Demand Forecasting for Improved Inventory Management in Small and Medium-Sized Businesses

Abstract

Small and medium-sized businesses are constantly seeking new methods to increase productivity across all service areas in response to increasing consumer demand. Research has shown that inventory management significantly affects regular operations, particularly in providing the best customer relationship management (CRM) service. Demand forecasting is a popular inventory management solution that many businesses are interested in because of its impact on day-to-day operations. However, no single forecasting approach outperforms under all scenarios, so examining the data and its properties first is necessary for modeling the most accurate forecasts. This study provides a preliminary comparative analysis of three different machine learning approaches and two classic projection methods for demand forecasting in small and medium-sized leathercraft businesses. First, using K-means clustering, we attempted to group products into three clusters based on the similarity of product characteristics, using the elbow method's hyperparameter tuning. This step was conducted to summarize the data and represent various products into several categories obtained from the clustering results. Our findings show that machine learning algorithms outperform classic statistical approaches, particularly the ensemble learner XGB, which had the least RMSE and MAPE scores, at 55.77 and 41.18, respectively. In the future, these results can be utilized and tested against real-world business activities to help managers create precise inventory management strategies that can increase productivity across all service areas.

Full text

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 56
DEMAND FORECASTING FOR IMPROVED INVENTORY
MANAGEMENT IN SMALL AND MEDIUM-SIZED BUSINESSES
Dian Indri Purnamasari1,
Vynska Amalia Permadi
2*
,
Asep Saepudin
3
,
Riza Prapascatama Agusdin
4
1 Department of Accounting, Universitas Pembangunan Nasional Veteran Yogyakarta
2*,4 Department of Informatics, Universitas Pembangunan Nasional Veteran
Yogyakarta
3 Department of International Relations, Universitas Pembangunan Nasional Veteran
Yogyakarta
email: dian_indri@upnyk.ac.id1, vynspermadi@upnyk.ac.id2*, asep.saepudin@upnyk.ac.id3,
rizapra@upnyk.ac.id4
Abstract
Small and medium-sized businesses are constantly seeking new methods to increase productivity
across all service areas in response to increasing consumer demand. Research has shown that
inventory management significantly affects regular operations, particularly in providing the best
customer relationship management (CRM) service. Demand forecasting is a popular inventory
management solution that many businesses are interested in because of its impact on day-to-day
operations. However, no single forecasting approach outperforms under all scenarios, so
examining the data and its properties first is necessary for modeling the most accurate forecasts.
This study provides a preliminary comparative analysis of three different machine learning
approaches and two classic projection methods for demand forecasting in small and medium-sized
leathercraft businesses. First, using K-means clustering, we attempted to group products into three
clusters based on the similarity of product characteristics, using the elbow method's
hyperparameter tuning. This step was conducted to summarize the data and represent various
products into several categories obtained from the clustering results. Our findings show that
machine learning algorithms outperform classic statistical approaches, particularly the ensemble
learner XGB, which had the least RMSE and MAPE scores, at 55.77 and 41.18, respectively. In
the future, these results can be utilized and tested against real-world business activities to help
managers create precise inventory management strategies that can increase productivity across
all service areas.
Keywords: Demand Forecasting, Inventory Management, Machine Learning, Small and Medium-
Sized Businesses
Received: 09-01-2023 | Revised: 28-03-2023 | Accepted: 31-01-2023
DOI: https://doi.org/10.23887/janapati.v12i1.57144
INTRODUCTION
Data analytics is no longer limited to
huge multinational companies due to
advancements in data processing and
storage capacity. However, it can be critical
in developing strategies to support
businesses of all sizes. On the other hand,
small and medium-sized businesses should
be able to use data analytics to uncover
information such as client purchase habits,
demand forecasting, and effective customer
relationship management. According to
Bokman et al. [1], businesses that use
consumer analytics beat their competition by
126%. In contrast, failing to consider data
analysis in strategy formulation may put you
at a competitive disadvantage.
Furthermore, increased consumer
demand for goods and services has
encouraged small and medium-sized

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 57
businesses to look for ways to improve
operational efficiency in any service domain.
Internal logistics and warehousing are high-
growth sectors that can increase an
organization's operational efficiency [2], [3]
and have been the subject of several
studies, as evidenced by the fact that
influential organizations have conducted
them [1]. Businesses have encouraged and
supported the fulfillment of customer
requirements and expectations throughout
the supply chain and warehouse activities,
which are critical to a company's operational
performance. They discovered that inventory
management significantly impacts logistics
performance indices, particularly for
organizations looking to reduce costs and
improve product formulation and delivery
procedures.
Inventory management refers to
administering and maintaining a company's
stock or inventory. In this context, the word
"inventory" refers to raw materials, auxiliary
materials, items in production, finished
goods, and spare parts. Several intelligent
inventory management solutions have been
investigated to increase inventory
management effectiveness [4]–[6]. Inventory
management is closely linked to customer
relationship management, and several
technologies are used to meet consumer
demand by shifting from traditional to
innovative inventory management. Various
approaches are available for forecasting
client demand. Two possible strategies are
to employ statistical analytic methodology
and data mining approaches. A prediction
based on statistics or mathematical analysis
strongly relies on the quality of historical data
(such as transaction history/product orders).
As a result, if an organization has archives of
high-quality data, making more accurate
estimations will be easier. Organizations that
use this inventory management technique
typically have a quantitative analytic staff
that analyzes historical data on a regular
basis to uncover potential patterns and
trends in market demand. The requirements
analysis is based on historical customer
demand transactions and will be used to
manage the firm's inventories.
X. Guo's research [7] observed past
order data to estimate client demand. The
initial investigation consisted primarily of
scanning the company's website for
information on product orders. Then, utilizing
data mining tools, the study was undertaken
on projected future consumer requests until
a more efficient inventory management
policy was established. Inventory
management using data mining and sales
history data may significantly reduce total
inventory expenses. As previously stated,
data quality is critical for achieving high-
significance estimations and efficiency.
However, the previous study showed that
the gathered findings might still be
improved/optimized because web-collected
data is typically poor-quality and requires
numerous additional procedures to be pre-
processed. Another study [8] used data
mining techniques to control inventories and
focused on associating historical data with
decision-making. A complete analysis was
conducted based on the observed
intercorrelation to boost forecast accuracy,
and the authors believe that the company's
expenses and consumption will be lowered.
Moreover, a predictive analytics-based
approach for inventory management that
uses machine learning algorithms to analyze
sales data and predict future demand has
already conducted. The authors focus on the
use of time-series forecasting models to
make accurate demand forecasts and
optimize inventory levels. The proposed
approach also incorporates a dynamic
pricing model that adjusts prices based on
demand patterns, which can help to further
optimize inventory and reduce costs. The
paper presents a case study demonstrating
the proposed approach's effectiveness in
improving inventory management for an
online retailer.
Moreover, Zhang’s [9] literature
review comprehensively reviews the existing
literature on inventory management for
spare parts. The author discusses various
approaches and techniques for spare parts
inventory management, including
forecasting demand, setting inventory levels,
and determining reorder points. The paper
also examines the challenges and
opportunities associated with spare parts
inventory management, such as intermittent
demand, obsolescence, and service level

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 58
agreements. Overall, the paper provides a
useful resource for researchers and
practitioners seeking to improve spare parts
inventory management in various industries,
including manufacturing, aerospace, and
healthcare.
This research aims to utilize various
analysis techniques to determine the most
appropriate model for one of the Small and
Medium-Sized Leathercraft Businesses in
Yogyakarta, Indonesia, as in previous
studies. The selected leathercraft industry is
among the largest SMEs in Yogyakarta,
established in 2011, and sells its products
through various channels. The company has
not yet employed a data analytics approach
in its decision-making process. Thus, this
study seeks to provide valuable insights into
the business by suggesting a demand
forecasting model that aligns with service
requirements, such as avoiding stock-outs or
over-orders. To achieve the company's goal
of delivering the best services to its
customers, we will identify the most suitable
demand forecasting technique that allows
them to predict future monthly demand
forecasts.
Since our objective is to develop the
most relevant forecasting model concepts to
assist the company in managing its inventory
of handcrafted products across multiple
parameters, the main takeaway of our study
is that it is crucial to construct the forecasting
model with particular consideration for the
type of dataset in order to achieve higher
accuracy. We will use a transactional
historical time-series dataset to compare
several demand forecasting algorithms. This
work will make several contributions,
including: (1) employing machine learning
clustering to categorize various products
with similar characteristics for efficiency, (2)
utilizing demand forecasting based on
statistical computation and machine learning
algorithms to predict demand and provide a
comparative analysis of each model's
performance, and (3) suggesting the best
forecasting model for one of the largest
leathercraft SMEs in Yogyakarta's inventory
management.
METHOD
Forecasting models can be classified
into two types: qualitative and quantitative,
each with three approaches based on
analytical methodology: statistical, data
mining/machine learning-based, and hybrid.
The literature on business forecasting
outlines continuous and intermittent demand
techniques based on underlying market
demands for products to manage inventory.
Identifying trends such as intermittency is
critical for selecting the best forecasting
strategy. A typical approach that
emphasizes expert judgment or client
viewpoints above quantitative analysis is
qualitative forecasting, also known as
judgmental forecasting. Qualitative
forecasting is desirable and frequently
necessary in the absence of historical data
to support quantitative methodologies or
when past values have little or no influence
on future events. However, qualitative
forecasting is prone to bias due to its reliance
on human opinion, which can be influenced
by personal and political objectives. Experts
and forecasters also tend to place greater
emphasis on recent historical happenings,
resulting in estimates that are close to the
current reference point, adding another
challenge to appraising predictions.
Quantitative forecasting uses
mathematical (statistical) models to predict
the future. Since quantitative forecasting
models are objective, they should be used
whenever there is a substantial amount of
previous data that can be logically
associated with predicted values (i.e., past
historical data have unique trends and
continuous values). Cross-sectional or time-
series data can be used for quantitative
forecasting, with time-series data being the
most common type used for predictions.
Quantitative forecasting uses various
models based on unique combinations of
predictive parameters and are included in
one of two categories: time-series or
explanatory. Explanatory forecasting models
aim to identify the factors that affect the
target variable, such as inflation, while not
taking previous trends into consideration.
Regression analysis is the most well-known
method in the field of forecasting.
Regression projections explore the

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 59
relationships between one or more
dependent variables and an independent
variable.
The following explanation covers a
variety of time forecasting methodologies
and current publications on demand
forecasting applications, split into three
categories: statistical, machine learning, and
hybrid.
Statistical Procedures
Time-series forecasting, particularly
demand and sales forecasting, is often
accomplished through statistical methods.
Furthermore, statistical methods can be
broadly classified as either continuous,
where a constant time-series pattern
captures the demand history, or non-
continuous. Additionally, there is an ad hoc
intermittent special analytic technique for
slow-moving items. As part of our literature
review, in this section, we will
comprehensively discuss several examples
of well-known classic statistical forecasting
approaches and some of the straightforward
methodologies that are frequently used.
The implementation of forecasting
methods on time series data relies mainly on
Exponential Smoothing models. This
method generates projections as the
weighted average of previous data. There
are several approaches to exponential
smoothing, including simple, double, and
triple Exponential Smoothing models. The
Autoregressive Integrated Moving Average
model [10] combines the best aspects of
autoregressive and moving average models
by differentiating time series data. ARIMA
iteratively executes three stages using the
Box-Jenkins method: model detection,
parameter estimation, and diagnostic
checking. The Theta Model [11] is frequently
applied in time series forecasting,
particularly in supply chain management and
planning, because of the precision of its point
forecasts [12]. The Vector Autoregressive
(VAR) model [13] extends the univariate
autoregressive model's capabilities to
multivariate time series prediction. It has
become a common tool for time series
forecasting due to its ease of use and
versatility. However, selecting the variables
and lags employed in a VAR model is
essential. To keep this method performing
well, limit the number of variables to the
correlated ones.
Machine Learning Methods
Machine learning (ML) approaches
were first used for forecasting in 1964, but
little follow-up work was done for several
decades. Since then, several studies have
been conducted on applying ML systems to
demand to forecast. The most popular time-
series forecasting models include CART
regression trees [14], Generalized
Regression Neural Networks [15], K-Nearest
Neighbor regression [16], Bayesian Neural
Networks [17], Gaussian Processes
regression [18], Long Short Term Memory
network [19], Multi-Layer Perceptron [20],
Recurrent Neural Networks [21], and Radial
Basis Functions [22]. Several large-scale
comparative studies, most of which are
empirical, have reviewed different
approaches to regression or time-series
forecasting challenges. In a significant
comparative study [23], the Multi-Layer
Perceptron and Gaussian Processes
regression were the most effective
algorithms, followed by Bayesian Neural
Networks and Support Vector Regression.
Another study [24] using time-series data
points discovered that the model with the
best performance was Radial Basis
Functions, followed by Recurrent Neural
Networks and Multi-Layer Perceptron.
Generalized Regression Neural Networks,
on the other hand, had the worst
performance according to recent
comparison research [25], and Multi-Layer
Perceptron is the most viable forecasting
strategy among Machine Learning models.
Although each method has advantages and
weaknesses, data quality is critical for any
empirical study seeking to evaluate the
performance of a specific forecasting
methodology. As such, there is no "generic"
guaranteed technique for making
predictions. The nature of the data and the
situation in which the forecast is being made
should affect the methodology chosen.
Research also shows that Neural Networks
and their variants perform the best of all
machine learning algorithms when it comes
to predicting time series.

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 60
Hybrid Approaches
This approach aims to bring together
the best features of many statistical and ML-
based forecasting techniques. Hybrid
approaches include methods like SOM-SVR
and ANN-ARIMA. To provide better learning
and more precise prediction results, SOM-
SVR uses a Self-Organizing Map to first split
the dataset into clusters, then a Support
Vector Regressor delivers grouped data.
Tay and Caos' research [26] utilized the
hybrid SOM-SVR for financial time series
forecasting. Moreover, ANN-ARIMA has
produced more accurate forecasts because
of its ability to cover linear and nonlinear time
series components [27]. Time-series
forecasting problems, including the
prediction of energy prices and stock market
movements [28], have benefited from this
hybrid approach.
We concluded from our thorough
investigation that no single forecasting
approach outperforms all scenarios. For the
most accurate forecasts, it is necessary to
first examine the data and its properties. This
research aimed to evaluate which
forecasting methodologies would be the
most efficient for one of the leathercraft
Small and Medium-Sized Businesses in
Yogyakarta, Indonesia. The steps we took to
complete our contribution are detailed in the
following parts.
Figure 1. CRISP-DM methodology [29]
First, we applied a Cross Industry
Standard Process for Data Mining (CRISP-
DM) [29] approach to resolve our demand
forecasting comparative research. The
stages of CRISP-DM are depicted in Fig. 1.
CRISP-DM methodology is the most widely
disseminated standard process model that
describes common data mining techniques
and phases. The initial phase is to analyze
the business process and available data,
followed by data preparation and modeling,
and lastly, evaluate the model. This study,
however, did not encompass the deployment
step. The procedures involved at each level
are outlined below.
Business & Data Understanding
After collecting the necessary
transactional data from various sales
channels in the leathercraft industry, we first
evaluate the data that will be used to create
a solution as the initial step in developing a
demand forecast. Therefore, the exploratory
data analysis process involves the following
steps: first, visualizing historical sales and
demand data; second, analyzing the primary
characteristics of demand and sales time
series; and third, examining the cross-
correlation between demand and other time-
dependent variables (such as product price).
Additionally, we have incorporated certain
features into the datasets. For example, we
included vacation dates in our analysis to
determine if external factors could aid in
demand forecasting. While compiling holiday
information, we considered both the general
public's interests and observable school
holiday periods.
Data Preparation
After completing the above stages,
and considering that numerous products
have already been sold, we recommend
grouping the products into specific clusters
to generate a demand prediction forecast for
each group. To classify products with similar
characteristics into multiple categories, we
will use K-Means, a machine learning
clustering approach. We will utilize
hyperparameter tuning techniques such as
the elbow method to determine the optimal
number of k-clusters that reflect the best
number of product groups. We do not wish
to specify the exact number of categories
required, as we aim to use a machine
learning implementation to find the most

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 61
suitable number of clusters based on their
characteristics.
Our objective here is to identify the
optimal number of clusters that exhibit
similar characteristics in the data. The
parameter "k" is used to define the number
of groups into which the data should be
divided. The elbow method is utilized as a
hyperparameter tuning technique to
determine the ideal number of clusters. The
appropriate number of clusters is achieved
when the SSE sharply declines initially and
then levels off as k increases. This
phenomenon can be evaluated through the
SSE plot of each k iteration.
Modeling
Table 1 summarizes the models
investigated in this comparative analysis,
aimed at comparing machine learning and
traditional (classical) forecasting methods.
Therefore, we chose SARIMA, a common
univariate methodology, as well as
SARIMAX, a multivariate classical
alternative, to be compared with machine
learning algorithms in our study. We also
investigated machine learning approaches
capable of capturing nonlinear relationships,
taking into account the probability of temporal
dependencies. For this purpose, we built a
Recurrent Neural Network (RNN) using Long
Short-Term Memory (LSTM) network cells.
Additionally, we included Extreme Gradient
Boosting in this comparative study, as
integrated or ensemble approaches have
been found to perform better than standalone
ones in certain cases [30], [31]. Lastly, we
included a Bayesian approach to model
uncertainty using Gaussian Process
Regression.
Table 1. Comparative analysis algorithm list
Algorithm Abbreviation
Algorithm
Abbreviation
Seasonal Autoregressive
Integrated Moving Average
SARIMA
Seasonal Autoregressive
Integrated Moving Average with
external factors
SARIMAX
Long Short-Term Memory
Network
LSTM
Extreme Gradient Boosting
(XGBoost)
XGB
Gaussian Process Regression
GPR
We used time series cross-validation
with regular model fitting to simulate the
operational demand forecasting scenario
with frequently updated business sales
reports and a potentially shifting data
distribution. Firstly, the 30 most recent
months were selected as the training set to
determine the best hyperparameter
combination. The remaining data was used
as the testing set. The model configuration
with the best performance across the entire
test set was chosen based on the evaluation
metrics.
Evaluation
We used the Root Mean Squared
Error (RMSE) in Equation 1 and the Mean
Absolute Percent Error (MAPE) in Equation 2
for model evaluation. A lower score indicates
improved performance across all
assessment metrics. We added a constant
value to the denominator to avoid division by
zero when using MAPE. MAPE values can
potentially increase significantly when
demand numbers are close to zero, which is
a common situation in daily observation
datasets.
 
󰇛󰇜

 (1)
 
󰇻

󰇻

 (2)
where  is the number of data points,  is
the i-th measurement, and  is its
corresponding prediction.
RESULT AND DISCUSSION
This section summarizes our
findings, followed by an in-depth analysis of
our experimental research. After studying
the characteristics of historical sales data,
we selected several product characteristics
(Product Size, Product Motif, Product Color),
sales amount, sales type, and unit pricing as
clustering features. An overview of the data,
including the attributes and value
distributions for each attribute, is provided in
Table 2.

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 62
Then, we employed K-means
clustering to automatically cluster the data
based on similar characteristics. Our aim
was to determine the best number of clusters
that represent the best data group with
similar features. The k parameter indicates
the number of groups into which the data
should be aggregated. This research applies
the elbow approach as hyperparameter
tuning to determine the best number of
clusters. The SSE is the elbow method's
core index, representing the clustering
impact indicating the clustering inaccuracy of
all samples under evaluation of different k
possibilities. When the number of clusters is
fewer than k, increasing k amplifies the
degree of aggregation of each cluster, hence
reducing the SSE. k is considered as the
correct amount of clusters when the SSE
initially decreases sharply and then levels off
as k increases.
Table 2. Data Overview
Attributes
Value Distributions
Product Name
More than thousand unique
product name
Product Size
Small, Medium, Large
Product Motif
More than fifty unique
product motif (batik motif,
e.g.: Sidomukti, Parang, etc.)
Product Color
More than thirty unique
product color (e.g. Havana,
Borduk, etc.)
Sales Amount
12 ~ 200
Sales Type
In stock, Pre-order
Unit Pricing
75.000 ~ 1.195.000
For each iteration, test results to
determine the proper number of k clusters
and their SSE value are represented in the k
and SSE diagram in Fig 2. We aimed to vary
the value of k from 1 to 8, and the graph
below shows that three clusters are sufficient
for grouping our transactional dataset. Three
is chosen since SSE initially decreases
sharply as seen in the figure below, then
levels off as k increases.
Then, the obtained k is used to group
all the products into three cluster using K-
Means algorithm. Through cluster result data
analysis, we concluded that the third
category of products has the highest sales
volume, the highest sales frequency, and the
lowest price. We labeled this category as
"Prioritized product" since these products
have the highest customer demand and must
always be kept in stock. The first category of
products ranks second in terms of sales
volume and frequency, and the unit price is
also lower. So we named this group "Popular
product," which should be kept in stock in
moderate quantities. The second category of
products is more expensive than the first and
third categories, and its sales are still less
frequent; hence we labeled these products
as an "Exclusive Collection," which should be
kept in limited quantities to provide
alternative options while not interrupting cash
flow. These classification results can be used
to analyze whether the business's stock
inventory is adequate on an operational
basis.
Figure 2. Elbow method SSE plot results to
determine the best  cluster is three
The next step to achieve successful
inventory management is to establish the
exact amount of stock levels for each
category mentioned above. The most
straightforward strategy is to guess the
proportion of stock in each category by trial
and error. Unfortunately, such approaches
impair a company's management team's
ability to recognize critical moments.
Therefore, the following section explores
several demand forecasting methodologies
to provide the manager with the best demand
forecasting method, completing the inventory
management process. Our analysis will only
provide a rough estimate of which algorithm
is most likely to produce the best results in
our case study. In the future, the manager will
need to implement a system that utilizes one
of these demand forecasting methods to be

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 63
adequately prepared to develop inventory
management strategies.
Before machine learning algorithms
can use the series data, which contains
historical transactional data from the last
three years (2020-2022), it must be turned
into a supervised learning scenario. In other
words, we convert numerical inputs into
outputs by taking the features of earlier time
steps t_2 and t_1 as input and output the
supervised value of the current time step t.
Then, we divide the dataset into training and
testing data. We use the first 30 months of
data for training and the last 6 months for
testing.
Hyperparameter tuning is a machine-
learning technique that takes a snapshot of a
model's performance at a given time and
compares it to earlier snapshots. Every
machine learning method requires the
establishment of hyperparameters before
developing a model into a real intelligence
system. By adjusting the hyperparameters of
the model, we can boost our model's
performance and validate the chosen
parameters using the validation dataset.
Before we describe our procedure
further, it is important to understand the
concept of cross-validation, which is a critical
step in the hyperparameter tuning process.
Cross-validation (CV) is a statistical
technique used to evaluate the efficacy of
machine learning models. Normally, we can
predict how well a model will do on unknown
data only after it has been trained. In other
words, we cannot tell if the model is
underfitting, overfitting, or performing well by
evaluating how it performs on unknown data.
When the data supplied is limited, cross-
validation is considered a highly beneficial
way to establish a machine learning model's
performance. To perform cross-validation,
we set aside some of the data for testing and
validation, meaning not all subsets will be
used to train the model; several data points
will be kept for future use to validate the
model's performance. K-Fold is a popular
cross-validation strategy, and we used it to
validate our model. We used a value of 10 for
K in our cross-validation process for each
algorithm. Tables 3–5 display the
hyperparameter scenarios used by
SARIMAX, LSTM, and GPR in this study.
Table 3. Seasonal Autoregressive Integrated
Moving Average (with external factors)
Hyperparameter
Parameter
Values
///
[0, 1, 2, 3]
/
[0, 1]

[False, True]

[False, 'log', 'pw']
Table 4. Long Short-Term Memory Network
Hyperparameter
Parameter
Values
activation_function
ReLu
optimizer
Adam
dropout_rate
[0.0, 0.5]
batch_size
[4, 8, 16, 32]
learning_rate
[1e-3, 1e-2, 1e-1]
min_val_loss_improvement
[0.01, 0.1]
max_epochs_wo_improvement
[10, 30, 50, 100]
lstm_hidden_dim
[5, 10, 15, 50]
lstm_num_layers
[1, 2]
seq_length
[1, 4]
Table 5. Extreme Gradient Boosting
Hyperparameter
Parameter
Values
learning_rate
[0.05, 0.1, 0.3]
max_depth
[3, 5, 7]
subsample
[0.3, 0.7, 1]
n_estimators
[10, 100, 500, 1000]
gamma
[0, 1, 10]
alpha
[0, 0.1, 1, 10]
reg_lambda
[0, 0.1, 1, 10]
Below is a summary outlining several
hyperparameters that can be adjusted while
optimizing GPR. Since the kernel function is
the most influential GPR parameter, we
experimented with a wide variety of kernel
functions as well as specific combinations of
a maximum of three different kernels.
1. 󰇛󰇜
2. 󰇛󰇜
3. 󰇛󰇜
4. 󰇛󰇜
5. 󰇛󰇜
6. 󰇛 
󰇛󰇜  
󰇜
7. 󰇛  󰇛󰇜 
󰇜
8. 󰇛 
󰇛󰇜  
󰇜󰇠
To thoroughly examine our
experiments, we have prepared a summary
of the results for each of the five demand

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 64
forecast methods investigated and the best
evaluation metric results for each
hyperparameter iteration. These results are
shown in Table 6. SARIMA, the classic
projection method, has an RMSE of 93.13
and a MAPE of 85.29. The SARIMAX
algorithm, an extension of SARIMA,
performs better with an RMSE of 48.96 but
has a higher MAPE of 89.85. The LSTM
algorithm has a RMSE of 85.36 and a MAPE
of 82.41. The ensemble learner XGB
outperforms other algorithms with a RMSE of
55.77 and a MAPE of 41.18, making it the
most accurate algorithm for demand
forecasting in this study. Finally, the
Gaussian process regression (GPR) has a
RMSE of 63.41 and a MAPE of 77.69.
Table 6. Comparison of metric evaluation results
of all demand forecast model
Our findings indicate that the
machine learning-based techniques
outperform the classic statistical approach in
forecasting demand. XGB yields the best
performance in terms of RMSE and MAPE,
as highlighted in the table. In addition, the
XGB ensemble outperformed the rest of the
machine learning models. These findings
demonstrate that the ensemble learning
approach is preferable for capturing data
phenomena in this use case. Compared to
the other models evaluated, the results also
reveal that XGB's superior performance can
overcome the limited quantity of data used in
this study, where only data from the previous
three years were used. LSTM and GPR may
not perform well in this case because the
amount of information available significantly
impacts the machine learning algorithms'
performance. SARIMAX's comparable
strong performance might be due to extrinsic
variables such as distinct data dissemination
in the training set, which could inhibit
prediction. However, since all superior
approaches were multivariate, the findings
show that external inputs, such as holiday
data and clusters' generated characteristics,
lead to increased predicting ability. This
extra information is also considered valuable
in machine learning-based approaches.
Based on the evaluation matrix, we
will recommend the use of XGB projection as
the demand forecasting model for our case
study, one of Yogyakarta's Leathercraft
Small and Medium-Sized Businesses.
However, it is crucial to consider the impact
of the new normal era after COVID-19. We
suggest first using historical data as training
data to determine if it fits well, as there may
be different sales trends during the
pandemic.
CONCLUSION
This study presents a preliminary
comparative analysis of three Machine
Learning approaches and two classic
projection methods for demand forecasting in
Leathercraft Small and Medium-Sized
Businesses. Firstly, we utilized K-means
clustering to group the products into three
clusters based on the similarity of product
characteristics, using the elbow method's
hyperparameter tuning. Furthermore, the
data was summarized to represent the
significance of the clustering results. The
"Prioritized product" cluster had the highest
sales volume and frequency, and the price
was also relatively low. The products in the
"Popular product" cluster ranked second in
terms of sales volume and frequency, and
the price was also relatively low. The
"Exclusive collection" cluster contained more
expensive products than the first two
categories, and its sales were less frequent,
and the unit price was also lower. According
to strategic inventory management
recommendations, "Popular Products"
should be retained in moderation, "Priority
Products" should be kept in large quantities,
and "Exclusive Collections" should be
preserved in limited quantities to provide
alternative options while not interrupting cash
flow. The evaluation results of five different
demand forecasting algorithms, including a
classic projection method, are presented. In
the evaluation of demand forecasting
algorithms, SARIMA, which is a traditional
projection method, produces a RMSE of
Algorithm
Evaluation Metric
RMSE
MAPE
SARIMA
93.13
85.29
SARIMAX
48.96
89.85
LSTM
85.36
82.41
XGB
55.77
41.18
GPR
63. 41
77.69

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 65
93.13 and a MAPE of 85.29. On the other
hand, the SARIMAX algorithm, which is a
modification of SARIMA, performs better with
an RMSE of 48.96, but its MAPE is higher at
89.85. In terms of the LSTM algorithm, it
generates a RMSE of 85.36 and a MAPE of
82.41. In comparison, the ensemble learner
XGB stands out as the most accurate
algorithm for demand forecasting in this
study, with a RMSE of 55.77 and a MAPE of
41.18. Lastly, the Gaussian process
regression (GPR) has a RMSE of 63.41 and
a MAPE of 77.69. Overall, the results show
that machine learning algorithms outperform
the classic projection method, and XGB is the
most accurate algorithm for demand
forecasting in this study.
Furthermore, in the future, these results
can be utilized and tested against real-world
business activities to help managers create
accurate inventory management strategies.
As a suggestion for subsequent
implementation, considering the new normal
era after COVID-19, historical data should be
used as training data first to determine if it fits
well since there may be a different trend
during the pandemic in terms of sales data.
REFERENCES
[1] McKinsey & Company, “Using customer
analytics to boost corporate performance
Marketing Practice Key insights from
McKinsey’s DataMatics 2013 survey,”
2014.
[2] A. Singh, M. Wiktorsson, and J. B. Hauge,
“Trends In Machine Learning To Solve
Problems In Logistics,” Procedia CIRP,
vol. 103, pp. 67–72, 2021, doi:
10.1016/j.procir.2021.10.010.
[3] A. Tufano, R. Accorsi, and R. Manzini, “A
machine learning approach for predictive
warehouse design,” The International
Journal of Advanced Manufacturing
Technology, vol. 119, no. 3–4, pp. 2369–
2392, Mar. 2022, doi: 10.1007/s00170-
021-08035-w.
[4] A. M. Atieh et al., “Performance
Improvement of Inventory Management
System Processes by an Automated
Warehouse Management System,”
Procedia CIRP, vol. 41, pp. 568–572,
2016, doi: 10.1016/j.procir.2015.12.122.
[5] T. Lima de Souza, D. Barbosa de Alencar,
A. P. Tregue Costa, and M. C. Aparício de
Souza, “Proposal for Implementation of a
Kanban System in the Auxiliary Inventory
Sector in a Auto Parts Company,” Int J
Innov Educ Res, vol. 7, no. 10, pp. 849–
859, Oct. 2019, doi:
10.31686/ijier.vol7.iss10.1833.
[6] Xie Haiyan, “EMPIRICAL STUDY OF AN
AUTOMATED INVENTORY
MANAGEMENT SYSTEM WITH
BAYESIAN INFERENCE ALGORITHM,”
Int J Res Eng Technol, vol. 04, no. 10, pp.
398–405, Oct. 2015, doi:
10.15623/ijret.2015.0410065.
[7] X. Guo, C. Liu, W. Xu, H. Yuan, and M.
Wang, “A Prediction-Based Inventory
Optimization Using Data Mining Models,”
in 2014 Seventh International Joint
Conference on Computational Sciences
and Optimization, Jul. 2014, pp. 611–615.
doi: 10.1109/CSO.2014.118.
[8] L. Lin, W. Xuejun, H. Xiu, W. Guangchao,
and S. Yong, “Enterprise Lean Catering
Material Management Information
System Based on Sequence Pattern Data
Mining,” in 2018 IEEE 4th International
Conference on Computer and
Communications (ICCC), Dec. 2018, pp.
1757–1761. doi:
10.1109/CompComm.2018.8780656.
[9] S. Zhang, K. Huang, and Y. Yuan, “Spare
Parts Inventory Management: A Literature
Review,” Sustainability, vol. 13, no. 5, p.
2460, Feb. 2021, doi:
10.3390/su13052460.
[10] Box George E. P., Jenkins Gwilym M.,
Reinsel Gregory C., and Ljung Greta M.,
Time Series Analysis: Forecasting and
Control. Wiley, 2015.
[11] V. Assimakopoulos and K. Nikolopoulos,
“The theta model: a decomposition
approach to forecasting,” Int J Forecast,
vol. 16, no. 4, pp. 521–530, Oct. 2000,
doi: 10.1016/S0169-2070(00)00066-2.
[12] K. Nikolopoulos, V. Assimakopoulos, N.
Bougioukos, A. Litsa, and F. Petropoulos,
“The Theta Model: An Essential
Forecasting Tool for Supply Chain
Planning,” 2011, pp. 431–437. doi:
10.1007/978-3-642-25646-2_56.
[13] H. Lütkepohl, “Vector autoregressive
models,” in Handbook of Research
Methods and Applications in Empirical
Macroeconomics, Edward Elgar
Publishing, 2013, pp. 139–164. doi:
10.4337/9780857931023.00012.
[14] L. Breiman, J. H. Friedman, R. A. Olshen,
and C. J. Stone, Classification And
Regression Trees. Routledge, 2017. doi:
10.1201/9781315139470.

ISSN 2089-8673 (Print) | ISSN 2548-4265 (Online)
Volume 12, Issue 1, March 2023
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 66
[15] D. F. Specht, “A general regression
neural network,” IEEE Trans Neural Netw,
vol. 2, no. 6, pp. 568–576, 1991, doi:
10.1109/72.97934.
[16] N. S. Altman, “An Introduction to Kernel
and Nearest-Neighbor Nonparametric
Regression,” Am Stat, vol. 46, no. 3, p.
175, Aug. 1992, doi: 10.2307/2685209.
[17] D. J. C. MacKay, “Bayesian neural
networks and density networks,” Nucl
Instrum Methods Phys Res A, vol. 354,
no. 1, pp. 73–80, Jan. 1995, doi:
10.1016/0168-9002(94)00931-7.
[18] C. K. I. Williams and C. E. Rasmussen,
“Gaussian Processes for Regression,” in
Proceedings of the 8th International
Conference on Neural Information
Processing Systems, 1995, pp. 514–520.
[19] S. Hochreiter and J. Schmidhuber, “Long
Short-Term Memory,” Neural Comput,
vol. 9, no. 8, pp. 1735–1780, Nov. 1997,
doi: 10.1162/neco.1997.9.8.1735.
[20] Zhengyou Zhang, M. Lyons, M. Schuster,
and S. Akamatsu, “Comparison between
geometry-based and Gabor-wavelets-
based facial expression recognition using
multi-layer perceptron,” in Proceedings
Third IEEE International Conference on
Automatic Face and Gesture Recognition,
pp. 454–459. doi:
10.1109/AFGR.1998.670990.
[21] Medsker L.R. and Jain L.C., Recurrent
neural networks: design and applications.
CRC Press, 1999.
[22] Buhmann M. D., Radial Basis Functions:
Theory and Implementations, vol. 12.
Cambridge University Press, 2003.
[23] N. K. Ahmed, A. F. Atiya, N. el Gayar, and
H. El-Shishiny, “An Empirical Comparison
of Machine Learning Models for Time
Series Forecasting,” Econom Rev, vol.
29, no. 5–6, pp. 594–621, Aug. 2010, doi:
10.1080/07474938.2010.481556.
[24] J. J. Montaño Moreno, A. Palmer Pol, and
P. Muñoz Gracia, “Artificial neural
networks applied to forecasting time
series.,” Psicothema, vol. 23, no. 2, pp.
322–9, Apr. 2011.
[25] S. Makridakis, E. Spiliotis, and V.
Assimakopoulos, “Statistical and Machine
Learning forecasting methods: Concerns
and ways forward,” PLoS One, vol. 13,
no. 3, p. e0194889, Mar. 2018, doi:
10.1371/journal.pone.0194889.
[26] F. E. H. Tay and L. J. Cao, “Improved
financial time series forecasting by
combining Support Vector Machines with
self-organizing feature map,” Intelligent
Data Analysis, vol. 5, no. 4, pp. 339–354,
Nov. 2001, doi: 10.3233/IDA-2001-5405.
[27] G. P. Zhang, “Time series forecasting
using a hybrid ARIMA and neural network
model,” Neurocomputing, vol. 50, pp.
159–175, Jan. 2003, doi: 10.1016/S0925-
2312(01)00702-0.
[28] C. N. Babu and B. E. Reddy, “A moving-
average filter based hybrid ARIMA–ANN
model for forecasting time series data,”
Appl Soft Comput, vol. 23, pp. 27–38, Oct.
2014, doi: 10.1016/j.asoc.2014.05.028.
[29] R. Wirth and J. Hipp, “CRISP-DM:
Towards a standard process model for
data mining,” in Proceedings of the 4th
international conference on the practical
applications of knowledge discovery and
data mining, 2000, pp. 29–39.
[30] F. Petropoulos, R. J. Hyndman, and C.
Bergmeir, “Exploring the sources of
uncertainty: Why does bagging for time
series forecasting work?,” Eur J Oper
Res, vol. 268, no. 2, pp. 545–554, Jul.
2018, doi: 10.1016/j.ejor.2018.01.045.
[31] C. S. Bojer and J. P. Meldgaard, “Kaggle
forecasting competitions: An overlooked
learning opportunity,” Int J Forecast, vol.
37, no. 2, pp. 587–603, Apr. 2021, doi:
10.1016/j.ijforecast.2020.07.007.