Claim Missing Document
Check
Articles

Found 7 Documents
Search

Metode K-Means dalam Mengukur Tingkat Pemahaman Materi Mata Kuliah Inti dan Penilaian Mahasiswa di Prodi Informatika Deti Karmanita; Defit, Sarjon; Sumijan
Jurnal KomtekInfo Vol. 11 No. 3 (2024): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v11i3.551

Abstract

Data mining adalah proses yang menggunakan teknik statistik, matematika, kecerdasan buatan, dan machine learning untuk mengekstrasi dan mengidentifikasi informasi yang bermanfaat dan pengetahuan yang terkait dari berbagai database besar. KDD sering disebut juga sebagai penemuan pengetahuan dalam basis data. Data Mining memiliki lima fungsi utama, termasuk pengelompokan (clustering), klasifikasi (classification), asosiasi (association), urutan (sequencing) dan peramalan (forecasting). Algoritma clustering berupaya memisahkan kumpulan informasi yang ada menjadi kelompok-kelompok yang homogen atau sejenis. Tingkat kesamaan data di dalam suatu kelompok akan menghasilkan nilai yang semakin besar, sementara perbedaan antar kelompok akan menghasilkan nilai yang semakin kecil. Algoritma K-Means merupakan bagian dari clustering data mining, dimana algoritma K-Means dapat dipergunakan untuk pembentukan kelompok baru dari data. Pembentukan kelompok baru dari data pada algoritma K-Means dengan proses pembentukan cluster pada proses yang dilakukan. Penelitian ini bertujuan untuk mengetahui tingkat pemahaman materi mata kuliah inti pada program studi Informatika Universitas Dehasen yang diterima oleh mahasiswa. dimana peneliti menyebarkan kuisioner kepada mahasiswa untuk menentukan tingkat pemahaman materi mata kuliah inti menjadi 4 kelompok yaitu sangat baik, baik, cukup baik dan kurang baik. Metode yang digunakan adalah K-Means dengan tahapan yaitu pemilihan data, pra-pemrosesan, transformasi data, ekstraksi informasi dan evaluasi hasil. Data terdiri dari 46 mata kuliah inti yang di ambil dari kurikulum Prodi Informatika yang dinilai oleh mahasiswa dengan pemahaman materi mata kuliah Sangat Baik sebanyak 29%, Baik sebanyak 35%, Cukup Baik sebanyak 24%, Kurang Baik sebanyak 12%. Penelitian ini menunjukkan bahwa implementasi metode K-Means dengan dukungan aplikasi RapidMiner efektif dalam mengelompokkan data pemahaman materi mahasiswa dan hasilnya dapat digunakan untuk evaluasi dan peningkatan kualitas pengajaran.
Penerapan Metode Rough Set Dalam Memprediksi Penjualan Pada PT. Jaya Framex Bengkulu Lubis, Fitri Amelia Sari; Lubis, Siti Sahara; Agustin, Riris; Karmanita, Deti; Defit, Sarjon
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.758

Abstract

So far, in predicting sales at PT. Jaya Framex Bengkulu, only relies on manual calculations. There are no calculations that use a system to help predict sales at PT. Jaya Framex Bengkulu in the future. As more and more entrepreneurs emerge, it requires entrepreneurs to plan sales strategies. So that what is produced does not decrease further, and is not less competitive with other entrepreneurs, to avoid this, it is necessary to have sales predictions to predict sales so that you can plan future sales strategies. Based on the research conducted, the author can draw the conclusion that predicting the number of food products using Data Mining is very helpful in processing data that has been classified such as product supply, product type and capabilities so that it produces rules that support a decision which can later be used as support for sales prediction decisions. to be more optimal. From 13 sample data of the Data Mining sales process using the rough set method, 5 Reducts were produced which were extracted into knowledge of 11 Generate Rules, thereby producing a decision that was conveyed from the resulting rules. The results of this research can be used by developers to predict future sales. It is hoped that adding new variables can produce more varied decisions and more useful knowledge as decision support
Anomali Data Mining Menggunakan Metode K-Means Dalam Penilaian Mahasiswa Terhadap Pelayanan Prodi Karmanita, Deti; Hendrik, Billy
Jurnal Media Infotama Vol 19 No 2 (2023): Oktober
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v19i2.4744

Abstract

Cluster analysis is a data mining technique that aims to identify a group of objects that have the same characteristics. The number of groups that can be identified depends on the amount of data and the type of object, so that data problems arise when there is a change to a number of redundant data, but not all of it is changed where the data above is repeatedly made into one table with a different code as the primary key and there are anomalies Insertion, so K-means is one method of clustering data which is divided into the form of one or more clusters/groups that have the same characteristics. Student data clustering uses the k-means method, consisting of student assessments. This study uses student assessment data. Then it was concluded that the assessment group was based on reliability aspects: the ability of lecturers, education staff and administrators to provide services, responsiveness aspects: the willingness of lecturers, education staff and administrators to help students and provide services quickly, aspects of certainty ( assurance): the ability of lecturers, staff and administrators to give confidence to students that the services provided are in accordance with the provisions, aspects of empathy (empathy): the willingness/concern of lecturers, staff and managers to give attention to students, tangibles aspects: students' assessment of the adequacy , accessibility, quality of facilities and infrastructure from the grouping results based on reliability, responsiveness, assurance and empathy data.
Sistematik Literatur Review : Intelegent System Didunia Pendidikan Resnawita, Resnawita; Karmanita, Deti
Journal of Information System and Education Development Vol. 2 No. 4 (2024): Journal of Information System and Education Development
Publisher : Manna wa Salwa Foundation (Yayasan Manna wa Salwa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62386/jised.v2i4.113

Abstract

Perkembangan teknologi informasi dan komunikasi telah membawa dampak signifikan pada berbagai sektor kehidupan, termasuk dalam dunia pendidikan. Salah satu inovasi yang tengah berkembang pesat adalah penerapan sistem cerdas atau intelligent systems. Di dunia pendidikan, penerapan sistem cerdas tidak hanya terbatas pada penggunaan teknologi untuk mendukung kegiatan belajar-mengajar, tetapi juga mencakup pengelolaan administrasi, evaluasi hasil belajar, serta pengembangan kurikulum yang lebih responsif terhadap kebutuhan dan perkembangan peserta didik. Metode penelitian yang digunakan ialah metode systematic literatur review. Penelitian ini bertujuan untuk mengeksplorasi manfaat, tantangan, dan peran Artificial Intelligence (AI) dalam dunia pendidikan melalui pendekatan Systematic Literature Review (SLR). Hasil penelitian menunjukkan Penerapan Artificial Intelligence (AI) dalam pendidikan memberikan manfaat berupa personalisasi pembelajaran, otomatisasi tugas administratif, dan dukungan pembelajaran mandiri. AI juga meningkatkan aksesibilitas dan interaktivitas dalam pendidikan. Namun, implementasinya menghadapi tantangan seperti ketergantungan teknologi, risiko privasi data, dan kesenjangan akses. AI melengkapi, bukan menggantikan, peran guru yang tetap penting dalam membangun hubungan emosional dan membimbing siswa secara etis. Kolaborasi antara AI dan guru dapat meningkatkan kualitas pendidikan.penerapan AI di bidang pendidikan membutuhkan pendekatan yang bijaksana dan sinergi antara teknologi dan guru untuk memastikan pendidikan yang berkualitas, inklusif, dan berkelanjutan.
PENERAPAN BIG DATA ANALYTICS DALAM PREDIKSI TREN E-COMMERCE DI INDONESIA Karmanita, Deti; Utami, Feri Hari; Prahasti, Prahasti; Harwini, Dewi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4587

Abstract

Abstract: The growth of e-commerce in Indonesia has been accelerating, driven by increasing internet penetration and the widespread use of mobile devices. The large, complex, and diverse volume of transaction data requires appropriate analytical methods to produce accurate trend predictions. This study aims to apply Big Data Analytics in analyzing consumer shopping patterns, popular product trends, and factors influencing purchasing decisions. Data were collected from various e-commerce platforms, processed using Hadoop and Spark, and further analyzed through predictive modeling with Machine Learning algorithms. The results indicate that integrating Big Data Analytics can improve trend prediction accuracy by up to 85% compared to conventional methods. These findings are expected to support strategic decision-making in Indonesia’s e-commerce sector. Keywords: Big Data Analytics, E-commerce, Machine Learning, Trend Prediction, Indonesia Abstrak: Pertumbuhan e-commerce di Indonesia semakin pesat, didorong oleh penetrasi internet dan meningkatnya penggunaan perangkat mobile. Data transaksi yang besar, kompleks, dan beragam membutuhkan metode analisis yang tepat untuk menghasilkan prediksi tren yang akurat. Penelitian ini bertujuan untuk menerapkan Big Data Analytics dalam menganalisis pola belanja konsumen, tren produk populer, serta faktor yang memengaruhi keputusan pembelian. Metode yang digunakan mencakup pengumpulan data dari berbagai platform e-commerce, pemrosesan menggunakan Hadoop dan Spark, serta analisis prediktif dengan algoritma Machine Learning. Hasil penelitian menunjukkan bahwa integrasi Big Data Analytics mampu meningkatkan akurasi prediksi tren hingga 85% dibanding metode konvensional, sehingga dapat mendukung strategi bisnis e-commerce di Indonesia. Kata kunci: Big Data Analytics, E-commerce, Machine Learning, Prediksi Tren, Indonesia
Penerapan Metode Clustering dengan Algoritma K-Means pada Pengelompokkan Peminatan Mata Kuliah Deti Karmanita; Billy Hendrik
Jurnal Ilmiah Dan Karya Mahasiswa Vol. 1 No. 6 (2023): DESEMBER : JURNAL ILMIAH DAN KARYA MAHASISWA
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jikma.v1i6.1028

Abstract

Choosing a concentration in student academic activities is not an easy thing because it depends on interests, talents and desires, therefore careful consideration is needed so that students do not make a mistake in choosing the desired concentration. This often happens when final semester students do their final assignment but it does not match their field of ability. Choosing a concentration haphazardly without careful consideration can have a negative impact on students, namely difficulty in absorbing lecture material. Therefore, a special method is needed that students can use to determine student concentration. One of the methods used is the K-Means method. The K-Means algorithm is a non-hierarchical method that initially takes a number of population components to become the initial cluster center. At this stage the cluster center is selected randomly from a set of data populations. Next, K-Means tests each component in the data population and marks the component to one of the cluster centers that has been defined depending on the minimum distance between components and each cluster. with a total of 100 data records, using cluster centers C1 70, 82.5, 85, C2 70, 75, 80 and C3 80, 85, 80 produces 6 iterations with the results of Cluster 1. Students are recommended to enter the Expert Systems Concentration. In the calculation above, there are 3 students who are included in cluster 1. Cluster 2 Students are recommended to enter the multimedia programming concentration. In the calculation above, there are 20 students included in cluster 2. Cluster 3 Students are recommended to enter the Cisci and Network Concentration. In the calculation above, there are 34 students included in cluster 3. From validation testing it is obtained: initial and final centroid of the first attribute: 5.83%, second attribute: 31.44%, third attribute: 35.89%. It is hoped to develop concentration clustering for Information Systems majors using other methods, not only the K-Means method, and determining concentration majors using variables other than academic grades, such as non-academic achievement scores which are linear with the study program. In the future, the concentration determination system will be carried out in the information systems study program.
PENGGUNAAN MEDIA SOSIAL SEBAGAI PROMOSI BISNIS DIGITAL TINJAUAN SYSTEMATIC LITERATURE REVIEW DENGAN MACHINE LEARNING Deti Karmanita; Jhon Veri
Juremi: Jurnal Riset Ekonomi Vol. 4 No. 1: Juli 2024
Publisher : Bajang Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53625/juremi.v4i1.8037

Abstract

This research aims to examine the use of social media as a promotional tool in digital business through a Systematic Literature Review (SLR) approach supported by machine learning methods. Social media has become a major platform for marketing due to its ability to reach consumers widely and efficiently. This study identifies, evaluates, and interprets various research results related to the role of social media in improving marketing performance. The data used in this study comes from journal articles and proceedings published between 2020 and 2024, with a focus on social media and digital business. The SLR method is used to avoid subjective bias in the selection and assessment of literature. The results show that social media not only serves as an information channel, but also as an effective tool to build interactions with consumers, increase customer trust, and strengthen loyalty. Machine learning is used to analyze patterns and trends in the collected data, thus providing deeper insights into the effectiveness of social media in digital business promotion.