Article Per Year (5 Year)
p-Index From 2021 - 2026
1.671
P-Index
This Author published in this journals
All Journal Sebatik Building of Informatics, Technology and Science TEPIAN Indo-MathEdu Intellectuals Journal
Salmon Salmon, Salmon
Unknown Affiliation
Computer Science & IT Mathematics

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Building of Informatics, Technology and Science

 1 
Penerapan Algoritma K-Means Data Mining Pada Clustering Kelayakan Penerima UKT Dengan Normalisasi Data Model Z-Score Yunita, Yunita; Fahmi, Muhammad; Salmon, Salmon
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6475

Abstract

Tuition Assistance is money given specifically to students with the aim of alleviating the problem of paying educational costs for less fortunate students so they can continue their education. With the large number of scholarship applicants on a campus, especially Budidarma University, a computerized information system is needed so that the selection of students who receive tuition assistance can run well. One way that can be implemented is by applying data mining with the K-Means algorithm. From the results of applying the data mining method, it can be concluded that there were 10 students who received tuition assistance who were included in cluster 1 and likewise in cluster 2 there were 10 students who did not receive tuition assistance.
Perbandingan Kinerja Algoritma K-Nearest Neighbor dan Algoritma Random Forest Untuk Klasifikasi Data Mining Pada Penyakit Gagal Ginjal Salmon, Salmon; Azahari, Azahari; Ekawati, Hanifah
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6476

Abstract

Kidney failure is one of the most common chronic diseases worldwide. This condition occurs when the kidneys lose their ability to filter waste and excess fluid from the blood. Kidney failure is a serious condition that occurs when kidney function decreases significantly or stops altogether. Kidney failure has a wide impact on the physical, mental, and social health of patients. Therefore, early treatment and a holistic approach are needed to minimize its impact. In the health sector, technological advances have enabled more effective processing of medical data through the application of data mining. Data Mining is the process of exploring and analyzing large amounts of data to find patterns, relationships, or valuable information that was previously unknown. Classification in Data Mining is the process of grouping or categorizing data into certain classes or labels based on the attributes or features it has. In the classification itself, there are various algorithms in it such as the K-Nearest Neighbor (KNN) and Random Forest (RF) algorithms. The K-Nearest Neighbor (KNN) and Random Forest (RF) algorithms are two algorithms that are widely used in classification tasks. Therefore, this study will carry out a comparison process on the performance of the K-Nearest Neighbor algorithm and the Random Forest algorithm. Comparison of data mining algorithm performance to evaluate and determine which algorithm is the most effective and efficient in solving a particular problem based on various evaluation metrics. Overall, the accuracy value obtained is above 90%, but the Random Forest algorithm has better performance. Where the accuracy level results obtained from the Random Forest algorithm are 99.75%. Therefore, the model or pattern produced by the Random Forest algorithm will later be used to assist in the process of diagnosing kidney failure and the Random Forest algorithm is an algorithm that has better performance.
Determining the Country with the Best Economic Conditions 2025 using the MCDM Method Harpad, Bartolomius; Azahari, Azahari; Salmon, Salmon
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7346

Abstract

In the midst of increasingly complex global challenges in 2025, evaluating a country's economic condition is an important element in supporting strategic decision-making, whether at the government, corporate or individual level. The diversity of economic indicators such as Gross Domestic Product (GDP), inflation, unemployment, and human development index often makes it difficult to make an objective and comprehensive assessment. Reliance on a single indicator tends to produce a biased and unrepresentative picture. To address these issues, this research adopts a Multi-Criteria Decision Making (MCDM) approach that is able to consider various economic aspects simultaneously and systematically. The three MCDM methods used in this study are TOPSIS, VIKOR, and COCOSO. The analysis was conducted on 19 countries using four main indicators, namely GDP in billion USD, inflation rate, unemployment rate, and economic growth rate. Based on the results of data processing, the USA occupies the top position as the country with the best economic performance, followed by China. The three methods show consistency in ranking some countries, but there are also striking differences for some alternatives due to different approaches in normalisation and weighting. These findings emphasise the importance of choosing the right method in multicriteria evaluation. Therefore, a combined approach such as ensemble decision-making is recommended to strengthen the validity of the results. For further development, the use of additional indicators and the integration of artificial intelligence-based technology are suggested to improve accuracy and flexibility in analysing economic conditions between countries.
Determining the Best E-Commerce Using the Multi Criteria Decision Making (MCDM) Method Salmon, Salmon; Lailiyah, Siti; Arriyanti, Eka
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7395

Abstract

The rapid expansion of e-commerce has positively influenced lifestyles and fueled economic growth, as evidenced by rising transaction volumes and government revenue. However, challenges persist, especially in consumer security, logistics infrastructure, and taxation. The quality of e-commerce websites is crucial, serving as a primary source of customer information and ensuring secure transactions. Selecting the right e-commerce platform is also essential for business development. Despite the proliferation of e-commerce platforms offering diverse features and user-friendly interfaces, issues like product quality discrepancies, fraudulent activities, and incomplete features continue to frustrate consumers. To address these challenges and aid consumers in selecting optimal platforms, Multi-Criteria Decision Making (MCDM) methods are employed. This study explores various MCDM techniques to rank 8 major e-commerce platforms based on 5 criteria. The analysis consistently identifies Shopee as the top-performing platform. While Tokopedia, Bukalapak, Lazada, and TikTok Shop show some variations in rankings depending on the MCDM method used, Blibli, JD.ID, and OLX Indonesia maintain consistent rankings across all methods. This suggests that while Shopee demonstrates clear superiority, the subtle differences in MCDM methodologies can influence the relative rankings of other platforms.
Investment Decision-Making for High-Potential Startups in the Digital Economy Using AHP and VIKOR Salmon, Salmon; Rahmadani, Rizki Galang; Harpad, Bartolomius
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8633

Abstract

The rapid growth of the digital economy has driven the emergence of numerous startup companies that play a vital role as catalysts for innovation and business transformation in the modern era. However, the increasing number of startups poses a major challenge for investors in selecting the most potential and profitable investment opportunities. The main problem lies in the multi-criteria evaluation process, which involves various aspects such as market potential, product innovation, business model, team performance, and financial stability. To address this complexity, this study applies a combination of the Analytical Hierarchy Process (AHP) and VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) methods as an objective and measurable multi-criteria decision-making approach. The AHP method is utilized to determine the priority weights of each criterion through a pairwise comparison process. The results show that market potential (C1) is the most dominant criterion with a weight of 0.458, followed by product innovation (C2) with a weight of 0.247, and business model (C3) with a weight of 0.144. Meanwhile, team performance (C4) and financial stability (C5) have relatively lower weights of 0.105 and 0.046, respectively. These findings indicate that market and innovation aspects are the primary factors influencing startup investment feasibility. Furthermore, the VIKOR method is employed to rank the alternatives based on compromise solutions toward the ideal outcome. The results reveal that startup A17 has the lowest compromise value (Q = 0.0000), making it the most optimal investment alternative, followed by A4 (Q = 0.0303) and A19 (Q = 0.0586). This study demonstrates that the combination of AHP and VIKOR methods provides a comprehensive, objective, and consistent analysis in the decision-making process for digital startup investments. The proposed approach assists investors in evaluating startups more systematically and accurately based on the priority of relevant criteria in the context of the dynamic digital economy. Therefore, a decision support system based on the AHP-VIKOR method can serve as an effective solution for decision-makers to identify and select the most promising startups for future development.
Customer Sentiment Analysis of E-Commerce Products Using the Naïve Bayes Method and Word Embedding Harpad, Bartolomius; Azahari, Azahari; Salmon, Salmon
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8879

Abstract

This study discusses customer sentiment analysis toward e-commerce products using the Naïve Bayes method combined with Word Embedding techniques to enhance the semantic understanding of Indonesian-language customer reviews. The research background is based on the rapid growth of e-commerce, which has created a strong need to understand consumer opinions through online reviews. The main challenge in sentiment analysis lies in the complexity of natural language, such as the use of informal words, abbreviations, and diverse emotional expressions. This study utilizes 40,607 Tokopedia customer reviews across five product categories with three sentiment labels (positive, neutral, and negative). The research stages include data collection, text preprocessing (case folding, tokenization, stopword removal, stemming, and slang normalization), feature representation using Word2Vec and FastText, and classification using Multinomial Naïve Bayes. Experimental results show that the combination of Word2Vec and Naïve Bayes achieved an accuracy of 87.92%, while FastText and Naïve Bayes improved accuracy to 91.52%. The FastText-based model proved superior in handling morphological variations and non-standard spellings, making it more effective for Indonesian customer review texts. The WordCloud visualization reveals the dominance of positive words such as “sesuai” (appropriate), “barang” (item), and “cepat” (fast), indicating customer satisfaction regarding product conformity and service speed. The Confusion Matrix results indicate a bias toward the positive class due to data imbalance, where the model still struggles to recognize neutral and negative classes. Overall, this study demonstrates that integrating Word Embedding with Naïve Bayes enhances classification performance and provides richer semantic representations compared to traditional Bag of Words approaches. This approach has the potential to be applied in developing data-driven recommendation systems and marketing strategies within Indonesia’s e-commerce ecosystem.
Co-Authors Andriawan Arriyanti, Eka Asmendri Asmendri Azahari, Azahari Dair, Muhammad Filza Al Demina Demina Ekawati, Hanifah Fachry Abda El Rahman Fadhilah Fadhilah Hakiki, Muhammad Rezha Nur Haristyawan, Ivan Harpad, Bartolomius Maharni, Septi Milya Sari Muhammad Fahmi Niansyah, Sugih Niza, Yesita Rosa Nurlinda Nurlinda, Nurlinda Pahrudin, Pajar Pitrasacha Adytia Reza Andrea Rizki Galang Rahmadani Siswadi, Renalda Yunita Yunita