p–ISSN: 2723 – 6609 e-ISSN: 2745-5254

Vol. 5, No. 12 Desember 2024 http://jist.publikasiindonesia.id/

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 12, Desember 2024 5755

Designing a Recommendation System at Yense Restaurants

Benhard

, Hugeng

, Manatap Dolok Lauro

Universitas Tarumanagara, Indonesia

Email : [email protected]

, [email protected]

[email protected]

*Correspondence

ABSTRACT

Keywords:

Recommendation System;

web; SDLC; Assocation

Rule Mining

The culinary industry in Indonesia is experiencing rapid

growth, driven by the increasing use of online food delivery

platforms, which have transformed consumer behavior. This

study aims to design a web-based recommendation system

for Rumah Makan Yense, a restaurant in Jakarta, to enhance

customer satisfaction and operational efficiency. The

research utilizes the Association Rule Mining method with

the FP-Growth algorithm to analyze customer transaction

data and identify purchasing patterns. The system provides

personalized menu recommendations to customers,

addressing the challenge of information overload in menu

selection. The findings demonstrate that the

recommendation system effectively improves customer

satisfaction by delivering relevant menu suggestions, while

also increasing sales and service efficiency. The study

concludes that implementing such a system enables Rumah

Makan Yense to remain competitive in the dynamic culinary

industry, showcasing the potential of technology in

supporting business operations.

Introduction

The culinary industry in Indonesia continues to grow rapidly, driven by

digitalization and the increasing use of online food ordering platforms such as GoFood,

GrabFood, and ShopeeFood. Digitalization has become the main factor that drives

Indonesia's economic progress in the current digital era (Gultom et al., 2024).

This digitalization not only makes it easier for customers to choose and order food

but also significantly changes people's consumption patterns. In an increasingly

competitive ecosystem, service personalization is becoming a critical element to provide

a relevant customer experience and increase their loyalty.

Rumah Makan Yense, a restaurant located in Jakarta, serves a variety of signature

dishes such as Hainan rice and grilled chicken. To reach more customers, Yense

Restaurant has taken advantage of an online ordering platform. However, the presence of

many menu options often makes customers feel confused, which can ultimately affect

their purchase decision. Therefore, a system is needed that can help customers choose

menus that suit their preferences, while encouraging restaurant operational efficiency.

The phenomenon of excess information faced by most people in Indonesia opens up

opportunities as well as a challenge to prove the role and existence of information experts

Benhard, Hugeng, Manatap Dolok Lauro

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 9, September 2024 5756

in the midst of the accelerating flow of information (Hariyati & Heriyanto, 2021;

Prawitasari, 2022).

The recommendation system is one of the technological solutions that can be used

to deal with the problem of information overload. The system works by analyzing

customer historical data, such as ordering patterns, to provide relevant menu suggestions.

With proper implementation, a recommendation system can not only improve the

customer experience but also contribute to increased restaurant satisfaction, loyalty, and

revenue (Pratondo, 2023; Rane et al., 2023).

Approaches such as Association Rule Mining are one of the potential methods in

building a recommendation system. Algorithms such as A priori and FP-Growth are used

to find association patterns among various items in sales data. This pattern can help

restaurants understand the relationship between items, for example, menu combinations

that are often ordered together. This information is useful not only for recommendation

systems but also for promotion strategies, stock planning, and inventory management,

which can ultimately improve restaurant operational efficiency (Swink et al., 2022; Zuhri

& Utami, 2023).

This study aims to design a recommendation system that utilizes the Association

Rule Mining approach to improve service efficiency, customer experience, and sales at

Yense Restaurant. With this solution, it is hoped that Yense Restaurant can remain

competitive in the midst of increasingly fierce competition in the culinary industry.

Table 1. Journal References

Reference

Discussion Results

Difference

Dino Akbar Pratondo

[5]

The content-based filtering-

based recommendation

system with TF-IDF, SVD,

and Cosine Similarity

algorithms managed to

achieve 85.22% accuracy in

providing relevant campaign

recommendations on the

fundraising platform.

The research focused on food

menu recommendations

based on customer transaction

data for Yense Restaurant,

while the journal utilized

campaign text metadata, not

related to transaction data or

specific dishes.

Savina Choirina Zuhri

(2023)

The AHP method-based

menu recommendation

system helps customers

choose menus based on

criteria such as taste, price,

and quality, with a consistent

hierarchical approach through

the calculation of the

Consistency Ratio.

This research prioritizes

order history data to compile

recommendations based on

customer preferences, while

this journal uses explicit

criterion weights (AHP) to

provide recommendations,

focusing on manual analysis

of individual criteria.

Dhananjaya et al. (2022)

Research on personalized

recommendation systems for

e-learning using content-

based filtering and machine

learning approaches, shows

the challenges of improving

the accuracy and relevance of

recommendations on big data.

This journal focuses on

recommendations in digital

content-based education and

machine learning, while this

research applies a

recommendation system for

cuisine with a more data-

Designing a Recommendation System at Yense Restaurants

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 9, September 2024 5757

based approach to restaurant

user transaction data.

Research methods

The association method works with the Association Rule Mining. Association rules

are one of the techniques in descriptive data mining that serves to identify patterns of

relationships between various items in data (Saputra et al., 2023). This method has a

relationship between items (menus) formulated in the form of rules such as the following

example rule: If a customer orders Hainan Rice, then they are likely to also order sweet

iced tea. Each of these rules has several important evaluation parameters:

1. Support

The support of an association rule is the percentage of combinations of items in the

database or the percentage of transactions that contain certain combinations of items

to the overall transaction (Maulidah & Bachtiar, 2021). Support is used to identify

relationships between words (Fauzy et al., 2023).

2. Confidence

Measure how often item B is purchased when item A is purchased.

3. Elevator

Measure how much the relationship between two items compares if the two items are chosen

at random.

In the application of this association method, there is an FP-Growth algorithm that

has a very close relationship with the association method because this algorithm is a

technique used in the application of association rule mining. FP-Growth with the concept

of building a tree (FPTree) in looking for frequent itemsets (Ardianto & Fitrianah, 2019).

This algorithm builds an FP-tree (Frequent Pattern Tree) structure to store data and look

for patterns of frequently appearing items without having to go through the entire dataset

repeatedly.

Figure 2. Association method formula

Source: (Nissa, 2020)

Benhard, Hugeng, Manatap Dolok Lauro

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 9, September 2024 5758

Results and discussion

After conducting the analysis, the next step is to create a web-based

recommendation system application. In this application, there are menus at Yense

restaurants and there are recommendations given to customers when they want to choose

a menu.

In designing this application, several stages are needed.

1. Needs Analysis

Determining the main purpose of the web, for example providing

recommendations on the food menu and showing the entire menu at the restaurant so

that buyers can be helped in determining the food menu to order.

2. Design

- UI/UX Design Make a sketch or wireframe about how the web looks and layout starting

from logos, menu lists, food recommendations and others.

- System Architecture Design Create flowcharts to easily understand the interactions that can

occur in the application.

3. Development

- Frontend Development

Create a basic framework using HTML, then add styles or layouts using CSS and add

interactivity like JavaScript or React/Vue.js.

- Backend Development

Implement recommendation logic using Python and then build an API to connect the

frontend and backend.

- Responsiveness and Testing

Ensure the design is responsive and compliant with CSS or frameworks and then test

compatibility across various browsers.

3. Testing

Conducting tests both in terms of functionality and usability. Ensure that the feature

is working for the intended purpose and that the layout is easy to use.

After visiting the stages above, the design of the recommendation system can begin.

The design of the recommendation system application to be made can be seen in Figure

Figure 3. Web application view

Designing a Recommendation System at Yense Restaurants

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 9, September 2024 5759

Conclusion

The design of a web-based recommendation system application for Yense Restaurant

is a strategic solution in answering the challenge of information overload in the

competitive culinary industry. Using the SDLC Waterfall method, each stage, from needs

analysis to maintenance, is carried out systematically to ensure the system can run

according to its goals. This recommendation system leverages Association Rule Mining-

based algorithms, such as FP-Growth, to analyze buying patterns and generate relevant

menu recommendations. In addition to improving service efficiency, the system is also

designed to support a more personalized customer experience and increase customer

loyalty. With an intuitively designed interface through a UI/UX approach, as well as

responsive frontend and backend integration, the app offers ease of use while supporting

data-driven decision-making. Rigorous functional and usability testing ensures the system

is able to meet user needs, while regular maintenance allows for further development

based on the latest data and trends. With the implementation of this system, Rumah

Makan Yense is expected to increase its competitiveness in the midst of the rapid growth

of the digital-based culinary industry.

Bibliography

Ardianto, A., & Fitrianah, D. (2019). Penerapan Algoritma FP-Growth Rekomendasi

Trend Penjualan ATK Pada CV. Fajar Sukses Abadi. Jurnal Telekomunikasi Dan

Komputer, 9(1), 49. https://doi.org/10.22441/incomtech.v9i1.3263

Dhananjaya, G. M. , Goudar, R. H., Kulkarni, A. A., Rathod, V. N., & Hukkeri, G. S.

(2024). A Digital Recommendation System for Personalized Learning to Enhance

Online Education: A Review. IEEE Access, 12, 34019–34041.

https://doi.org/10.1109/ACCESS.2024.3369901

Gultom, D., Hutabarat, G. S. P., Dirgantara, M., Pratama, R., & Hidayah, A. (2024).

Positive Impact of Digitalization On The Indonesia Economy. Jurnal Konstanta,

3(1). https://doi.org/10.29303/konstanta.v3i1.1078

Hariyati, M., & Heriyanto, H. (2021). Kompetensi Pustakawan di Era Industri 4.0 dalam

Menghadapi Information Overload. Daluang: Journal of Library and Information

Science, 1(1), 1. https://doi.org/10.21580/daluang.v1i1.2021.8005

Fauzy, M., Saleh, K. R., & Asror, I. (2023). A priori algorithm performance analysis using

evaluation parameters on transaction data. Journal of Information and

Communication Technology, 5(2), 123–130.

Ma’ady, M. N. P., Rizaldy, D. D., Satria, R. F., & Anaking, P. (2023). Sparring: Sistem

Rekomendasi Peneliti Terintegrasi Google Scholar via SerpAPI dan Latent Dirichlet

Allocation pada Konteks Perguruan Tinggi. Jurnal Teknologi Dan Manajemen

Informatika, 9(2), 161–171. https://doi.org/10.26905/jtmi.v9i2.11111

Benhard, Hugeng, Manatap Dolok Lauro

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 9, September 2024 5760

Maulidah, A., & Bachtiar, F. A. (2021). Penerapan Metode Association Rule Mining

untuk Asosiasi Ulasan Terhadap Aspek Tempat Wisata Jawa Timur Park 3. Jurnal

Teknologi Informasi Dan Ilmu Komputer, 8(5), 1029–1038.

https://doi.org/10.25126/jtiik.2021854417

Nissa, F. (2020, January 25). Association Rules using RStudio. Medium.

https://images.app.goo.gl/xgQTyX3zBf3tqre46

Pratondo, D. A. (2023). Pengembangan Sistem Rekomendasi Berbasis Content- based

Filtering pada Data Dinasmis. Universitas Syarif Hidayatullah.

Prawitasari, P. P. (2022). Will accountants still exist? Challenges of the accountant

profession in facing technological disruption in the new normal era. International

Conference Faculty of Economics and Business, 1(1), 326–350.

Rane, N. L., Achari, A., & Choudhary, S. P. (2023). Enhancing Customer Loyalty

Through Quality of Service: Effective Strategies to Improve Customer Satisfaction,

Experience, Relationship, and Engagement. International Research Journal of

Modernization in Engineering Technology and Science, 5(5), 427–452.

https://doi.org/10.56726/IRJMETS38104

Ristianingrum, R. S., & Sulastri, S. (2022). Analysis of Publication Article Title

Association Patterns Based on Google Scholar Data Using a Priori Algorithm.

Journal of Informatics Engineering, 10(3), 140–148.

Saputra, A., Sari, H. L., & Sartika, D. (2023). Implementasi Metode Association Rule

Mining Pada Penjualan Barang Di Toko Bangunan Ada Mas Menggunakan

Algoritma Apriori. Jurnal Multidisiplin Dehasen (MUDE), 2(4).

https://doi.org/10.37676/mude.v2i4.4805

Swink, M., Hu, K., & Zhao, X. (2022). Analytics applications, limitations, and

opportunities in restaurant supply chains. Production and Operations Management,

31(10), 3710–3726. https://doi.org/10.1111/poms.13704

Zuhri, S. C., & Utami, W. S. (2023). Aplikasi Pemesanan Makanan Berbasis Analytical

Hierarchy Process (AHP) dengan Menu Rekomendasi. KLIK: Kajian Ilmiah

Informatika Dan Komputer, 4(3), 1245–1254.

https://doi.org/https://doi.org/10.30865/klik.v4i3.1299