cover
Contact Name
Abdullah
Contact Email
abdialam@gmail.com
Phone
+628127580419
Journal Mail Official
data.science.ins@gmail.com
Editorial Address
Jl. Soebrantas Gg. Jelutung Indah no 49 Tembilahan Indragiri Hilir Riau
Location
Kab. indragiri hilir,
Riau
INDONESIA
Data Science Insights
Published by PT Visi Media Network
ISSN : -     EISSN : 30311268     DOI : https://doi.org/10.63017/jdsi.v3i2
Data Science Insights, with ISSN 3031-1268 (Online) published by PT Visi Media Network is a journal that publishes Focus & Scope research articles, which include Data Science and Machine Learning; Data Science and AI; Blockchain and Advance Data Science; Cloud computing and Big Data; Business Intelligence and Big Data; Statistical Foundation for Data Science; Probability and Statistics for Data Science; Statistical Inference via Data Science; Big Data and Business Analytics; Statistical Thinking in Business; Data Driven Statistical Methods; Statistical Methods for Spatial Data Analytics; Statistical Techniques for Data Analysis; Data Science in Communication; Information and Communication Technology; Graph Data Management for Social Network Applications; Metadata for Information Management; Information/Data: Organization and Access; Information Science and Electronic Engineering; Big Data and Social Science; Data Communication and Computer Network; ICT & Data Analytics. This journal is published by the PT Visi Media Network, which is published twice a year.
Articles 28 Documents
Integrating IoT and Blockchain for Enhanced Security: Challenges and Solutions bin Zainuddin, Ahmad Anwar; binti Mortadza, Aina Syazana; binti Musa , Faheyra Ezzah
Data Science Insights Vol. 2 No. 1 (2024): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v2i1.17

Abstract

The integration of Internet of Things (IoT) and blockchain integration addresses security concerns in IoT devices through decentralized networks. Challenges include scalability, interoperability, and privacy. Proposed solutions involve decision frameworks, lightweight consensus mechanisms, and hybrid architectures. Smart contracts and privacy-preserving techniques enhance secure transactions. Integration benefits industries like healthcare, supply chain, and energy by improving efficiency and transparency. The methodology involves selecting a blockchain platform, designing a consensus mechanism, developing smart contracts, and integrating IoT devices. Challenges like data ownership and governance can be mitigated through policies and privacy-preserving techniques, ultimately optimizing operations, and improving customer satisfaction across industries.
Decision Support System Application in Disaster Management Yilin, Li; Zhaoji, Fu; Kowthalam, Vijay Rathnam; Guangfa, Wu; Binti Abdul Rahim, Yusrina; Maidin, Siti Sarah; Yahya, Norzariyah
Data Science Insights Vol. 2 No. 1 (2024): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v2i1.21

Abstract

Disasters such as earthquake, flood, fire, and tsunami result in catastrophic human suffering, loss of property and other negative consequences. The continues threats of future disasters enforce human to find best possible ways to detect and take premeasured actions based on calculated risks to reduce these negative impacts of disasters. 
Assessing the Efficiency and Accuracy of K-Means Clustering Compared to Other Clustering Techniques Khan, Iliyas; Daud, Hanita Binti Daud; Zainuddin , Nooraini binti Zainuddin; Sokkalingam, Rajalingam Sokkalingam; Azad , Abdus Samad Azad; Samad, Abdussamad; Suleiman, Ahmad Abubakar Suleiman
Data Science Insights Vol. 3 No. 2 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i2.23

Abstract

Clustering is an important method in data analysis, faces challenges due to the different nature of datasets, resulting in certain algorithms being less effective and taking a long time. Choosing the most effective clustering method involves evaluating its accuracy and computational speed for a dataset poses a significant challenge for today's researchers. To address these issues, current study compares different clustering methods, by using datasets, including iris, seed, and well log to evaluate their accuracy and execution speed. Results show that K-means performs better with large datasets. As sample size increases, the accuracy of the K-means algorithm tends to improve. The execution time of k-means is influenced by the number of features in the dataset, with datasets having a larger number of features typically requiring more time to process. Mean shift algorithm and spectral clustering algorithm are performed well in small data sets, but it takes a long time.
Analysis of Sales Data Visualization of Warung Indomie using the Looker Studio Platform Purwenti, Rinda; Bela, Nova Rustiana; Alda, Hutri Rizkiyah; Jihannata, Nabila
Data Science Insights Vol. 3 No. 1 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i1.33

Abstract

Indomie stalls are stalls that serve noodles from Indomie products.because people's tastes are very familiar with indomie, the opportunity to do business in the field of warmindo is large.so research was carried out to analyze the sales data of the indomie stall. The method used is Sales Data Visualization Analysis at Indomie Warung Using the Looker Studio Platform, starting from data collection, data preparation and data exploration. The data taken is secondary data from the Bima Putra website. The attributes used are invoice_id,tanggal_transaksi, jenis_produk, quantity, harga_jual, jenis_pembayaran, jenis_pesanan, and nilai_penjualan.so as to produce several visualizations. From this visualization, it is known that the best-selling Indomie product type is Indomie soup with 682 sales and the non-selling product is Indomie Goreng which sold only 293 from January-August 2022. The favorite product is Indomie Soto Betawi flavor as many as 80 sales. With the overall indomie flavor is 18 flavors. For the type of orders that are widely made, delivery is 51.7% with cash payment, which is 20%.the highest monthly income is July 2022 with a total of 1.4 million and the lowest is April 2022 with a total of 899 Rp. With an overall total of 975 sales. Therefore, this indomie stall can pay attention so that the stock of best-selling goods is always available, increase the promotion, improve the service, comfort and facilities of the stall, and of course the taste of the indomie dish should attract customers. Because the factors that cause the success or not of the business come from the number of sales.In addition, from this information, customers can also know which products can be recommended.
Cluster Analysis of Superstore Data using K-Means and K-Medoids for Product Delivery Insights Sarumaha, Intan chintia; Foureshtree, Ajeng Cahyani; Jocelyn, Angela; Santoso, Jeffri; Hutabarat, Fernando
Data Science Insights Vol. 3 No. 2 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i2.34

Abstract

It is difficult to overcome the challenge of understanding the relationship between consumer patterns and overall market trends and improve the company's operational efficiency through optimizing the delivery process. Utilizing sales data from Super Store available on the Kaggle website, this study aims to identify predictable consumer patterns using cluster analysis, as well as explore how to improve delivery efficiency based on a better understanding of consumer needs and preferences. This research utilizes K-Means and K-Medoids clustering methods to group product subcategories into three categories: best-selling, in-selling, and not-selling. The process of data transformation, exploratory analysis, model building, as well as cluster performance evaluation were conducted with the help of analytical tools such as Microsoft Excel, Tableau, and RapidMiner. The results show that the K-Medoids algorithm provides more accurate clustering performance compared to K-Means, with a Davies-Bouldin Index value of -0.867 for K-Medoids and -0.519 for K-Means. This shows that K-Medoids is more suitable in describing the characteristics of existing data. The most in-demand cluster results are in the sub-category of machines and copiers products.
Comprehensive Approach to Weather Prediction with the Random Forest Algorithm Pedro Joyarieb; Silalahi, Vian Candra; Anggelica , Vallencia; Ongso, Khatrina Kelly
Data Science Insights Vol. 3 No. 2 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i2.35

Abstract

Weather is an air condition that is very important in everyday life. Accurate weather predictions can help people anticipate and deal with weather changes that can have an impact on daily activities. This research aims to develop an effective weather prediction model using machine learning algorithms. In this research, we use three popular machine learning algorithms, namely Random Forest, Support Vector Machine (SVM), and Decision Tree. The data used consists of historical weather data, including air temperature, air humidity, rainfall, wind direction, air pressure, wind speed, and solar radiation. The research results show that the Random Forest algorithm has the highest accuracy, with a prediction rate of 83%. The SVM algorithm is next, with a prediction rate of 78%, while the Decision Tree algorithm has a prediction rate of 72%. These findings show that Random Forest is the most effective algorithm in predicting weather, especially in predicting air temperature and rainfall. This research has significant practical implications in increasing the accuracy of weather predictions, which can help society anticipate and deal with weather changes that can impact in daily activities. In the future, this research can be used as a basis for developing more accurate and reliable weather prediction systems.
Cluster Analysis on Laptop Sales Data and Specifications Using K-Means and K-Medoids Methods Fajar, Ibnu
Data Science Insights Vol. 2 No. 2 (2024): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v2i2.38

Abstract

This research aims to address the challenges in understanding the relationship between laptop specifications and sales prices and to enhance product segmentation based on cluster analysis. By using available laptop specifications and sales price data, this study aims to identify patterns in laptop specifications that influence sales prices using K-Means and K-Medoids cluster analysis. This research employs the K-Means and K-Medoids clustering methods to categorize laptops into several categories based on specifications such as screen size (inches), price, RAM capacity, and weight. The data transformation process, exploratory analysis, model building, and cluster performance evaluation were conducted using the RapidMiner analysis tool. The research results show that the K-Medoids algorithm provides more accurate clustering performance compared to K-Means, with a Davies-Bouldin Index value of -0.665 for K-Medoids and -0.487 for K-Means at configurations k=4 and k=5. A lower Davies-Bouldin Index value indicates that K-Medoids better represents the characteristics of the existing data. The clustering results identify laptop categories based on a combination of specifications and prices, which can be used by manufacturers and sellers to develop more targeted marketing strategies. This research is expected to provide useful insights for the laptop industry in understanding consumer preferences and needs, and to assist in making more informative decisions to improve sales and customer satisfaction.
Identification of Diabetes Mellitus Risk in Women using Random Forest Wijaya, Eka
Data Science Insights Vol. 3 No. 1 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i1.95

Abstract

Diabetes Mellitus (DM) is one of the chronic diseases that can cause various serious complications, especially in women. Early risk identification is an important step in preventing the progression of this disease. This study aims to identify the factors influencing the risk of diabetes in women by analyzing data from several parameters, namely the number of pregnancies, glucose level, blood pressure, skin thickness, insulin level, body mass index (BMI), diabetes pedigree function, and age. A quantitative approach was used in this study with descriptive and inferential statistical analysis methods. The research results show that glucose levels and BMI are the most significant factors in increasing the risk of diabetes, followed by family history of diabetes and age. In addition, the number of pregnancies also has an impact on the risk of diabetes, especially in women with a history of gestational diabetes. This research concludes that the combination of several parameters can be used to predict the risk of diabetes more accurately, especially in women. These results are expected to support early prevention efforts and better clinical decision-making in the management of diabetes.  
Drug Classification using Machine Learning Algorithms fernando, Hengky
Data Science Insights Vol. 3 No. 1 (2025): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v3i1.96

Abstract

The right selection of drugs is a crucial factor in the treatment of various diseases to ensure the effectiveness of therapy and avoid risks that can worsen the patient's condition. This study aims to develop a machine learning-based prediction model to classify the appropriate type of drug based on patient characteristics. Several machine learning algorithms are tested to determine the most optimal model. The results of the analysis show that the Random Forest algorithm provides the best performance with the highest level of accuracy in predicting the right type of drug. Thus, the Random Forest-based model is recommended to be implemented as a decision support tool in the selection of drug therapies that is more accurate and efficient.
Predicting Emerging Art Styles in AI-Generated Artworks Willyem, Willy
Data Science Insights Vol. 2 No. 2 (2024): Journal of Data Science Insights
Publisher : PT Visi Media Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63017/jdsi.v2i2.99

Abstract

The development of artificial intelligence (AI) technology has brought significant changes in various fields, including the arts. AI-generated art is no longer just a technical experiment, but has evolved into a recognized artistic medium, creating new opportunities in the exploration of creativity and aesthetics. This study evaluates the prediction of aesthetic trends that develop in artistic creativity using the analysis of artwork datasets generated by Artificial Intelligence (AI) based on Machine Learning. In the digital age, AI has become an essential tool in art exploration, producing works with unique styles, techniques, and aesthetics. The study aims to understand the aesthetic patterns and dynamics that emerge from AI artwork. The results of the research obtained can be seen that the random tree model is an appropriate algorithm in making predictions. Through this approach, this article not only contributes to art and technology literature but also provides insight into how the relationship between humans and AI can shape the contemporary art landscape. This research is expected to be the basis for the development of more inclusive and creative AI technology in the future.

Page 2 of 3 | Total Record : 28