challenge, as the statistical characteristics of demand change over time due
to external influences. Companies must adopt adaptive forecasting methods to effectively
navigate these fluctuations.
In addition, other types of demand are called dynamic demand which accounts for scenarios
where customer demand patterns evolve over time. Recent research has focused on addressing
the challenges posed by dynamic demand in the IRP. For example, [2] proposed a dynamic
programming approach that adjusts inventory replenishment and routing decisions in real- time based on changing demand patterns. They demonstrated the effectiveness of their
approach using a case study from the food distribution industry. The types of demand rates are
illustrated in Figure 1.
Fig. 1 Characteristic for demand
Demand
Deterministic
Stochastic
Dynamic
Page 3 of 9
78
Advances in Social Sciences Research Journal (ASSRJ) Vol. 10, Issue 7, July-2023
Services for Science and Education – United Kingdom
Hence, this article aims to highlight the demand variability with the knowledge and strategies
needed to effectively manage it. By exploring the differences between deterministic and
stochastic demand, as well as the nuances between stochastic stationary and nonstationary
demand, we will delve into the methodologies, tools, and approaches available for businesses
to make accurate forecasts and optimize their operations. In the dynamic landscape of today's
market, staying ahead of demand fluctuations is paramount. By embracing advanced analytics,
data-driven decision-making, and adaptive forecasting techniques, businesses can gain a
competitive advantage, enhance customer satisfaction, and achieve operational excellence. Join
us as we embark on a journey to unravel the mysteries of demand variability and unlock the
potential for success in an ever-changing business environment
LITERATURE REVIEW
In the fast-paced and competitive world of business, understanding and effectively managing
demand variability is vital for organizations across industries. The ability to accurately forecast
and adapt to shifting demand patterns can make or break a company's success. This article aims
to delve into the intricacies of demand variability, exploring the concepts of deterministic and
stochastic demand, as well as the challenges associated with stochastic stationary and
nonstationary demand.
Previous study by [3], they provide a comprehensive overview of supply chain management,
emphasizing the importance of demand variability in shaping supply chain strategies. The book
covers various aspects of demand forecasting, inventory management, and risk mitigation in
the face of uncertain demand. [4] explores mitigation strategies for managing supply chain
disruptions caused by demand variability, providing insights. Furthermore, [5] provide a
comprehensive overview of operations management, discussing the importance of demand
variability and its impact on operational decision-making. The book explores forecasting
techniques, capacity planning, and inventory management strategies to address uncertain
demand. Also, [6] provide a comprehensive definition of supply chain management,
highlighting the role of demand variability and the need for effective coordination and
collaboration across the supply chain.
From the global perspective on supply chain management, [7] study on demand variability. It
discusses the impact of demand forecasting on inventory management, production planning,
and customer satisfaction, providing practical insights and case studies. [8] examines the
impact of demand uncertainty on supply chain performance, emphasizing the need for robust
forecasting and risk management strategies to mitigate the effects of demand variability. Others
study review various inventory control models and techniques in the context of stochastic
demand, highlighting the importance of demand variability in effective inventory management
[9].
Earliest study proposed by [10] explores different techniques for combining forecasts from
multiple sources, a useful approach in dealing with stochastic demand. The review offers
insights into the strengths and limitations of various combination methods, providing guidance
for improving demand forecasting accuracy. And also, the study made by [11] which focus on
the demand uncertainty challenge in supply chain management. The book presents strategies
for managing uncertainty, including demand pooling, postponement, and agile supply chain
practices, providing insights into mitigating the effects of stochastic demand.
Page 4 of 9
79
Harahap, A. Z. M. K., Nursal, A. T., Sahlan, K., & Sobry, S. C. (2023). The Characteristics of Demand Rates in Inventory Routing Problem. Advances in
Social Sciences Research Journal, 10(7). 76-84.
URL: http://dx.doi.org/10.14738/assrj.107.15043
[12] offers a review of demand forecasting techniques, highlighting their strengths,
weaknesses, and applicability in different contexts. The study provides valuable insights into
the state of the art in demand forecasting, helping businesses make informed decisions about
forecasting methodologies. [13] review paper summarizes the developments in forecasting
research and practice during the period of 2000-2005. It provides an overview of forecasting
techniques, models, and software, helping businesses stay up-to-date with the latest
advancements in the field. In addition, [14] quantifies the bullwhip effect, a phenomenon
caused by demand variability amplifying as it moves upstream in a supply chain, emphasizing
the importance of accurate demand forecasting. Otherwise, [15] come out with a minimizing
the bullwhip effect in a single product multistage supply chain using genetic algorithm [16]
investigate the effects of demand learning and strategic production capacities on the accuracy
of demand forecasts, highlighting the significance of incorporating these factors into demand
variability analysis. [17] propose a revised classification system for forecasting intermittent
demand, addressing the challenges associated with demand variability in sporadic or
infrequent demand patterns. This systematic review by [18] examines various forecast
improvement methods and their applications. The study presents an extensive overview of
techniques such as judgmental forecasting, statistical models, and collaborative forecasting,
aiding businesses in selecting appropriate approaches for managing stochastic demand.
Hence, several studies have compared and evaluated different approaches for deterministic,
stochastic, and dynamic demand in the IRP. For instance, [19] conducted a comparative study
of deterministic and stochastic models for the IRP. They evaluated the performance of these
models in terms of costs and service levels. Their findings showed that stochastic models
outperformed deterministic models in terms of cost reduction and risk mitigation.
USER QUERY INTENT AND STORAGE OF TAGS
There are many types of demand usually happen in business. Here, we provide the explanation
on the types of demand as shown in Figure 2.
Deterministic Demand
Deterministic demand refers to a situation in which the demand for a product or service can be
precisely predicted or forecasted with complete certainty. In other words, the demand follows
a fixed pattern or trend that can be determined in advance. This type of demand is typically
characterized by stable and consistent patterns, allowing businesses to make accurate forecasts
and plan their operations accordingly.
Stochastic Demand
Stochastic demand, on the other hand, refers to a situation in which the demand for a product
or service is uncertain and can vary randomly over time. Unlike deterministic demand,
stochastic demand is not predictable with complete certainty. Instead, it is influenced by
various factors such as market conditions, customer preferences, economic fluctuations, and
other random variables. Businesses need to use statistical methods and probability theory to
estimate and manage stochastic demand [20].
Stationary and non-stationary Data
Stationarity and non-stationary are terms that are important for understanding changes in the
Earth System [21]. A stationary time series has statistical properties or moments (e.g., mean
Page 5 of 9
80
Advances in Social Sciences Research Journal (ASSRJ) Vol. 10, Issue 7, July-2023
Services for Science and Education – United Kingdom
and variance) that do not vary in time. Stationarity, then, is the status of a stationary time series.
Conversely, non-stationary is the status of a time series whose statistical properties are
changing through time [22].
Stochastic Stationary Demand
Stochastic stationary demand is a type of stochastic demand in which the statistical properties
of demand remain constant over time. Although the demand may fluctuate randomly, the
underlying statistical characteristics, such as mean and variance, remain the same across
different time periods. This allows businesses to analyze historical data and use statistical
models to make predictions about future demand patterns.
Stochastic Nonstationary Demand
Stochastic nonstationary demand refers to a type of stochastic demand in which the statistical
properties of demand change over time. Unlike stochastic stationary demand, the mean,
variance, or other statistical characteristics of demand may vary across different time periods.
This type of demand is typically influenced by external factors such as market trends, changing
consumer behavior, or shifts in economic conditions. Businesses face greater challenges in
forecasting and managing stochastic nonstationary demand due to its changing nature and the
need for adaptive forecasting methods.
In addition, Figure 3 shows the illustration of the principle of stationary and non-stationary
data. More likely, the time series will not be stationary which means that have to identify the
trends present in the series and manipulate the data to become stationary [23]. After the trends
are removed, then the advanced modeling techniques are applied while maintaining the
valuable knowledge of the separated trends, which will be used later.
Fig. 3 An illustration of the principles of stationary and non-stationary data
Sources: [23]
As we observe the graph of the time-dependent mean, there is a consistent trend in the
stationary series. In the case of non-stationary demand series, the trend remains consistent, but
the quantity increases over time. When it comes to non-stationary series, we notice
inconsistencies in demand rates.
Stationary series Non-stationary
series
Non-stationary
series
Non-stationary
series
Time-Dependent
Mean
Time-Dependent
Variance
Time-Dependent
Covariance