Article Per Year (5 Year)
p-Index From 2019 - 2024
1.683
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika JUTI: Jurnal Ilmiah Teknologi Informasi Telematika Seminar Nasional Informatika (SEMNASIF) Matrik : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) Progresif: Jurnal Ilmiah Komputer PROGRES PENDIDIKAN Universitas Muhammadiyah Yogyakarta Undergraduate Conference Proceeding Jurnal INFOTEL
Vynska Amalia Permadi
Universitas Pembangunan Nasional Veteran Yogyakarta
Agriculture, Biological Sciences & Forestry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Library & Information Science Mathematics Physics Public Health Social Sciences Other

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

Found 11 Documents
Search

 1   2 
DATA REFINEMENT APPROACH FOR ANSWERING WHY-NOT PROBLEM OVER K-MOST PROMISING PRODUCT (K-MPP) QUERIES Permadi, Vynska Amalia; Ahmad, Tohari; Santoso, Bagus Jati
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 16, No. 2, Juli 2018
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v16i2.a754

Abstract

K-Most Promising (K-MPP) product is a strategy for selecting a product that used in the process of determining the most demanded products by consumers. The basic computations used to perform K-MPP are two types of skyline queries: dynamic skyline and reverse skyline. K-MPP selection is done on the application layer, which is the last layer of the OSI model. One of the application layer functions is providing services according to the user's preferences.In the K-MPP implementation, there exists the situation in which the manufacturer may be less satisfied with the query results generated by the database search process (why-not question), so they want to know why the database gives query results that do not match their expectations. For example, manufacturers want to know why a particular data point (unexpected data) appears in the query result set, and why the expected product does not appear as a query result. The next problem is that traditional database systems will not be able to provide data analysis and solution to answer why-not questions preferred by users.To improve the usability of the database system, this study is aiming to answer why-not K-MPP and providing data refinement solutions by considering user feedback, so users can also find out why the result set does not meet their expectations. Moreover, it may help users to understand the result by performing analysis information and data refinement suggestion.
Analisis Sentimen Menggunakan Algoritma Naive Bayes Terhadap Review Restoran di Singapura Permadi, Vynska Amalia
Jurnal Buana Informatika Vol 11, No 2: Vol 11, No 2 (2020): Jurnal Buana Informatika Volume 11 - Nomor 2 - Okober 2020
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v11i2.3769

Abstract

Abstract. Sentiment Analysis Using Naive Bayes Classifier Against Restaurant Reviews in Singapore. Various restaurant options bring up a problem for diners to pick a restaurant to dine in. Thus, visitors usually perceive the restaurant's recommendation or rating in advance to know other diners' opinions about the restaurant. Previous restaurant diners' comments can be presented in sentiment analysis to determine their satisfaction. This research investigates the Naïve Bayes Classifier algorithm's performance in classifying visitors' sentiment based on restaurant diner comments. We will group visitors' comments into two types of sentiment: positive (satisfied) and negative (unsatisfied). The results of the data classification test are analyzed to determine its accuracy. The grouping of visitor satisfaction reviews using the naïve bayes algorithm provides an accuracy score of 73%. Besides, we visualize the research classification results in the browser-based R Shiny web application through word cloud and diagrams.Keywords:restaurant review, sentiment analysis, Naïve Bayes ClassifierAbstrak. Variasi pilihan restoran yang tidak sedikit menjadi salah satu masalah bagi pengunjung ketika ingin memilih restoran. Sehingga, pengunjung biasanya melihat rekomendasi atau penilaian pengunjung lain terhadap restoran tersebut terlebih dahulu untuk mengetahui penilaian pengunjung lain terhadap restoran tersebut. Penilaian atau review pengunjung dapat disajikan dalam analisis sentimen berdasarkan komentar para pengunjung restoran sebelumnya untuk melihat kepuasan pengunjung terhadap restoran tersebut. Penelitian ini dilakukan untuk mengetahui performa algoritma Naïve Bayes Classifier dalam melakukan klasifikasi sentimen berdasarkan komentar pengunjung restoran. Penelitian dilakukan dengan mengklasifikasikan data komentar pengunjung restoran menjadi dua kategori sentimen, yaitu: positif (satisfied) dan negatif (unsatisfied). Hasil pengujian pengklasifikasian data kemudian dianalisis akurasinya. Hasil pengelompokan review kepuasan pengunjung menggunakan algoritma naïve bayes memberikan nilai akurasi sebesar 73%. Visualisasi hasil klasifikasi dari analisis kemudian ditampilkan pada aplikasi berbasis web yaitu R Shiny berupa wordcloud dan diagram. Kata Kunci: penilaian restoran, analisis sentimen, Naïve Bayes Classifier
Analisis Sentimen Menggunakan Algoritma Naive Bayes Terhadap Review Restoran di Singapura Vynska Amalia Permadi
Jurnal Buana Informatika Vol. 11 No. 2: Vol 11, No 2 (2020): Jurnal Buana Informatika Volume 11 - Nomor 2 - Okober 2020
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v11i2.3769

Abstract

Abstract. Sentiment Analysis Using Naive Bayes Classifier Against Restaurant Reviews in Singapore. Various restaurant options bring up a problem for diners to pick a restaurant to dine in. Thus, visitors usually perceive the restaurant's recommendation or rating in advance to know other diners' opinions about the restaurant. Previous restaurant diners' comments can be presented in sentiment analysis to determine their satisfaction. This research investigates the Naïve Bayes Classifier algorithm's performance in classifying visitors' sentiment based on restaurant diner comments. We will group visitors' comments into two types of sentiment: positive (satisfied) and negative (unsatisfied). The results of the data classification test are analyzed to determine its accuracy. The grouping of visitor satisfaction reviews using the naïve bayes algorithm provides an accuracy score of 73%. Besides, we visualize the research classification results in the browser-based R Shiny web application through word cloud and diagrams.Keywords:restaurant review, sentiment analysis, Naïve Bayes ClassifierAbstrak. Variasi pilihan restoran yang tidak sedikit menjadi salah satu masalah bagi pengunjung ketika ingin memilih restoran. Sehingga, pengunjung biasanya melihat rekomendasi atau penilaian pengunjung lain terhadap restoran tersebut terlebih dahulu untuk mengetahui penilaian pengunjung lain terhadap restoran tersebut. Penilaian atau review pengunjung dapat disajikan dalam analisis sentimen berdasarkan komentar para pengunjung restoran sebelumnya untuk melihat kepuasan pengunjung terhadap restoran tersebut. Penelitian ini dilakukan untuk mengetahui performa algoritma Naïve Bayes Classifier dalam melakukan klasifikasi sentimen berdasarkan komentar pengunjung restoran. Penelitian dilakukan dengan mengklasifikasikan data komentar pengunjung restoran menjadi dua kategori sentimen, yaitu: positif (satisfied) dan negatif (unsatisfied). Hasil pengujian pengklasifikasian data kemudian dianalisis akurasinya. Hasil pengelompokan review kepuasan pengunjung menggunakan algoritma naïve bayes memberikan nilai akurasi sebesar 73%. Visualisasi hasil klasifikasi dari analisis kemudian ditampilkan pada aplikasi berbasis web yaitu R Shiny berupa wordcloud dan diagram. Kata Kunci: penilaian restoran, analisis sentimen, Naïve Bayes Classifier
Ecoprint dan Pengelolaan Media Sosial Pemasaran pada Kelompok Ibu-ibu PKK RW 03/RT 01, Demangan Yogyakarta Frans Richard Kodong; Juwairiah Juwairiah; Vynska Amalia Permadi; Riza Prapascatama Agusdin
Seminar Nasional Informatika (SEMNASIF) Vol 1, No 1 (2020): Peran Digital Society dalam Pemulihan Pasca Pandemi
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

AbstractThe PKK Driving Team (Empowerment of Family Welfare) runs from the central level to the village / kelurahan level, the PKK is managed and driven by the PKK Driving Team chaired by the wife of the Regional Leadership. At the smallest level, the PKK program can be developed by groups of PKK RW and RT mothers. One of the steps to increase the empowerment of village communities is the PKK RT 01 RW 03 Demangan Yogyakarta Women's Group since 2017 has formed an environmentally friendly fabric making business, where in its implementation the business involves community members so they can carry out a productive business that utilizes or processes materials -Natural / organic ingredients to produce environmentally friendly fabric products. In accordance with the development of information and communication technology, social media can become a reliable marketing medium. This paper will discuss about community economic empowerment and also how to use social media for online marketing. The approach is carried out by stages; the process of finding solutions to existing problems, discussion of the needs of social media to PKK group managers, is carried out by providing assistance in order to increase the capacity of administrators (in particular) and members (in general) to empower the community's economy, increase quantity and quality production tools, as well as product promotion and marketing.Keywords : PKK, Bussines, Fabric, MarketingTim Penggerak PKK (Pemberdayaan Kesejahteraan Keluarga) berada di tingkat pusat sampai dengan desa/kelurahan, PKK dikelola dan digerakkan oleh Tim Penggerak PKK yang diketuai oleh isteri Pimpinan Daerah. Pada tingkat yang terkecil pun program PKK dapat di kembangkan oleh kelompok ibu-ibu PKK RW maupun RT. Salah satu langkah peningkatan pemberdayaan masyarakat desa maka Kelompok Ibu-Ibu PKK RT 01 RW 03 Demangan Yogyakarta sejak tahun 2017 telah membentuk suatu usaha pembuatan kain ramah lingkungan, dimana dalam pelaksanaannya usaha tersebut melibatkan warga masyarakat agar dapat melakukan suatu usaha produktif yang memanfaatkan atau mengolah bahan-bahan alami/organik untuk menghasilkan produk kain ramah lingkungan. Sesuai perkembangan teknologi informasi dan komunikasi, media sosial mampu menjadi media pemasaran yang handal. Paper ini akan membahas tentang pemberdayaan ekonomi masyarakat dan juga bagaimana memanfaatkan media sosial untuk pemasaran daring (online marketing). Pendekatan diakukan dengan tahap ; proses pencarian solusi terhadap permasalahan yang ada, diskusi terhadap kebutuhan media sosial kepada pengurus Kelompok ibu-ibu PKK, dilakukan dengan memberikan pendampingan dalam rangka peningkatan kemampuan kepada pengurus (pada khususnya) dan anggota (pada umumnya) untuk pemberdayaan ekonomi masyarakat, meningkatkan kuantitas dan kualitas alat produksi, serta promosi dan pemasaran produkKata Kunci : PKK, Usaha, Kain, Pemasaran
Musical Instruments Recommendation System Using Collaborative Filtering and KNN Alfriska Deviane Puspita; Vynska Amalia Permadi; Aliza Hanum Anggani; Edwina Ayu Christy
Proceedings University of Muhammadiyah Yogyakarta Undergraduate Conference Vol. 1 No. 2 (2021): Engaging Youth in Community Development to Strengthen Nation's Welfare
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (484.727 KB)

Abstract

Introduction – The trend of e-commerce and online shopping has offered customers more product choices, but it also resulted in information overload. Nowadays, users are equipped with technology that allows websites to automatically deliver products that they may be interested in so that they can easily locate their favorite items from enormous options. To automate the recommendation process, recommender systems are created and built. This research creates a musical instrument recommendation system based on user reviews. Methodology/Approach – In this paper, we design and implement a recommendation system that combines the k-Nearest Neighbor (kNN) algorithm with a collaborative filtering framework. Collaborative filtering is chosen in this case because of its capability of providing new information to users by collecting information that has been obtained from the other users. Furthermore, kNN is considered as a suitable combination in this case since this method is relatively simple and able to find the similarity of objects being compared. Findings – To evaluate this study, the recommendation results are evaluated using the Root Mean Square Error (RMSE) calculation method, and the RMSE result obtained is 0.8734 for schema that divides dataset into 70% data train and 30% dataset using KNNWith Means with pearson measurements, and the MAE (Mean Absolute Error) result obtained is 0.5998 with schema 60% data train and 40% data test using KNNBasic algorithm with cosine similarity. Originality/ Value/ Implication – We present experimental results of consolidating the kNN algorithm in the collaborative filtering framework using Amazon’s musical instrument dataset. Furthermore, we can see that kNN together with a collaborative filtering algorithm performs a satisfactory outcome.
K-MEANS AND ELBOW METHOD FOR CLUSTER ANALYSIS OF ELEMENTARY SCHOOL DATA Vynska Amalia Permadi; Sylvert Prian Tahalea; Riza Prapascatama Agusdin
PROGRES PENDIDIKAN Vol. 4 No. 1 (2023): January 2023
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/prospek.v4i1.328

Abstract

This research was conducted to find the groups of elementary schools in the Special Capital Region of Jakarta, also known as DKI Jakarta. Elementary school data were selected because it is the first stage of formal education in Indonesia. This research used K-means clustering with the elbow method to determine optimal cluster numbers. The optimal cluster number is three with Cluster 2 having the most members, followed by Cluster 1 and Cluster 0. The data distribution of Cluster 2 shows that the second-most student body and public schools located in East and West Jakarta have an adequate student-to-teacher ratio based on Article 17 of Government Regulation 74, 2008.
Penerapan Aturan Asosiasi untuk Rule Mining pada Piala Dunia FIFA 2022 Sylvert Prian Tahalea; Vynska Amalia Permadi
Progresif: Jurnal Ilmiah Komputer Vol 19, No 1: Februari 2023
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v19i1.1063

Abstract

Football strategy comes from learning and evaluation of previous matche, but there are only a few research that conducted to explore the synergies between players. This research was conducted to implement the data mining method; and association’s rule in the sports data case study. Football is already embracing new technology as part of its ecosystem. This research used a data mining method to explore and analyze the passing route of a football team in the biggest football tournament, FIFA World Cup 2022, held in Qatar. The data was collected from the Sports References website and preprocessed before being mined. An association rule is constructed using an apriori algorithm by creating the item sets, calculating the support and confidence value, and defining the rules. The results showed the formation of 3 association rules with a confidence limit of 95%. Rule mining using an apriori association provides the possibility of an antecedent and consequent combination, which is a combination of the order in which the ball moves from the first player to the third player until the occurrence of a goal.Keywords: Association rule; Data mining; A priori algorithm; Soccer AbstrakPengembangan strategi sepak bola dilakukan dengan melakukan evaluasi dari pertandingan yang telah dilakukan sebelumnya, akan tetapi belum banyak penelitian yang dilakukan untuk melakukan evaluasi terhadap sinergi antar pemain pada suatu permainan. Penelitian ini dilakukan dengan tujuan untuk mengimplementasikan metode data mining pada bidang olahraga, salah satunya sepak bola, yang telah menggunakan teknologi sebagai bagian dari ekosistem permainan. Metode data mining digunakan untuk mengeksplorasi dan menganalisis operan pada tim sepak bola pada perhelatan turnamen Piala Dunia FIFA 2022 yang dilaksanakan di Qatar. Data yang dikumpulkan dari website Sport References dikenakan prapemrosesan data sebelum diolah. Penerapan aturan asosiasi dengan algoritme Apriori dilakukan dalam beberapa langkah, seperti pembentukan itemset, perhitungan nilai support dan confidence, hingga penentuan aturan atau rule. Hasil penelitian menunjukan pembentukan 3 aturan asosiasi dengan batasan confidence 95%. Rule mining menggunakan algoritme asosiasi Apriori memberikan kemungkinan kombinasi antecedent dan consequent yang merupakan kombinasi urutan perpindahan bola dari pemain pertama hingga pemain ketiga sampai dengan terjadinya goal.Kata kunci: Aturan asosiasi; Data mining; Algoritme Apriori; Sepak bola
Demand Forecasting for Improved Inventory Management in Small and Medium-Sized Businesses Dian Indri Purnamasari; Vynska Amalia Permadi; Asep Saepudin; Riza Prapascatama Agusdin
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 12 No. 1 (2023)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v12i1.57144

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.
Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems Budi Santosa; Muhamad Azam Fuadi; Mangaras Yanu Florestiyanto; Vynska Amalia Permadi; Wilis Kaswidjanti
Telematika Vol 16, No 1: February (2023)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v16i1.2080

Abstract

The large number of users and the items offered in e-commerce make it difficult for buyers to choose the right items and sellers to offer their items to the right buyers. To overcome this problem, a system that can offer and recommend goods automatically, namely a recommendation system is needed. One of the most popular methods used to create a recommendation system is collaborative filtering, the recommendations are created based on similarities in user behavior. Unfortunately, this method has a weakness, namely cold start, where the recommendations will be inaccurate on data that has a lot of new users and items due to minimal historical data regarding user behavior. This problem will be tried to be solved in this study using a hybrid method, where this method combines more than 1 method to create a list of recommendations so that it will cover the shortcomings of each method. This study uses Amazon's e-commerce product and transaction data. The use of the hybrid method in this study can overcome the cold start problem by using switching and mixed methods, by not using the collaborative filtering model on new user recommendations or users who have little interaction. New users will receive recommendations based on the combination of popularity-based and content-based filtering models. This can be seen from the Mean Absolute Error (MAE) value of the model, where the MAE value for the data with a minimum user has at least 3 times rating is 0.566883, for the minimum 7 times, the MAE value is smaller, 0.487553.
LSTM forecast of volatile national strategic food commodities Herlina Jayadianti; Vynska Amalia Permadi; Partoyo Partoyo
JURNAL INFOTEL Vol 15 No 4 (2023): November 2023
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v15i4.1037

Abstract

Using the Long Short-Term Memory (LSTM) forecast, this study suggested a short-term projection model for national critical food pricing commodities. The model was trained using historical time-series data from each commodity price over the previous three years. The results demonstrated that the proposed LSTM architecture model was generalizable to all commodities and performed well in the majority of cases. This result indicates that the model is resilient and can be used to forecast commodity prices and offer accurate forecasts for most of the ten volatile national strategic foods, with an error value of less than 0.01 and an accuracy value of >95%. The model, however, failed to recognize the pricing pattern in cooking oil and beef commodities, both of which had increasing trend patterns. This shows that the model may be unable to effectively estimate commodity prices in the face of fast price fluctuations. The magnitude and quality of the dataset hampered the investigation. The time period selected also influenced the study. Future research should employ a more extensive and diversified dataset to increase the model's performance, allow it to learn more patterns and make more accurate predictions, and could use a more extended lookup date to improve forecast accuracy. This would enable the model to account for more recent pricing changes. Despite the limitations, the results of this study are promising and could be used to develop a more accurate and reliable food price prediction model. Policymakers and stakeholders could use the model to make informed food prices and inflation decisions.
Co-Authors Agusdin, Riza Prapascatama Alfriska Deviane Puspita Aliza Hanum Anggani Asep Saepudin Dian Indri Purnamasari Edwina Ayu Christy Frans Richard Kodong Herlina Jayadianti Juwairiah Juwairiah Mangaras Yanu Florestiyanto Muhamad Azam Fuadi Partoyo Partoyo Santosa, Budi Santoso, Bagus Jati Sylvert Prian Tahalea Tahalea, Sylvert Prian Tohari Ahmad Wilis Kaswidjanti