Claim Missing Document
Check
Articles

Found 17 Documents
Search

CLUSTERING LOYALITAS PELANGGAN DENGAN METODE RFM (RECENCY, FREQUENCY, MONETARY ) DAN FUZZY C-MEANS Sudriyanto Sudriyanto
Prosiding SNATIF 2017: Prosiding Seminar Nasional Teknologi dan informatika (BUKU 3)
Publisher : Prosiding SNATIF

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

Abstract

Semakin maju dan berkembangnya dunia usaha, menciptakan persaingan yang luar biasa ketata. Persaingan yang ada mengharuskan pemilik usaha untuk selalu dapat memahami sebuah pasar yang terus berkemnbang. Banyak faktor yang mempengaruhi berkembangnya usaha, salah satunya pelanggan. Untuk membangun strategi yang handal dalam dunia usaha, harus menemukan cara untuk menarik dan mengembangkan aset manusia yang tepan dan menjaga mereka. Untuk mengetahui hal tersebut, dilakukan penelitian mencari pola dari mutu calaster dengan pemilihan atribut mengunakan metode RFM (Recency, Frequency, Monetary) untuk mengklaster pelanggan yang lebih efisien dan akurat dengan algoritma Fuzzy C-Means untuk memilih pelanggan yang potensial dan loyal. Dari hasil pengukuran validitas menggunakan Partition Coefficient Index (PCI) dan Xie dan Beni (XBI) 5 cluster dengan pangkat dua dan tiga dengan nilai PCI pangkat dua 0,8156, pangkat tiga 0,5860, untuk nilai XBI pangkat dua 0,0069, pangkat tiga 0,0632 dimana nilai PCI yang mendekati angka satu mempunyai arti kualitas cluster yang didapat semakin baik, sedangkan untik XBI yang semakin kecil mempunyai arti kualitas hasil pengelompokan yang semakin baik. Dari hasil pengukuran validitas mengunakan PCI dan XBI, nilai akuraasi FCM dengan pangkat dua lebih baik dibandingkan dengan nilai akurasi FCM dengan pangkat tiga.Kata kunci: RFM (Recency, Frequency, Monetary), Fuzzy C-Means, clustering, validitas cluster, Partition Coefficient Index (PCI) dan Xie dan Beni (XBI)
DETEKSI LEMBAR JAWABAN KOMPUTER MENGGUNAKAN OMR (OPTICAL MARK RECOGNITION) DI MTS NURUL IMAN Moh Novi Hermawan; Maulidiansyah Maulidiansyah; Sudriyanto Sudriyanto
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 8 No 3 (2021): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v8i3.1078

Abstract

Conventional exams or manual exams were implemented decades ago and are still used today. This type of test uses a writing instrument as a test medium, namely the test is carried out in the form of general stationery such as paper, pencil, and pen, the questions and answers to the test are written by hand. One way to assess the success of the teaching process in schools is to carry out exams. In the implementation of the exam at MTS Nurul Iman, he used a computer answer sheet as an entry. Meanwhile, schools are required to have certain scanners that are expensive to correct computer answer sheets. Another alternative that can be done by schools is to manually correct computer answer sheets, but this makes a lot of time wasted, and can cause errors in correcting and slow work productivity. From the problems that have been described, to detect the computer answer sheet, a method is needed. Through this research, it is hoped that a method can be developed that automatically detects the answer choices on the computer answer sheet, so that more accurate and faster results are obtained. Based on the problems of this study, the researchers used the OMR (Optical Mark Recognition) method to detect computer answer sheets automatically. From the test results, it can be concluded that the accuracy of detection of computer answer sheets using OMR is 97%.
SISTEM INFORMASI NOTIFIKASI KEGIATAN MASJID MUJAHIDIN MENGGUNAKAN ANDROID Moh Ahsan Al Maliki; Wahab Sya’roni; Sudriyanto Sudriyanto
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 8 No 4 (2021): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v8i4.1207

Abstract

Mujahidin mosque is the center of Islamic religious activities and many activities are carried out at the mosque. As in Mujahidin mosque, including tahtimul Qur'an, annual agendas such as donations to orphans, Islamic new year and commemorating the birth of the Prophet Muhammad. and there is a schedule for the imam of the mosque, muezzin, and bilal. In this case, the mosque takmir has trouble handling the agenda that will be carried out in weekly, monthly and yearly activities at the mosque. Even the schedule when on the mading board the schedule has been included and the congregation has been distributed invitations to announcements that come to the mosque the delivery of their activities is still not conveyed consistently, therefore an information system for notification of mujahideen mosque activities is needed using Android By using the waterfall method which can make it easier and faster for mosque administrators to inform mosque activities to the public with a mosque activity notification application. The waterfall model provides a sequential or sequential software life flow like a waterfall requirement,system and software desain, implementation and unit testing, integration and system testing, dan opration and maintenence. The results of the blackbox test obtained a conclusion that was appropriate that all those tested externally obtained a percentage value of 83%, so that it could be said to be very good and feasible to use.
Implementasi Algoritme Decision Tree (C4.5) dengan Optimize Weights (PSO) untuk Memprediksi Kelulusan Mahasiswa Tepat Waktu Sudriyanto Sudriyanto; Rudi Rizaldi; M. Ainun Rofiq Hariri
Jurnal Informatika Universitas Pamulang Vol 6, No 2 (2021): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v6i2.9197

Abstract

The implementation of quality education is a requirement for higher education institutions to produce quality students. Government regulations regarding the limitation of the maximum length of lectures that students can take are intended so that the institutions involved in the educational process have careful planning in the learning process. Good planning is expected to be able to accreditation value of higher education institutions and deliver student studies so that they can graduate on time. In order to achieve these results, aspects that are so influential on the optimal value of accreditation results are needed, one of which is that students graduate on time and play an importan role in determining the results of accreditation. Decision tree itself is a very simple algorithm and easy understanding, decision tree algorithm alonei is enough to produc good and optimal accuracy values. Therefore, the optimization method particle swarm optimization (PSO) with its advantages can increase the level of accuracy by removing irrelevant features. The results of the study using a student dataset of class 2016 - 2017 explain that the optimization ofparticle swarm optimization (PSO) can produce 92.36% accuracy and increase the accuracy of 01.05%, with the decision tre method C4.5 with an accuracy rate of 91.31%. Furthermore, the T-test testing process is carried out on the decision tree algorithm C4.5 and the decison tree algorithm C4.5 optimization of particle swarm optimization (PSO) with the final result alpha = 0.635 where the results are less significant, it is said to be significant if the test results are below alpha = 0.050. 
Pendampingan Kelompok Mahasiswa dalam Memanfaatkan Marketplace dan Online Shop Sebagai Media Pemasaran Produk Inovasi Pesantren Sudriyanto Sudriyanto; Isti Ghulam Hidayatullah; M. Alman David; Putri Tsamrotul Fu’adiyah; M. Fajar Santoso; M. Lukman Hakim
GUYUB: Journal of Community Engagement Vol 2, No 1 (2021): Pendampingan Pendidikan, Agama, dan Teknologi
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/guyub.v2i1.2048

Abstract

Based on the results of a survey report from the Indonesian Internet Service Providers Association (AP JII) on June 2-25, 2020, the total number of Indonesian internet users is 73.7 percent or 196,714,070.3 million people from the total population in Indonesia of 266,911,900 people. . Fenomina is currently using the internet as a means of promotion for online marketing. Many companies are so implementing online sales that it has had an impact on the decline in the turnover of otheer companies that are still offline. The purpos of this activity is to improve the skills and knowledge of companies and students so they can implement marketplace-based online sales. The essence of this activity with one day of training to create a marketplace account and online marketing asistance for a full month. It is hoped that with this training, partner companiies and students can advance and develop their online marketplacee-based sales independently. The training model with one day followed by one month of mentoring is expected to be areference for similar activities.
PKM Pendampingan dan Pelatihan Microsoft Office untuk Meningkatkan Keterampilan Santri Pesantren Nurul Hidayah Sudriyanto Sudriyanto; Sukma Agung Adi Luwih; Syamsul Arifin; Wahyu Pratama Mukti; Wakiludinil Hasan
GUYUB: Journal of Community Engagement Vol 3, No 2 (2022)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/guyub.v3i2.3945

Abstract

The development of technology has helped a lot of human work. One of the things that we can enjoy from these technological developments include Microsoft Word, Microsoft Excel and power points. Microsoft Word, functions as a word processing software includes creating, editing, and formatting documents. The students have not been able to operate Microsoft word, Excel and Power Point because they are not taught at school, the high cost of computer courses among students. One of them is to train the ability to use a word processing application, namely Microsoft Word. Community service activities are emphasized in the form of training on how to apply Microsoft Office for students of the Nurul Hidayah Islamic Boarding School. It is hoped that with this training, students can know more about the basic techniques of using Microsoft Office by utilizing Microsoft Word, Microsoft Excel, Microsoft Power Point. The results of the service activities carried out provide experience and skills for students in using Microsoft Office. Thus, the implementation of community service activities at the Nurul Hidayah Islamic Boarding School Foundation Using Microsoft Office provides significant benefits for improving the skills of students in utilizing information technology and computers. The students were very enthusiastic about participating in further training activities. The students already understand and can run Microsoft Office applications. 
Implementasi Particle Swarm Optimization (PSO) untuk Optimisasi Algoritma Naive Bayes dalam Memprediksi Mahasiswa Lulus Tepat Waktu Sudriyanto Sudriyanto
COREAI: Jurnal Kecerdasan Buatan, Komputasi dan Teknologi Informasi Vol 2, No 1 (2021)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (482.542 KB) | DOI: 10.33650/coreai.v2i1.2181

Abstract

Istitusi perguruan tinggi merupakan wadah bagi mahasiswa dalam mendapatkan pengetahuan sebelum terjun langsung dan bersaing dalam dunia kerja. Institusi perguruan tinggi berperan dalam menciptakan lulusan yang sesuai dengan kebutuhan dunia industri. Salah satu indikator dalam keberhasilan perguruan tinggi salah satunya ialah jumlah kelulusan mahasiswa yang mana berdampak kepada penilaian masyarakat dan akreditasi dari pemerintah. Peneliti sudah banyak melakukan penelitian dalam memprediksi kelulusan mahasiswa untuk mengetahui lulus terlambat atau tepat waktu. Menurut kondisi tersebut metode data mining yang cocok digunakan adalah classification. Salah satu metode data mining adalah Naive Bayes. Dalam penelitian ini algoritma yang digunakan Naive Bayes dengan PSO (Particle Swarm Optimization) sebagai penyeleksi atribut. Dari dataset yang digunakan adalah sebanyak 384 record data mahasiswa dari smestet 1 sampai dengan smester 8 diperoleh nilai akurasi sebesar 89.46%. Penelitian ini mempunyai tujuan agar universitas bisa memprediksi mahasiswa yang berpotensi tidak lulus tepat waktu, yang kemudian universitas akan memberikan penanganan khusus ataupun peringatan kepada mahasiswa agar supaya mahasiswa tersebut bisa lulus tepat pada waktunya.
Optimasi Parameter Support Vector Machine Menggunakan Algoritma Genetika untuk Meningkatkan Prediksi Pergerakan Harga Saham Sudriyanto Sudriyanto; Rian Hidayad; Rafsanjai Akbar Ronaldo; Riangga Aji Prasetiyo; Setyo Agung Edho Wicaksono
COREAI: Jurnal Kecerdasan Buatan, Komputasi dan Teknologi Informasi Vol 3, No 1 (2022)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1273.723 KB) | DOI: 10.33650/coreai.v3i1.3859

Abstract

Prediksi pergerakan harga saham menjadi satu topik yang menarik terutama bagi para investor saham, dealer dan broker. Kesulitan dalam memprediksi pergerakan harga saham dikarenakan banyak faktor ketidak pastian yang terlibat seperti kinerja perusahaan, faktor ekonomi nasional maupun internasional, iklim politik dan perbedaan persepsi dari setiap orang terhadap suatu saham. Tujuan penelitian ini adalah meningkatkan hasil prediksi pergerakan harga saham. Salah satu metode yang dapat digunakan untuk memprediksi pergerakan harga saham yaitu Support Vector Machine (SVM). SVM memiliki kelemahan pada sulitnya memilih parameter terbaik dari suatu kernel termasuk parameter pinalti untuk data yang diklasifikasikan secara benar. Untuk meningkatkan akurasi dari prediksi harga saham, yang bertujuan untuk mengoptimasi algoritma SVM dengan algoritma genetika (GA) untuk mendapatkan parameter terbaik sehingga akurasi prediksi dapat ditingkatkan. Pada penelitian ini menggunakan data historis dari perusahaan PT Astra International Tbk mulai dari 2013 sampai 2021. Atribut yang digunakan pada penelitian ini yaitu (Date, Open, High, Low, Close dan Volume). Dari hasil percobaan didapat akurasi prediksi dengan metode Support Vector Machine dengan nilai Root Mean Squared Error (RMSE) sebesar 140.000 +/- 5.698 dan Squared Error (SE) sebesar 19629.215 +/- 1609.864. Sedangkan dengan metode Support Vector Machine Berbasis Algoritma Genetika dengan nilai Root Mean Squared Error (RMSE) sebesar 101.208 +/- 9.475 dan Squared Error (SE) sebesar 10323.858 +/- 1956.237. Dari hasil percobaan dapat dilihat bahwa nilai tingkat akurasi untuk prediksi pergerakan harga saham menggunakan metode Support Vector Machine Berbasis Algoritma Genetika mendapatkan hasil dengan tingkat akurasi yang lebih baik.
Implementasi Algoritma C4.5 Untuk Memprediksi Kesesuaian Gaya Belajar Siswa Sekolah Dasar Sudriyanto Sudriyanto; Feriska Listrianti; Jamal Jamal
COREAI: Jurnal Kecerdasan Buatan, Komputasi dan Teknologi Informasi Vol 3, No 2 (2022)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (844.573 KB) | DOI: 10.33650/coreai.v3i2.5074

Abstract

Data Mining adalah proses mengekstraksi dan menemukan pola dalam kumpulan data besar yang melibatkan metode dalam proses  pembelajaran mesin, statistik, dan sistem basis data. SD Negeri Sidodadi Paiton merupakan sekolah dasar yang terletak di desa Sidodadi kecamatan paiton. Pada proses pembelajaran di SD Negeri Sidodadi, masih banyak murid yang tidak fokus dan tidak memiliki kemauan untuk belajar, kemungkinan terbesar adalah ketidak cocokan gaya belajar dan metode belajar guru tersebut. Oleh karenanya, penulis melakukan analisis data mining terhadap data murid dan kepribadiannya agar data tersebut dapat berubah menjadi informasi yang bermanfaat bagi lembaga. Informasi ini bisa membantu untuk meningkatkan proses belajar mengajar di SD Negeri Sidodadi Paiton. Penulis menggunakan hasil data quisioner terhadap siswa kelas 4, 5 dan 6 sebanyak 165 data siswa-siswi yang telah penulis sajikan. Dalam proses analisis ini, penulis menggunakan tools Rapiminer Studio. Metode yang digunakan decision tree dengan algoritma C4.5. Hasil prediksi menggunakan algoritma decision tree C4.5 dengan hasil 8 rules. Persentasi hasil akurasi decision tree dengan menggunakan menggunakan 10 Fold Cross Validation  membuktikan bahwa tingkat akurasinya sebesar 81.18%. dengan nilai class precission untuk prediksi kinestetik sebesar 85.43%, prediksi visual sebesar 33.33%, dan prediksi auditorial sebesar 0.00%, hasil 5 Fold Cross Validation akurasinya sebesar 82.27%. dengan nilai class precission untuk prediksi kinestetik sebesar 86.09%, prediksi visual sebesar 41.67%, dan prediksi auditorial sebesar 0.00%. Dari hasil perbandingan membuktikan implementasi dengan model 5 Fold Cross Validation lebih baik.
PENERAPAN ALGORITMA K-MEANS UNTUK CLUSTERING SANTRI PRA-SEJAHTERA DI YAYASAN BANTUAN SOSIAL (YBS) AZ-ZAINIYYAH PONDOK PESANTREN NURUL JADID Sudriyanto Sudriyanto; Ahmad Khairi; Atoillah Shohibul Hikam
NJCA (Nusantara Journal of Computers and Its Applications) Vol 8, No 1 (2023): June 2023
Publisher : Computer Society of Nahdlatul Ulama (CSNU) Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36564/njca.v8i1.234

Abstract

The problem of poverty is a social problem that has a sizeable impact in various countries, not only in a large scope, but even on a small scale, poverty is a problem that needs special attention, one example is within the scope of Islamic boarding schools. In this study, the dataset was obtained from Pedatren, namely data from SLTP and SLTA Nurul Jadid Islamic Boarding School students in 2021. The algorithm used in this research is the K-Means Clustering method. The K-Means Clustering method is an Unsupervised technique, as well as a method of grouping data into several groups, according to each other's characteristics. The advantages of the K-Means algorithm are relatively simple and easy to implement, scalable for large datasets, easily adaptable to new examples, commonly implemented to clusters of different shapes and sizes. The amount of data used is 749 junior and senior high school students data, divided into 4 clusters namely (C1) Pre-Prosperous Families (C2) Prosperous Families 1 Prosperous Families 2 (C3) and Prosperous Plus Families (C4). As for the phase that done in this research such as identifying a problem, a literature review, data collection, prepocessing, the implementation of k-means algorithm clustering and the last evalusi the results of. From the results of the grouping of clusters of data or C1 = 163, C2 = 215, C3 = 246 and C4 = 125.The end of use evalusi matrix davies bouldin mem-peroleh akurai 0,90 value index.