M. Afdal
Universitas Islam Negeri Sultan Syarif Kasim Riau

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

Determining the Final Project Topic Based on the Courses Taken by Using Machine Learning Techniques Vicky Salsadilla; Inggih Permana; Muhammad Jazman; M. Afdal
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 3 No. 2 (2023): MALCOM October 2023
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v3i2.904

Abstract

A thesis (TA) is a scientific paper based on a problem. TA must be completed by students who wish to complete their studies. During this time, students often experience difficulties in determining the TA topic they want to research. To fix it, this research tries to determine TA topics using Machine Learning (ML) techniques based on the elective courses that students have taken. Elective courses are one form of academic data that can be used to consider TA topics. The ML algorithms used are KNN, NBC, ANN, SVM, C4.5, Random Forest, and Logistic Regression. The dataset used in this research is imbalanced data. This research balances the data using the Random Oversampling method and the Random Undersampling method. The results of experiments show that datasets balanced using ROS produce much higher ML performance, but tend to over-fit due to data duplication in the dataset. If the dataset is not balanced at all then the ML performance will be very low. Therefore, for unbalanced data, it is recommended to use the RUS method as data balance. The highest accuracy results for algorithms balanced using ROS are ANN=69.7%, RF=66.7%, SVM=57.6%, LR=57.6%, NBC=42.4%, C4.5=42.4%, and KNN=33.3%
Analisis Sentimen Ulasan Aplikasi PLN Mobile Menggunakan Algoritma Naïve Bayes Classifier dan K-Nearest Neighbor: Sentiment Analysis of PLN Mobile Application Review Using Naïve Bayes Classifier and K-Nearest Neighbor Algorithm Syafrizal Syafrizal; M. Afdal; Rice Novita
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 1 (2024): MALCOM January 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i1.983

Abstract

Bukti nyata PLN terus meningkatkan pelayanannya adalah dengan meluncurkan sebuah aplikasi yaitu PLN Mobile. Banyak pelanggan yang merasakan kemudahan dengan adanya aplikasi tersebut. Namun kini beberapa pelanggan mulai menjumpai permasalahan seperti gagal memuat lokasi saat melakukan pengaduan dan saat pembelian token dengan virtual account, saldo telah terpotong namun kode token tidak muncul. Penelitian ini melakukan analisis sentimen terhadap ulasan pengguna aplikasi PLN Mobile menggunakan pendekatan text mining. Pendekatan ini dapat melakukan klasifikasi sentimen pada ulasan pengguna dengan cepat. Data dikumpulkan menggunakan teknik scrapping pada Google Play Store dan mendapatkan 3000 baris data. Data tersebut kemudian diberi label oleh seorang pakar sehingga menghasilkan 2099 sentimen positif (69,97%), 368 netral (12,27%) dan 533 negatif (17,77%). Selanjutnya dilakukan pemodelan menggunakan algoritma NBC dan KNN dengan K-Fold Cross Validation sebagai teknik validasi. Hasilnya menunjukkan model NBC lebih baik dibandingkan KNN dengan akurasi sebesar 77,69%, recall 53,14%, precision 59,84% dan F1-Score 54,09%. Selanjutnya proses analisis dilakukan dengan visualisasi data menggunakan word cloud. Hasilnya yaitu dengan adanya aplikasi PLN Mobile memberikan kemudahan kepada pelanggan dalam menggunakan layanan PLN seperti pembelian token, pengaduan, dan berbagai fitur lainnya. Namun aplikasi PLN Mobile masih memiliki beberapa permasalahan yang sering menjadi ulasan penggunanya salah satunya adalah saat melakukan pembayaran token.
Analisis Loyalitas Pelanggan Business To Business Berdasarkan Model RFM Menggunakan Algoritma Fuzzy C-Means: Business to Business Customer Loyalty Analysis Based on RFM Model Using Fuzzy C-Means Algorithm Al-Yasir Al-Yasir; M. Afdal; Zarnelly Zarnelly; Arif Marsal
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 1 (2024): MALCOM January 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i1.1163

Abstract

PT. XYZ merupakan perusahaan yang bergerak di bidang distributor atap plastik dan Aluminium Composit Panel (ACP) yang mengadopsi model usaha B2B. Saat ini strategi yang digunakan oleh PT. XYZ masih belum berfokus pada segmentasi pelanggan dan masih memperlakukan setiap pelanggan dengan sama. Selain itu data penjualan yang terdapat ribuan lebih riwayat transaksi hanya digunakan sebagai arsip yang seharusnya dapat digunakan untuk pengembangan strategi perusahaan. Berdasarkan hal tersebut, penelitian ini melakukan segmentasi pelanggan pada PT. XYZ menggunakan model RFM dan algoritma FCM untuk menganalisis pelanggan bersasarkan karakteristik dan perilakunya. Data yang digunakan terdiri dari 9163 transaksi yang memuat 494 pelanggan. Untuk mendapatkan jumlah cluster yang optimal maka dilakukan pengujian pada jumlah cluster yaitu 2-10. Hasilnya menunjukkan 2 cluster sebagai jumlah yang terbaik dengan nilai DBI 0,4908. Cluster 1 yang terdiri dari 387 pelanggan dikategorikan sebagai loyal customer sedangkan cluster 2 yang terdiri dari 107 pelanggan dikategorikan sebagai lost customer. Sebagai pelanggan yang loyal, perusahaan perlu memberikan apresiasi untuk mempertahankan hubungan baik dengan pelanggan seperti memberikan diskon, ataupun penawaran khusus. Kemudian untuk segmen lost customer, perusahaan perlu mengambil langkah yang tepat untuk mencoba memulihkan hubungan dengan pelanggan dan menganalisis faktor dan penyebab pelanggan pada segmen ini beralih ke perusahaan lain.
Penerapan Algoritma Long Short-Term Memory untuk Prediksi Produksi Kelapa Sawit: Application of Long Short-Term Memory Algorithm for Palm Oil Production Prediction Fahri Husaini; Inggih Permana; M. Afdal; Febi Nur Salisah
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 2 (2024): MALCOM April 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i2.1187

Abstract

Kelapa sawit memberikan kontribusi yang besar bagi perkembangan perekonomian Indonesia. Salah satunya ekspor non migas negara dan yang terus mengalami pertumbuhan yang dilakukan perusahaan kelapa sawit. PT XYZ merupakan salah satu perusahaan kelapa sawit yang mengolah kelapa sawit menjadi minyak kelapa sawit. Dalam menghadapi permintaan minyak kelapa sawit dunia yang terus meningkat, PT. XYZ berkomitmen untuk meningkatkan produksinya. Untuk meningkatkan produksi, PT XYZ telah menetapkan target produksi dengan melakukan prediksi produksi kelapa sawit menggunakan metode Global Telling. Namun, metode ini kurang efektif karena tidak dilakukan secara berkala. Untuk itu, diperlukan suatu metode yang dapat mempelajari pola panen setiap bulannya untuk membuat target produksi. Penelitian ini menerapkan Algoritma Long Short-Term Memory dengan percobaan beberapa parameter untuk menemukan model terbaik yang dapat memprediksi produksi kelapa sawit secara akurat. Berdasarkan hasil percobaan, model dengan optimizer RMSprop, learning rate 0.001, dan batch size 8 merupakan model dengan parameter terbaik dengan nilai RMSE 0.1725, MAPE 0.5087, dan R2 0.0578. Model tersebut memprediksi bahwa produksi kelapa sawit akan mengalami penurunan
Perbandingan Evaluasi Kernel Support Vector Machine dalam Analisis Sentimen Chatbot AI pada Ulasan Google Play Store Celine Mutiara Putri; M. Afdal; Rice Novita; Mustakim Mustakim
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 7 No. 3 (2024): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/jtsi.v7i3.41354

Abstract

AI (Artificial Intelligence) is becoming very important these days due to its ability as a personal assistant to increase efficiency, automate routine tasks, and speed up manual processes. AI chatbot are one of the practical applications of AI in language understanding, have various benefits and drawbacks that cause various comments from users in the review column on the Google Play Store. This research discusses sentiment analysis of AI chatbot application reviews using four SVM kernels. Labeling uses InSet Lexicon and hyperparameters to produce the best parameters. The purpose of the research is to find out how users respond to interactions with ChatGPT, Perplexity AI, and Bing Chat and prove whether the kernel in SVM can increase the accuracy value. The percentage division between test data and training data is 70:30, 80:20, and 90:10, data labeling using 2 sentiment classes and 3 sentiment classes, and using and not using the SMOTE Oversampling technique. The experimental results obtained the highest accuracy using SVM kernel Linear scenario 90:10 with an accuracy value of 92.68%.
Analisis Sentimen Ulasan Pengguna Aplikasi Penjualan Pulsa Menggunakan Algoritma Naïve Bayes Classifier Azis Syafi'i; M. Afdal; Eki Saputra; Rice Novita
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 7 No. 3 (2024): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/jtsi.v7i3.41364

Abstract

Many credit sales applications are commonly used by outlets or counters, such as DigiPOS, Tetra Pulsa, and Orderkuota. However, there are common problems with these applications such as prices that are starting to be less competitive, difficult to use, transactions that often fail, security, service and others. Therefore, this study analyzes the sentiment of user reviews to identify the strengths and weaknesses of these apps, to help developers improve their services, and to guide agents in choosing the right app. NBC algorithm is proposed to be used for sentiment classification. The analysis results show the dominance of positive sentiments on all apps, with Tetra Pulsa having the highest positive sentiment (97.10%), followed by Orderkuota (84.40%) and DigiPOS (64.00%). Then the results of the implementation of the NBC algorithm can perform sentiment classification well. Tetra Pulsa application has an accuracy of 97.10%, Orderkuota 92.39%, and DigiPOS 91.10%. The results of this study can be considered to evaluate and improve the application so that it can provide better service to users of the credit sales application.
Analisis Sentimen Ulasan Pengguna Aplikasi Mobile Banking Menggunakan Algoritma K-Nearest Neighbor Darwin Munandar; M. Afdal; Zarnelly Zarnelly; Rice Novita
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 7 No. 3 (2024): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/jtsi.v7i3.41409

Abstract

Mobile banking is evident in the improvement of business processes in the banking industry. Even so, the m-banking application cannot be separated from the problems experienced by its users. Therefore, further analysis is required. This research proposes a sentiment analysis technique using K-Nearest Neigbor (KNN) algorithm to identify user opinions and reviews of m-banking applications. Three popular m-banking apps were selected for further analysis namely BRImo, BSI Mobile, and Livin' by Mandiri. The analysis shows that BRImo is the most popular m-banking application, with a positive sentiment percentage of 58.25%, Livin' by Mandiri with 22.50%, and BSI Mobile with the lowest percentage of 12.70%. Modeling results using the KNN algorithm with K = 3, 5 and 7 test values show K = 3 has better capabilities. Based on the application, the best modeling is produced on BRImo with 82.9% accuracy, then Livin' by Mandiri with 70.3% accuracy, and BSI Mobile with 71.35% accuracy. Analysis and visualization were also conducted using word clouds to see keywords that are often discussed in reviews. As a result, m-banking apps have problems with difficult login, complicated registration or verification, and balance deduction despite failed transfer status.
Analysis of User Satisfaction of SAINS Pahlawan Tuanku Tambusai University Using the EUCS Method Raihan Alfarisy; Idria Maita; Tengku Khairil Ahsyar; M. Afdal
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 1 (2025): Maret
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/n7ene473

Abstract

  Abstract - Smart Academic Integrated System (SAINS) is an information system used to improve the quality and facilitate students, lecturers and staff in carrying out lecture activities at Universitas Pahlawan Tuanku Tambusai. Nevertheless, certain challenges persist, as revealed through interviews and observations with the Head of Student Affairs and Active Students. These include insufficient details regarding the KRS filling schedule and lecture information (content), an unappealing SAINS appearance (format), an inaccessible forgotten password menu (case of use), and a lengthy login process (timeliness). In order to gauge how happy SCIENCE users are with the system, this study used the End User Computing Satisfaction (EUCS) approach and polled 97 people. The results showed that three variables had a positive effect, namely accuracy, format and ease of use, and two variables had a negative effect, namely content and timeliness. The variables that have a positive influence have T-statistic values ​​of 2.804, 2.414, and 3.528, while the variables that have a negative influence have T-Statistic values ​​of 0.576, and 0.326. Research recommendations can add information about the KRS filling schedule and lectures on the SAINS system homepage, as well as increase the speed of access to the SAINS system by users.
Sentiment Analysis of Gojek, Grab, Maxim Applications Using Support Vector Machine Algorithm Muhammad Iqrom; M. Afdal; Rice Novita; Medyantiwi Rahmawita; Tengku Khairil Ahsyar
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 1 (2025): Maret
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/52fycr56

Abstract

This research analyzes user sentiment towards three major online transportation applications in Indonesia—Gojek, Grab, and Maxim using the \SVM algorithm. The analysis results indicate that Maxim has the highest positive sentiment rate (42.45%) compared to Grab (32.83%) and Gojek (20.21%). Maxim's advantages lie in its competitive pricing and driver professionalism. However, Gojek recorded the best performance in sentiment classification with an accuracy of 94%, followed by Maxim (90%) and Grab (87%). The evaluation based on five main variables (general sentiment, drivers, services, applications, and pricing/costs) reveals the strengths of each application in different categories. Maxim excels in general sentiment and driver satisfaction, Grab dominates in pricing/cost, and Gojek stands out in the application category. Wordcloud visualization reveals frequently mentioned words such as "driver," "application," and "order," reflecting users' primary concerns and experiences. This research provides valuable insights for online transportation service providers to improve service quality, although it has limitations in exploring external factors such as user demographics and marketing strategies, as well as relying on a single algorithm without comparison. The choice of the SVM algorithm is based on its ability to handle well-structured data and provide high accuracy in classification. SVM is effective in finding the optimal hyperplane that clearly separates data classes, making it suitable for sentiment analysis involving multiple variables.