Claim Missing Document
Check
Articles

Implementasi Algoritma Fuzzy C-Means menggunakan Model LRFM untuk Mendukung Strategi Pengelolaan Pelanggan Aini, Delvi Nur; Afdal, M.; Novita, Rice; Mustakim, Mustakim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7616

Abstract

The same treatment of all customers will cause customers who are not so valuable to become value destroyers in the concept of Customer Relationship Management. Providing discounts and promos to all customers without differentiating customer segments has not provided significant benefits for a company. These two things are being experienced by BC 4 HNI Pekanbaru, so changes are needed in evaluating the strategies taken to maintain relationships with customers and form segments according to customer characteristics. Customer segments can be analyzed from sales transaction data. The purpose of this study is to manage and group sales transaction data in determining customer segmentation so that the strategy is more targeted. The analysis of customer transaction data was carried out by grouping the data using the Fuzzy C-means algorithm and the length, recency, frequency, monetary (LRFM) model, and AHP weighting.  The formation of the number of validated clusters of the silhouette index and ranking is carried out by multiplying the weight of AHP to find the customer lifetime value (CLV) so that it can be known which customer groups provide high value to the company. The result of this study is that BC 4 HNI Pekanbaru customers are grouped into 2 segments, namely the potential customer group which has a fairly frequent transaction value with an average monetary value of Rp. 2,802,495.00 and a fairly high number of transactions contribute greatly to the Company and the new customer group which means a new customer segment with uncertain funds, an average monetary of Rp. 104,567.00. Based on the segment, BC 4 HNI Pekanbaru can carry out a strategy in managing its customers according to the type of segment generated from this research.
Klasifikasi Sentimen Pengguna X Terhadap Pemboikotan Produk Pro Israel Menggunakan Algoritma Machine Learning Susanti, Pingki Muliya; Afdal, M; Permana, Inggih; Marsal, Arif
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6533

Abstract

The campaign to boycott pro-Israel goods emerged as a result of the enduring conflict between Israel and Palestine. This boycott initiative led to a decline in sales, which adversely impacted the livelihoods of employees, manifesting in diminished bonuses, salary reductions, and job terminations. Such actions elicited a variety of reactions from the public on platform X. This study seeks to categorize the sentiments of X users regarding the boycott of pro-Israel products by comparing the efficacy of Machine Learning algorithms, namely Support Vector Machine and Random Forest. To address the class imbalance within the dataset, this research employs the synthetic minority over-sampling technique (SMOTE). The dataset comprised 2,275 entries, gathered through web scraping methods on the X platform. The findings indicate that a majority of X users in Indonesia endorse the boycott movement, exhibiting a positive sentiment of 58%. The SVM algorithm, when combined with SMOTE, demonstrated the highest performance in sentiment classification, achieving an accuracy of 90.54%, whereas Random Forest attained an accuracy of only 83.1%. This research offers insights into the views of the Indonesian populace regarding the boycott of pro-Israel products.
Analisis Sentimen Terhadap Program Makan Bergizi Gratis Menggunakan Algoritma Machine Learning Pada Sosial Media X Triningsih, Elsa; Afdal, M; Permana, Inggih; Rozanda, Nesdi Evrilyan
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6534

Abstract

The government has launched the Free Nutritious Meal Program as part of a strategic effort to reduce stunting in Indonesia. However, the program has generated a lot of controversy among the public, especially regarding the large budget allocation that is considered burdensome and its impact on the education sector and the country's financial stability. This study aims to analyze public sentiment towards the program by utilizing data from social media platform X (Twitter) as much as 2,400 data. Public sentiment is classified into three categories, namely positive, negative, and neutral, using two machine learning algorithms, namely Support Vector Machine (SVM) and Random Forest. In addition, the SMOTE technique is used to handle data imbalance in the model training process. The analysis results showed that negative sentiments dominated at 46%, with the main issue highlighted being the high budget allocation and its impact on education. In terms of performance, the SVM algorithm with SMOTE produced the highest accuracy of 85.74%, outperforming the Random Forest algorithm which only achieved 81.53% accuracy.
FERMENTASI JERAMI JAGUNG MENGGUNAKAN KAPANG TRICHODERMA HARZIANUM DITINJAU DARI KARAKTERISTIK DEGRADASI Suryadi, Suryadi; Darlis, Darlis; Syarif, Suhessy; Afdal, M.
Jurnal Karya Abdi Masyarakat Vol. 1 No. 1 (2017): Jurnal Karya Abdi Masyarakat
Publisher : LPPM Universitas Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (103.982 KB) | DOI: 10.22437/jkam.v1i1.3727

Abstract

Penelitian ini bertujuan untuk mengetahui lama waktu fermentasi dan karakteristik degradasi komponen serat jerami jagung fermentasi secara In sacco. Fermentasi jerami jagung secara padat menggunakan Trichoderma harzianum sebagai stater. Sebanyak 2,5 gram urea, 2,5 gram molases, 2,5 ml sediaan Trichoderma harzianum dicampur dengan air menjadi 20 ml yang kemudian disemprotkan pada 1000 gram jerami jagung segar. Selanjutnya jerami jagung dimasukkan ke dalam toples plastik dan diperam sesuai dengan perlakuan yaitu 4, 8, 12 dan 16 hari. Uji karakteristik degradasi jerami jagung fermentasi dilakukan dengan metode In sacco atau nylon bag technique. Sebanyak 6 gram sampel jerami dimasukkan ke dalam kantong nylon dengan ukuran 140, 80 mm diinkubasi ke dalam rumen sapi dengan interval waktu 6, 12, 24, 48 dan 72. Penelitian ini menggunakan rancangan acak lengkap (RAL) dengan perlakuan 4 lama fermentasi dan ulangan 3 untuk tiap perlakuan. Peubah yang diukur adalah karakteristik degradasi meliputi : Nilai fraksi a, nilai fraksi b dan nilai fraksi c dari NDF, ADF dan Hemiselulosa Jerami jagung fermentasi. Hasil penelitian ini menunjukkan bahwa lama fermentasi berpengaruh nyata terhadap nilai fraksi (a) dan nilai fraksi (b) dari NDF, nilai fraksi (c) dari ADF dan Hemiselulosa, tetapi tidak berpengaruh nyata pada fraksi (a) dan fraksi (b) dari ADF, fraksi (a) dan fraksi (b) dari hemiselulosa, fraksi (c) dari NDF jerami jagung fermentasi. Kesimpulan: Fermentasi jerami jagung dengan Trichoderma harzianum dapat meningkatkan nilai fraksi (a) dari NDF, ADF dan laju degradasi NDF ADF dan Hemiselulosa. Lama fermentasi yang terbaik pada jerami jagung fermentasi diperoleh pada perlakuan 16 hari.
Pengenalan Pakan Blok Berbasiskan Dekanter Sawit Sebagai Pakan Ternak Ruminansia Di Desa Kota Baru, Kecamatan Geragai Kabupaten Tanjung Jabung Timur Afdal, M.; Kaswari, Teja; Fakhri, Saitul; Suryani, Heni
Jurnal Karya Abdi Masyarakat Vol. 4 No. 3 (2020): Jurnal Karya Abdi Masyarakat
Publisher : LPPM Universitas Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (376.663 KB) | DOI: 10.22437/jkam.v4i3.11304

Abstract

Tujuan dari kegiatan pengabdian kepada masyarakat ini adalah pemanfaatan dan pengenalan Dekanter Sawit (DS) kepada masyarakat peternak di desa Kotabaru. Pelaksanaan kegiatan ini adalah dengan memperkenalkan DS kepada anggota Kelompok Tani. Metoda yang dipergunakan adalah dengan survey pendahuluan terhadap potensi dan pemanfaatan DS di desa Kotabaru. Berdasarkan hasil survey pendahulaun ini maka diadakan sosialisai penggunaan DS sebagai pakan alternatif bagi ternak dengan program penyuluhan dan dilanjutkan dengan demonstrasi. Pada tahap awal ini diperkenalkan tata cara pembuatan pakan blok berbasiskan DS sebagai pakan alternatif untuk ternak ruminansia. Kesompulan dari program ini kelompok tani Suka Maju dapat menerima inovasi ini dengan memanfaatkan DS sebagai pakan alternatif ternak sapi dan sudah diadakan pelatihan pembuatan pakan blok berbasiskan DS
Analysis of User Adaptation to the My Capella Application based on the Coping Model of User Adaptation (CMUA) Mutia, Risma; Megawati, Megawati; Afdal, M.; Permana, Inggih
Sistemasi: Jurnal Sistem Informasi Vol 14, No 4 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i4.5328

Abstract

The My Capella application developed by PT Capella Dinamik Nusantara was designed to facilitate customer access to digital services, particularly for booking Honda motorcycle servicing. However, its use still encounters several challenges, especially regarding user adaptation. These include difficulties in understanding and utilizing features, a complex interface, and insufficient user guidance. This study aims to analyze and identify user adaptation behavior toward the My Capella application in the Pekanbaru area using the Coping Model of User Adaptation (CMUA), which evaluates how users respond to new technologies through cognitive and emotional processes. The research findings support four accepted hypotheses: opportunity appraisal significantly influences problem-focused adaptation; secondary appraisal significantly influences both problem-focused and emotion-focused adaptation; and threat appraisal significantly influences problem-focused adaptation. The strongest effect was observed in the relationship between secondary appraisal and problem-focused adaptation, with a t-statistic of 7.259 > 1.960. These findings indicate that users respond to the My Capella application both cognitively and emotionally, aligning with the CMUA framework and reflecting adaptation processes that are both problem-focused and emotion-focused. Therefore, it is recommended that application developers provide interactive training modules, regular outreach or user engagement sessions, and improvements to the user interface (UI/UX) design to make it more intuitive. These efforts can enhance users' understanding and comfort in using application features—especially during system updates.
IMPLEMENTASI DATA MINING DALAM PENCARIAN DAERAH STRATEGIS UNTUK PENGENALAN SEKOLAH SWASTA DENGAN METODE FP-GROWTH Afdal, M
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 3 No 2 (2018): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2777.239 KB) | DOI: 10.24252/instek.v3i2.6044

Abstract

Sekolah Menengah Kejuruan (SMK) adalah salah satu institusi pendidikan resmi yang disahkan oleh pemerintah. Berdasarkan data pokok Sekolah Menengah Kejuruan untuk dinas pendidikan Kota Pekanbaru tahun 2016 terdapat sebanyak 60 Sekolah yang terdiri dari 7 SMK Negeri dan 53 SMK Swasta. Persaingan di dalam dunia bisnis, khususnya dalam bidang pendidikan pada SMK membuat pihak sekolah harus mencari pola sasaran daerah yang strategis dalam pengenalan sekolah. Dengan semakin banyaknya SMK Swasta di Kota Pekanbaru, membuat setiap sekolah berusaha mencari calon siswa baru kedaerah-daerah yang potensial. Salah satu cara yang dapat dilakukan untuk penentuan daerah strategis adalah dengan memanfaatkan teknik Data Mining. Dari data-data siswa yang ada disekolah dapat diolah mengunakan algoritma FP-Growth sehingga menghasilkan Frequent Itemset  yang menjadi informasi baru untuk  dimanfaatkan oleh sekolah dalam menentukan daerah yang strategis. Dalam penelitian ini yang menggunakan data siswa kelas X dengan  nilai minimum support = 0.04 dan nilai minimum confidence = 0.68 dinyatakan bahwa siswa yang berasal dari kecamatan Payung Sekaki adalah daerah yang paling strategis dalam pengenalan sekolah dengan tingkat kepercayaan 100% dan didukung oleh 4.7% dari data keseluruhan dengan nilai lift ratio 1.472. Kata Kunci: Association Rule, Data Mining, FP-Growth, Frequent Itemset
Analisis Sentimen Layanan J&T Express pada Sosial Media X Menggunakan Algoritma Naïve Bayes Clasifier dan K-Nearest Neighbor Priady, Muhamad Ilham; Afdal, M.; Permana, Inggih; Zarnelly, Zarnelly
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7721

Abstract

The demand for goods delivery services is increasing along with the widespread use of e-commerce platforms for buying and selling. One of the popular and frequently used delivery service providers is J&T Express. Until now, J&T has had a wide service coverage. However, various customers also have complaints that are often conveyed through social media X. For this reason, this study conducted a sentiment analysis of J&T Express user opinions on social media X using the Naïve Bayes Classifier (NBC) and K-Nearest Neighbor (KNN) algorithms. Data collection was carried out through scraping over a time span from January 1, 2023 to December 1, 2024, resulting in a total of 1,000 data points. The modeling results show that the NBC algorithm outperforms KNN, achieving an accuracy of 72.30%, a precision of 74.76%, and a recall of 72.30%. Meanwhile, the KNN algorithm with the best parameters (K = 9) only has an accuracy of 67.29%, precision of 69.46%, and recall of 67.29%. Then the results of the analysis show that J&T user opinions are dominated by negative sentiment (42.20%), followed by positive sentiment (38.70%) and neutral sentiment (19.10%). Further analysis based on five variables was also conducted and an understanding of J&T's weaknesses, namely in the service aspect, with the highest negative sentiment (21.0%). On the other hand, the user experience aspect is an advantage with the most positive sentiment (16.8%). The data visualization results also indicate that there are dominant customer complaints about the delay in the delivery process. However, customers also appreciate the speed and security of the delivery of goods. These findings provide valuable insights for J&T Express to conduct evaluations and improvements, especially in the service aspect, to improve overall customer satisfaction and experience.
EVALUASI USER EXPERIENCE PADA APLIKASI WONDR BY BNI MENGGUNAKAN METODE UEQ DAN SUS Lestari, Indah; Saputra, Eki; Afdal, M; Nur Salisah, Febi; Syaifullah, Syaifullah
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/vksfqm62

Abstract

Wondr by BNI is a mobile banking application in Indonesia designed to support systematic financial management through three main concepts: Insight, Transaction, and Growth. Despite offering advanced features, many users complain about issues such as failed transactions, login difficulties, and slow application response times. This study evaluates the user experience of the Wondr app by combining the UEQ and SUS methods. The UEQ evaluation results show an average score of: attractiveness 1.12; clarity 1.06; efficiency 1.05; accuracy 1.07; stimulation 0.71; and novelty 0.77. Meanwhile, the SUS score of 64.6 falls into category D, “OK” on the adjective scale, and “Marginally Acceptable” on the usability scale—indicating that the app's usability is slightly below the average standard. Overall, users gave positive ratings for clarity, efficiency, accuracy, and stimulation, but attractiveness and novelty still need improvement. To date, no studies have specifically evaluated the UX of the Wondr app by combining the UEQ and SUS methods. This research contributes new scientific insights by demonstrating the app's UX performance and areas requiring improvement.
OPTIMALISASI STRATEGI PROMOSI BERDASARKAN WAKTU DAN JENIS PRODUK MENGGUNAKAN ALGORITMA FP-GROWTH Andaranti, Arifah Fadhila; Afdal, M.; Permana, Inggih; Jazman, Muhammad; Marsal, Arif
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/dy69fk12

Abstract

Aba Mart is a convenience store that provides a wide range of daily necessities. One of the challenges faced by Aba Mart is the uncertainty in determining the optimal timing for product promotions. To address this issue, this study utilizes sales transaction data obtained from the store’s Point of Sale (POS) system, totaling 12,887 transactions recorded from March to August 2024. The dataset includes attributes such as date and product name, which were processed through attribute selection, categorization into 33 product types, conversion of dates to days, and transformation into boolean format for analysis. The study applies the Association Rule Mining (ARM) technique using the Frequent Pattern Growth (FP-Growth) algorithm to identify the relationship between the time of purchase and the types of products bought. The results demonstrate that the FP-Growth algorithm successfully identified patterns of association. By testing with minimum support values of 2%, 3%, and 4%, and a minimum confidence of 10%, the analysis produced 15 association rules in March, 11 in April, 14 in May, 13 in June, 11 in July, and 13 in August 2024. These rules have been used as a foundation for formulating more effective and targeted promotional strategies for Aba Mart.
Co-Authors - Mardalena, - A. Adriani AA Sudharmawan, AA Addion Nizori ADRIANI ADRIANI Adriani Adriani Afandi, Rival Aini, Delvi Nur Al-Yasir, Al-Yasir Alfakhri, Rezky Alfian, Zhevin Andaranti, Arifah Fadhila Andriyani, Dwi Ratna Angraini Angraini Anisa Putri Annisa Ramadhani Anofrizen Anofrizen Arif Marsal Arrazak, Fadlan Auliani, Sephia Nazwa Ayu Lestari Silaban Ayu Silaban Azzahra, Aura Basri, Faishal Khairi Darlis Darlis Darlis Darlis, Darlis Eki Saputra F. Safiesza, Qhairani Frilla Fauzan Ramadhan Febi Nur Salisah Filawati Filawati FITRY TAFZI Hendri, Desvita Heni Suryani Husaini, Fahri Husna, Nur Alfa Indah Lestari, Indah Indriyani Indriyani Indriyani Inggih Permana Intan, Sofia Fulvi Irwanda, Mahyuda Jazman, Muhammad Kusuma, Gathot Hanyokro Lisani Lisna, Lisna Loka, Septi Kenia Pita Luber, Yusuf Amirullah Mawaddah, Zuriatul Megawati - Miftahul Jannah Mochammad Imron Awalludin Mona Fronita, Mona Muhammad Ambar Islahuddin Munandar, Darwin Munzir, Medyantiwi Rahmawita Mustakim Mustakim Mustakim Mutia, Risma Muttakin, Fitriani Nabillah, Putri Nasution, Nur Shabrina Nelwida Nelwida Nurfadilla, Nadia Nurkholis Nurkholis Pertiwi, Tata Ayunita Priady, Muhamad Ilham Prizky Nanda Mawaddah Putra, Moh Azlan Shah Putri, Celine Mutiara Putri, Suci Maharani Rahmah, Astriana Rahmawita, Medyantiwi Ramadani, Faradila Ramadhani, Indah Rayean, Rival Valentino Remon Lapisa Rice Novita Rozanda, Nesdi Evrilyan Saad, Wan Zuhainis Sabillah, Dian Ayu Saitul Fakhri Sari, Gusmelia Puspita Sarwo Edy Wibowo Siti Monalisa Siti Rohimah Suhessy Syarif Suhessy Syarif, Suhessy Suryadi Suryadi Suryadi Suryadi Suryani, Heni Susanti, Pingki Muliya Suseno, Rahayu Syafi'i, Azis Syafrizal Syafrizal Syahri, Alfi Syaifullah Syaifullah T. T. Poy Teja Kaswari Tri Astuti Triningsih, Elsa Tshamaroh, Muthia Ula, Walid Alma Wibisono, Yudistira Arya Wilrose, Anandeanivha Winnugroho Wiratman, Manfaluthy Hakim, Tiara Aninditha, Aru W. Sudoyo, Joedo Prihartono Y Zaharanova Yuda, Afi Ghufran Yulianti, Nelvi Yun Alwi Yurleni Yurleni Yusuf Amirullah Luber Zarnelly Zarnelly Zarqani, Zarqani