Search Articles & Publications

Showing 91 articles found for "Achieving"

A COMPARATIVE ANALYSIS OF OPTIMIZED NEURAL NETWORK AND LARGE-SCALE LANGUAGE MODELS FOR MUSIC GENRE CLASSIFICATION

Marzuqi, Ahmad Naufal Luthfan, Nastiti , Vinna Rahmayanti Setyaning
Abstract: Abstract: The rapid growth of the digital music industry requires accurate music genre classification systems to enhance user experience in streaming services. This study compares a domain-specific Long Short-Term Memory… (LSTM) network with three Large Language Models (LLMs)—HuBERT, WavLM, and WAV2Vec 2.0—for Music Genre Classification (MGC). The LSTM model was trained using Mel-spectrograms transformed from the GTZAN dataset, while the LLMs were fine-tuned using a smaller set of raw audio samples due to computational constraints. All models were tested on datasets with identical genre labels to ensure a fair evaluation. Results show that the LSTM model achieved the highest accuracy of 97.10%, outperforming HuBERT (86.00%), WavLM (83.00%), and WAV2Vec 2.0 (80.00%). The LSTM demonstrated superior generalization and stability without overfitting, while the LLMs struggled to differentiate between genres with similar acoustic characteristics. These findings indicate that general-purpose pre-trained models, although powerful, are less effective in music-specific tasks due to domain mismatch. Therefore, incorporating music-specific features and architectures remains essential for achieving higher accuracy and reliability in automatic genre classification systems. Keywords: audio large language models; comparative deep learning; music genre classification.   Abstrak: Pertumbuhan industri musik digital yang pesat menuntut sistem klasifikasi genre musik yang akurat untuk meningkatkan pengalaman pengguna dalam layanan streaming. Penelitian ini dilatarbelakangi oleh perkembangan pesat model pembelajaran mendalam, khususnya jaringan LSTM dan model bahasa berskala besar LLM seperti HuBERT, WavLM, dan WAV2Vec 2.0, yang telah menunjukkan kemampuan representasi audio yang kuat. Tujuan penelitian ini ini membandingkan jaringan Long Short-Term Memory (LSTM) khusus domain dengan tiga model Large Language Models (LLM)—HuBERT, WavLM, dan WAV2Vec 2.0—untuk tugas Klasifikasi Genre Musik (MGC). Metode penelitian melibatkan pelatihan LSTM menggunakan data Mel-spectrogram hasil transformasi dari dataset GTZAN, sementara LLM disesuaikan (fine-tuning) menggunakan data audio mentah dalam jumlah lebih kecil karena keterbatasan komputasi. Seluruh model diuji pada dataset dengan label genre yang sama untuk memastikan evaluasi yang adil. Hasil penelitian menunjukkan bahwa model LSTM mencapai akurasi tertinggi sebesar 97,10%, sedangkan model HuBERT, WavLM, dan WAV2Vec 2.0 masing-masing memperoleh 86,00%, 83,00%, dan 80,00%. Model LSTM menunjukkan kemampuan generalisasi yang lebih baik tanpa overfitting, sedangkan model LLM cenderung kesulitan membedakan genre dengan karakteristik akustik yang mirip. Kesimpulan penelitian ini adalah ketidaksesuaian domain secara signifikan membatasi performa model umum saat diterapkan pada tugas berbasis musik. Oleh karena itu, penggunaan fitur dan arsitektur khusus musik sangat penting dalam membangun sistem klasifikasi genre yang lebih akurat. Kata kunci: klasifikasi genre musik; model bahasa besar; perbandingan pembelajaran mendalam.

COMPARISON OF DECISION TREE AND RANDOM FOREST ALGORITHMS FOR ASTHMA

Lase, Wisriani, Robet, Robet, Hendri, Hendri
Abstract: Abstract: Asthma is a chronic respiratory disease that affects millions of people worldwide, making early detection crucial to prevent complications. This study aims to compare the performance of the Decision Tree and Random… ndom Forest algorithms in classifying asthma based on clinical symptom data. The data were processed through feature selection and model training stages, then evaluated using accuracy, precision, recall, and F1-score.The experimental analysis revealed that the Random Forest algorithm surpassed the Decision Tree in all metrics, achieving 95.19% accuracy, 90.43% precision, 95.00% recall, and 93.00% F1-score. In contrast, the Decision Tree obtained 89.14% accuracy, 90.60% precision, 88.70% recall, and 89.70% F1-score. These results suggest that Random Forest is more robust and dependable, especially in managing complex and imbalanced medical datasets.   Keywords: asthma detection; decision tree; random forest; machine learning.     Abstrak: Asma merupakan penyakit pernapasan kronis yang memengaruhi jutaan orang di seluruh dunia sehingga deteksi dini sangat penting untuk mencegah komplikasi. Penelitian ini bertujuan membandingkan kinerja algoritma Decision Tree dan Random Forest dalam mengklasifikasikan asma berdasarkan data gejala klinis. Data diproses melalui tahapan seleksi fitur dan pelatihan model, kemudian dievaluasi menggunakan akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa Random Forest memberikan performa terbaik dengan akurasi 90.43%, presisi 95.00%, recall 95.00%, dan F1-score 93.00%. Sebaliknya, Decision Tree memperoleh akurasi 89.14%, presisi 90.60%, recall 88.70%, dan F1-score 89.70%. Hasil ini menunjukkan bahwa Random Forest lebih kuat dan dapat diandalkan, terutama dalam mengelola kumpulan data medis yang kompleks dan tidak seimbang.   Kata kunci: deteksi asma; decision tree; random forest; pembelajaran mesin.

COMPARISON OF NAÏVE BAYES, SVM, K-NN, DECISION TREE, AND RANDOM FOREST IN SENTIMENT ANALYSIS BASED ON SEABANK APPLICATION ASPECTS

Fachrozi, Muhammad Al, Tania, Ken Ditha
Abstract: Abstract: The increasing use of digital banking applications has led to the need for a deeper understanding of user perceptions, especially through aspect-based sentiment analysis. This study aims to classify the sentiment… nt of SeaBank app users by focusing on four main aspects: learnability, efficiency, technical issues or errors, and satisfaction. Review data totaling 1,971 comments were collected from the Google Play Store and labeled with sentiments based on the scores (ratings) given by users. The CRISP-DM approach serves as the methodological framework for this study, which includes five classification algorithms: Naïve Bayes, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Decision Tree, and Random Forest. The evaluation results show that the SVM algorithm provides the best performance with the highest average value of the four aspects achieving accuracy of 93.91%, Precision of 91.16%, recall of 97.96% and F1-Measure of 94.33%. According to the research findings, the Support Vector Machine (SVM) algorithm provides the best performance when performing aspect-based sentiment analysis on text data from digital banking application reviews. The findings are expected to serve as a reference for the development of automated evaluation systems that rely on user opinions as the basis for decision making.             Keywords: aspects; CRISP-DM; digital Banking; seabank; sentiment analysis     Abstrak: Peningkatan pemakaian aplikasi perbankan digital mendorong perlunya pemahaman yang lebih dalam mengenai persepsi pengguna, terutama melalui analisis sentimen berbasis aspek. Penelitian ini bertujuan untuk mengklasifikasikan sentimen pengguna aplikasi SeaBank dengan berfokus pada empat aspek utama: kemudahan dipelajari (learnability), efisiensi penggunaan (efficiency), kendala atau kesalahan teknis (error), serta tingkat kepuasan (satisfaction). Data ulasan berjumlah 1.971 komentar dikumpulkan dari Google Play Store dan diberi label sentimen berdasarkan skor (rating) yang diberikan oleh pengguna. Pendekatan CRISP-DM berfungsi sebagai kerangka metodologis untuk penelitian ini, yang mencakup lima algoritma klasifikasi: Naïve Bayes, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Decision Tree, dan Random Forest. Hasil evaluasi menunjukkan bahwa algoritma SVM memberikan performa terbaik dengan nilai rata-rata dari ke empat aspek tertinggi yang mencapai accuracy sebesar 93.91%, Precision sebesar 91.16%, recall sebesar 97.96% dan F1-Measure sebesar 94.33%. Menurut temuan penelitian, algoritma Support Vector Machine (SVM) memberikan kinerja terbaik saat melakukan analisis sentimen berbasis aspek pada data teks dari ulasan aplikasi Seabank. Temuan ini diharapkan dapat menjadi referensi bagi pengembangan sistem evaluasi otomatis yang mengandalkan opini pengguna sebagai dasar pengambilan keputusan.   Kata kunci: Analisis Sentimen, Aspek, Bank Digital, SeaBank, CRISP-DM

IMPLEMENTATION OF RANDOM FOREST CLASSIFIER FOR STUDENT GRADUATION CLASSIFICATION

Zaidan Putra, Bazil, Nur Fajri, Ika, Nugroho, Agung
Abstract: Abstract: Higher education plays an essential role in improving human resource quality, one of which is through the institution’s ability to monitor and predict student graduation outcomes. This study does not focus on a… a specific university but utilizes the publicly available Students Performance in Exams dataset from Kaggle, consisting of 1,000 student records containing mathematics, reading, and writing scores, along with demographic attributes such as gender, parental education level, lunch type, and test preparation participation. The data were processed through a feature engineering stage by adding an average score variable as an early indicator of graduation status. A predictive model was developed using the Random Forest Classifier, achieving an accuracy of 94.5%. The final model was integrated into a Streamlit-based web application to provide an accessible tool for academic stakeholders. The results indicate that the proposed model can serve as an effective decision-support tool for early evaluation of students’ likelihood of graduation. Keywords: prediction; random forest classifier, streamlit, student graduation.     Abstrak: Pendidikan tinggi memegang peran penting dalam peningkatan kualitas sumber daya manusia, salah satunya melalui kemampuan institusi dalam memantau dan memprediksi tingkat kelulusan mahasiswa. Penelitian ini tidak berfokus pada perguruan tinggi tertentu, melainkan menggunakan dataset publik Students Performance in Exams dari Kaggle yang berisi 1.000 data mahasiswa, terdiri atas nilai matematika, membaca, menulis, serta atribut demografis seperti gender, tingkat pendidikan orang tua, jenis makan siang, dan partisipasi kursus persiapan. Data diolah melalui tahap feature engineering dengan menambahkan variabel average score sebagai indikator awal kelulusan. Model prediksi dibangun menggunakan algoritma Random Forest Classifier, yang menghasilkan tingkat akurasi sebesar 94,5%. Model ini kemudian diimplementasikan ke dalam aplikasi web berbasis Streamlit untuk memberikan layanan prediksi yang mudah diakses oleh pihak akademik. Hasil penelitian menunjukkan bahwa model mampu digunakan sebagai alat pendukung keputusan untuk melakukan evaluasi dini terhadap potensi kelulusan mahasiswa.   Kata kunci: kelulusan mahasiswa; prediksi; random forest classifier; streamlit.

VEGECHAIN: SMART CONTRACT MARKETPLACE FOR VEGETARIAN SUPPLY CHAIN OPTIMIZATION

Febrianti, Eka Lia, Suryadi , Agus, Syafrinal , Ilwan, Andhika, Andhika
Abstract: Abstract: The global transition towards sustainable food systems faces significant challenges in vegetarian food supply chains, including transparency issues, distribution inefficiencies, and quality verification problems.&#8230; s. This research proposes VegeChain development, a decentralized marketplace ecosystem based on smart contracts designed to transform vegetarian food supply chains and accelerate Meatless, Balanced, Green (MBG) program adoption. Using mixed-method methodology integrating blockchain system design, stakeholder analysis, and economic simulation, this research develops a comprehensive technology framework combining blockchain transparency, smart contract automation, and sustainable tokenomics with novel mathematical models. The system implements dynamic pricing algorithms based on Automated Market Maker (AMM) mechanisms, multi-objective optimization for supply chain efficiency, and reputation-based consensus protocols. Simulation results demonstrate that VegeChain implementation can improve supply chain efficiency by 35%, reduce food waste by 28%, and increase consumer trust by 42% measured through validated stakeholder satisfaction surveys (n=456) using 5-point Likert scales with statistical significance p<0.001. Technical innovations include Byzantine Fault Tolerant consensus with 99.9% reliability, gas optimization achieving 67% cost reduction, and real-time quality verification algorithms with 98.7% accuracy.             Keywords: smart contracts; supply chain optimization; automated market makers; blockchain technology; sustainable tokenomics

IMPLEMENTATION OF THE FUZZY LOGIC METHOD TO DETERMINE EMPLOYEE ASSESSMENT

Siregar, Agus Trinanda, Andrianto, Richi, Rahayu Putri, Perra Budiarti
Abstract: Abstract: Performance assessment is the process of measuring an organization in achieving predetermined goals. Performance assessment can also be interpreted as periodically determining the operational effectiveness of an&#8230; n organization and its personnel, based on the vision, mission and organizational standards that have been previously established. Performance appraisals are carried out between superiors and subordinates, looking at the employee's work results in the last year. Employee performance assessment at the North Padang Lawas Regency PUPR Service still uses a manual system so that the files are not arranged quickly and employee performance assessment still uses calculations with Microsoft Excel. With this problem, the fuzzy logic method is used. The fuzzy method is used to obtain the best employee performance assessment, with 3 criteria to produce the greatest value selected. This research aims to design an employee performance assessment application using the fuzzy method, to obtain recommendations for promotion. The test results of 8 people had sufficient value and 2 people had low value. For low-ranking employees, they will be given sanctions and reprimands by their superiors, while for employees with sufficient value, their performance must be improved to be even better.   Keywords: fuzzy logic; performance; assessment; employee;     Abstrak: Penilaian kinerja merupakan proses pengukuran organisasi dalam mencapai tujuan yang telah ditetapkan. Penilaian kinerja dapat juga diartikan sebagai penentuan secara periodik efektivitas operasional suatu organisasi, dan personilnya, berdasarkan visi, misi dan standar organisasi yang telah ditetapkan sebelumnya. Penilaian kinerja dilakukan antara atasan dengan bawahan, melihat hasil kerja pegawai dalam setahun terakhir. Penilaian kinerja pegawai pada Dinas PUPR Kabupaten Padang Lawas Utara masih menggunakan sistem manual sehingga berkas-berkas file tidak tersusun secara rapid dan penilaian kinerja pegawai masih menggunakanperhitungan dengan microsoft excel.Dengan permasalahah tersebut menggunakan metode fuzzy logic. Metode fuzzy digunakan dalam mendapatkan penilaian kinerja pegawai terbaik, dengan 3 kriteria untuk menghasilkan nilai terbesar yang terpilih. Penelitian ini bertujuan untuk merancang aplikasi penilaian kinerja karyawan dengan metode fuzzy, untuk mendapatkan rekomendasi kenaikan jabatan. Hasil tes dari 8 orang memiliki nilai cukup dan 2 orang memiliki nilai rendah. Bagi pegawai yang memiliki nilai rendah akan diberikan sanksi dan teguran oleh atasannya, sedangkan bagi pegawai yang memiliki nilai cukup, kinerjanya harus ditingkatkan agar lebih baik lagi.   Kata kunci: fuzzy logic; penilaian; kinerja; pegawai

IMPLEMENTATION OF THE PREFERENCE SELECTION INDEX (PSI) METHOD IN COURIER PARTNER RECRUITMENT

Wardana, Aji, Putri, Raissa Amanda
Abstract: Abstract: One of the keys to the success of a company or agency in achieving certain goals is the workforce. However, finding the ideal partner that suits the needs of the organization or agency is difficult. Therefore,&#8230; the selection of suitable potential partners is very important in order to be able to recruit partners who are competent in their fields and meet the company's expectations and meet all stages carried out by the organization. The Preference Selection Index method is the method used in selecting employees. The option that returns the highest Preference Index value after all criteria and alternatives have been calculated is the best option, or options selected. Based on research findings, Andreyanto Wijaya's alternative is the best alternative to be chosen as the company's partner with the highest score, which is 0.95346. Keywords: decision support system; PSI; recruitment; partner   Abstrak: Salah satu kunci keberhasilan suatu perusahaan atau instansi dalam mencapai tujuan tertentu adalah tenaga kerjanya. Namun, menemukan Mitra ideal yang sesuai dengan kebutuhan organisasi atau instansi memang sulit. Oleh karena itu, pemilihan calon Mitra yang sesuai sangatlah penting agar dapat merekrut mitra yang berkompeten di bidangnya dan memenuhi harapan perusahaan serta memenuhi seluruh tahapan yang dilakukan oleh organisasi. Metode Preference Selection Index adalah metode yang digunakan dalam menseleksi pegawai. Pilihan yang menghasilkan nilai Indeks Preferensi tertinggi setelah semua kriteria dan alternatif dihitung adalah pilihan terbaik, atau pilihan yang terpilih. Berdasarkan temuan penelitian, alternatif Andreyanto Wijaya merupakan alternatif terbaik untuk dipilih menjadi mitra untuk perusahaan dengan skor tertinggi yaitu 0,95346.   Kata Kunci : sistem pendukung keputusan; PSI; rekrutmen; mitra

ENTERPRISE ARCHITECTURE: STRATEGY OF SMART VILLAGE DEVELOPMENT (VILLAGE SERVICES) USING TOGAF 9.2

Yusriyahti, Raden Roro Hanin Ramadhan, Nur Fajrillah, Asti Amalia, Nurtrisha, Widyatasya Agustika
Abstract: Abstract: The design of Smart Village Enterprise Architecture for village government systems serves to support sustainability in facilitating the creation of Good Governance in a Village Government. One significant role&#8230; in achieving Good Governance in a village is Education. Education plays a crucial role in enhancing and developing Good Governance and the SDGs values of a village. The conducted research focuses on the design of Enterprise Architecture of the Smart Village concept, with a focus on Village Services' dimension that specifically targets Education Services in a village in the Special Region of Yogyakarta. The research method utilized the TOGAF ADM 9.2 framework. The focus domain in this study includes the preliminary phase, architecture vision, business architecture, data architecture, application architecture, technology architecture, opportunities and solutions, and migration planning for the Education service in the Pagerharjo Village Government. The research result is an Enterprise Architecture blueprint as a solution to the issues that occur in the Education service in the Pagerharjo Village Government, along with an IT Roadmap as a reference for the village government in project development. It is hoped that the recommendations provided can enhance the Education services offered by the Pagerharjo village, thereby aiding the Pagerharjo Village Government in improving its score for the fourth SDGs, Quality Education.             Keywords: Enterprise Architecture, Smart Village, SDGs, TOGAF ADM 9.2.   Abstrak: Perancangan Enterprise Architecture Smart Village pada sistem pemerintahan Desa befungsi mendukung sustainability dalam membantu terciptanya Good Governance di suatu Pemerintahan Desa. Salah satu peranan penting terciptanya Good Governance di suatu Desa adalah Pendidikan. Pendidikan memiliki peran penting dalam peningkatan maupun pembangunan Good Governance dan nilai SDGs Desa. Penelitian yang dilakukan berfokus pada perancangan Enterprise Architecture konsep Smart Village dimensi Village Services yang berfokus pada Education Services di Desa Daerah Istimewa Yogyakarta. Metode penelitian dilakukan dengan menggunakan framework TOGAF ADM 9.2. Fokus domain yang diambil dalam penelitian ini mencakup fase preliminary phase, architecture vision, arsitektur bisnis, arsitektur data, arsitektur aplikasi, arsitektur teknologi, opportunities and solutions, dan migration planning pada layanan Pendidikan di Pemerintahan Desa Pagerharjo. Hasil dari penelitian yang dilakukan berupa blueprint Enterprise Architecture sebagai solusi dari permasalahan yang terjadi pada layanan Pendidikan di Pemerintahan Desa Pagerharjo serta IT Roadmap sebagai acuan Pemerintah Desa dalam melakukan pengembangan proyek. Diharapkan, rekomendasi yang diberikan dapat meningkatkan layanan Pendidikan yang disediakan oleh Desa Pagerharjo, sehingga mampu membantu Pemerintah Desa Pagerharjo meningkatkan score nilai SDGs ke-empat, Pendidikan yang Berkualitas.   Kata kunci: Enterprise Architecture, Smart Village, SDGs, TOGAF ADM 9.2

UTILIZATION OF AGILE METHODS TO DEVELOP EMPLOYEE INTERPERSONAL SKILLS: A SYSTEMATIC LITERATURE REVIEW

Fitroh, Fitroh, Hudaya, Fahmi, Hanif, Muhamad
Abstract: Abstract: Interpersonal skills in employees are an important part of technology companies in achieving their goals through the development of skills in their employees.  The application of agile methods for application development&#8230; development has been widely carried out by technology companies.  The agile method has the main principle of communication between employees, requiring skills to face these principles.  The method used in this study is the systematic literature review (SLR) method to know how the use of agile methods can develop interpersonal skills in karyawan.  In the initial search conducted using the Publish or Perish application, 740 journals were found in the range of 2015 to 2022. Next, journal filtering and cluster search continued using Microsoft Excel, Zotero, Mendeley, and VOS Viewer applications, resulting in 53 journals selected based on Q1. In the final stage of screening, researchers re-screened 9 journals that were used as a reference regarding the use of agile methods to develop employee interpersonal skills.  The results showed that the agile development method can affect the development of employee interpersonal skills. 11 skills develop because of the use of this agile development method including team working, emotional intelligence, negotiation and persuasion, problem-solving, communication skills, conflict resolution, decision making, time management, organizational skills, listening, and relationship building. Of the 11 skills, the most mentioned is team working.             Keywords: agile development methods; interpersonal skills; literature review   Abstrak: Interpersonal skill pada karyawan menjadi bagian penting bagi perusahaan teknologi dalam mencapai tujuannya melalui berbagai pengembangan keterampilan. Penerapan metode agile untuk pengembangan aplikasi sudah banyak dilakukan oleh perusahaan-perusahaan teknologi. Metode agile memiliki prinsip utama berupa komunikasi antar karyawan sehingga membutuhkan keterampilan untuk menghadapi prinsip-prinsip tersebut. Metode yang digunakan pada penelitian ini yaitu metode systematic literature review (SLR) dengan tujuan untuk mengetahui bagaimana pemanfaatan metode agile dapat mengembangkan interpersonal skill pada karyawan. Pada pencarian awal yang dilakukan menggunakan aplikasi Publish or Perish, ditemukan 740 jurnal pada rentang tahun 2015 sampai 2022. Selanjutnya, penyaringan jurnal menggunakan aplikasi Microsoft Excel dan Mendeley Desktop yang menghasilkan 53 jurnal yang dipilih berdasarkan penilaian kualitas. Pada tahap akhir penyaringan, peneliti menyaring kembali menjadi 9 jurnal yang digunakan sebagai acuan mengenai pemanfaatan metode agile untuk mengembangkan interpersonal skills karyawan. Hasil penelitian menunjukan bahwa metode agile development dapat mempengaruhi pengembangan interpersonal skill karyawan, faktanya terdapat 11 skill yang berkembang karena pemanfaatan metode agile development ini diantaranya adalah team working, emotional intelligence, negotiation and persuasion, problem solving, communication skills, conflict resolution, decision making, time management, organizational skill, listening, dan relationship building. Dari 11 skill tersebut yang paling banyak disebut yaitu team working.   Kata kunci: interpersonal skills; metode agile development; literature review;  

STUDENTS GRADUATION PREDICTION BASED ON ACADEMIC DATA RECORD USING THE DECISION TREE ALGORITHM C4.5 METHOD

Prahastiwi, Narita Ayu, Andreswari, Rachmadita, Fauzi, Rokhman
Abstract: Abstract: An application can assist organizations in achieving the goals to be achieved by facilitating ongoing work processes. This happened in the Information Systems Study Program at one of the best private universities,&#8230; es, namely Telkom University, where the SI Study Program has a website called PIPE and has one feature to be able to predict student graduation. However, this feature is currently being developed with an easy flow, so it requires development in the implementation of graduation achievements. Researchers solve these problems by building an assessment model based on academic data on the effect of choosing a specialization. Data mining is needed in this study to form predictive patterns, then one of the data mining groups is based on classification and using machine learning to perform automated assessments so that they can be sustainably performed. In determining the time and delay, using the decision tree method based on the C4.5 algorithm. The accuracy results obtained using the C4.5 algorithm are 94.11%, then the factor that becomes the root node is Jumlah SKS Lulus and the results have an influence on the selection of specialization. So that the results of this graduation model can be applied to the PIPE application.   Keyword: C4.5 algorithm; classification; decision tree; graduation prediction   Abstrak: Sebuah aplikasi dapat membantu organisasi dalam mencapai tujuan yang ingin dicapai dengan memudahkan proses kerja yang sedang berlangsung. Seperti yang terjadi pada Prodi Sistem Informasi yang ada pada salah satu Perguruan Tinggi Swasta terbaik yaitu Universitas Telkom, dimana pada Prodi SI memiliki website bernama PIPE dan memiliki salah satu fitur untuk dapat melakukan prediksi kelulusan mahasiswa. Namun fitur tersebut saat ini dikembangkan dengan alur penentuan sederhana, sehingga memerlukan pengembangan dalam hal implementasi algoritma prediksi kelulusan. Peneliti melakukan penyelesaian masalah tersebut dengan membangun model prediksi kelulusan berdasarkan rekam data akademik terhadap pengaruh pemilihan peminatan. Data mining dibutuhkan dalam penelitian ini untuk membentuk pola penyelesaian prediksi, kemudian salah satu pengelompokan data mining berdasarkan tugasnya adalah klasifikasi dan menggunakan machine learning untuk melakukan prediksi kelulusan secara otomatis terhadap data baru agar dapat dilakukan secara berkelanjutan. Dalam melakukan klasifikasi prediksi kelulusan tepat waktu dan terlambat, menggunakan metode decision tree berdasarkan algoritma C4.5. Hasil akurasi yang didapat dengan menggunakan algoritma C4.5 adalah sebesar 94,11%, kemudian faktor yang menjadi root node adalah Jumlah SKS Lulus dan hasil memiliki pengaruh terhadap pemilihan peminatan. Sehingga hasil model prediksi kelulusan ini dapat diterapkan pada aplikasi PIPE.   Kata kunci: algoritma C4.5; decision tree; klasifikasi; prediksi kelulusan.