Claim Missing Document
Check
Articles

Found 20 Documents
Search

Credit Risk Analysis With Extreme Gradient Boosting and Adaptive Boosting Algorithm Rosa Delima Mendrofa; Maria Hosianna Siallagan; Junita Amalia; Diana Pebrianty Pakpahan
Journal of Information System,Graphics, Hospitality and Technology Vol. 5 No. 1 (2023): Journal of Information System, Graphics, Hospitality and Technology
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37823/insight.v5i1.233

Abstract

Credit Risk Analysis digunakan untuk mengenali resiko terhadap pinjaman untuk mencegah penunggakan pembayaran utang. Pemberian uji kelayakan pinjaman dapat di analisis menggunakan model klasifikasi. Untuk menghasilkan model credit risk analysis yang sesuai, penulis mengajukan Algoritma Extreme Gradient Boosting (XGBoost) dan Adaptive Boosting (AdaBoost). Data yang digunakan dalam penelitian ini adalah data pinjaman platform Peer to Peer (P2P) Lending. Penelitian ini menerapkan data preprocessing yang bertujuan untuk menghasilkan data yang lebih baik dan melakukan analisis terhadap data. Analisis dilakukan berdasarkan fitur yang dimiliki oleh peminjam menggunakan algoritma klasifikasi berdasarkan historical data pinjaman peminjam. Fitur yang digunakan seperti jumlah pinjaman yang diajukan, total pinjaman yang ditawarkan, jumlah pembayaran pinjaman, jangka waktu pembayaran, suku bungan pinjaman, jumlah angsuran dan lain lain. Jumlah fitur sebelum dilakukan data reduksi 136 dan setelah direduksi 34 fitur.  Fitur tersebut digunakan pada penerapan algoritma XGBoost dan AdaBoost untuk menghasilkan klasifikasi good borrower dan bad borrower. Penulis menggunakan metode evaluasi kurva ROC dan nilai AUC untuk menilai performa dari kedua algoritma. Pada kurva ROC, nilai AUC dari algoritma XGBoost 0,92 dan nilai AUC dari algrithma AdaBoost adalah 0,89. Berdasarkan perbandingan nilai AUC tersebut dapat disimpulkan algoritma XGBoost menghasilkan klasifikasi yang lebih baik untuk model klasifikasi pemberian pinjaman.
Pelatihan Metode Ilmiah dan Analisis Statistika untuk Siswa SMKS Arjuna Junita Amalia*; Ike Fitrianingsih; Sahat Pandapotan Nainggolan
Dinamisia : Jurnal Pengabdian Kepada Masyarakat Vol. 7 No. 5 (2023): Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/dinamisia.v7i5.15818

Abstract

Kegiatan pengabdian kepada masyarakat (PkM) Pelatihan Metode Ilmiah dan Analisis Statistika untuk siswa SMKS Arjuna ini merupakan bagian dari upaya untuk menumbuhkan bakat, minat dan kemampuan meneliti siswa. Hal yang melatarbelakangi kegiatan ini adalah sedikitnya pemenang lomba karya ilmiah dari SMK di Sumatera Utara. SMK Swasta Arjuna merupakan salah satu SMK di sekitar Institut Teknologi Del yang membuka jurusan farmasi dan kesehatan, yang bekerja sama dengan Pemerintahan kabupaten Toba untuk pengembangan obat herbal. Pelaksanaan pelatihan ini telah berjalan lancar dengan baik. Meskipun siswa belum dapat menulis topik sesuai jurusan mereka, namun pelatihan ini telah mampu memberikan pemahaman dasar menulis karya ilmiah dan analisis statistika. Siswa telah mampu mengangkat topik di sekitar mereka dan menuliskannya ke dalam karya ilmiah serta mempresentasikan dan mempertanggungjawabkan hasil karyanya di depan juri. Berdasarkan hasil kuesioner, peserta menyampaikan bahwa pelatihan ini bermanfaat karena memberikan pemahaman serta motivasi untuk menulis karya ilmiah.
The News Classification Using Bidirectional Long Short Term Memory and GloVe Sirait, Elisabet Margaret; Silalahi, Raynaldo; Tambunan, Annessa Aprilly; Amalia, Junita
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 1 (2024): Articles Research Volume 8 Issue 1, January 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i1.13005

Abstract

The dissemination of information and news via online media encompasses not only established news platforms but also contributions from internet users, lacking oversight. News constitutes fact-grounded insights into ongoing occurrences. This research employed Bidirectional Long- and Short-Term Memory with Hyperparameter tuning on GloVe for news classification. This research aims to optimize news categorization through hyperparameter tuning on GloVe. GloVe facilitated the transformation of words into vector matrices, exploring its efficacy in news classification with hyperparameter tuning and Bi-LSTM for text analysis. Experiments encompassed untuned and hyperparameter-tuned approaches, employing GloVe's hyperparameters using Gridsearch and manual methods. GloVe's hyperparameter tuning reveals the potential for enhancing word vector representations. Surprisingly, non-hyperparameter tuned news classification yielded superior evaluation results compared to the hyperparameter approach. The untuned experiment achieved an accuracy of 0.98, while the gridsearch method yielded 0.85 accuracy, and hyperparameter tuning generated a 0.88 precision in the -11 model. These findings underscore the nuanced interplay of hyperparameters in optimizing text classification models like GloVe.
Impact Of Sarcasm Detection on Sentiment Analysis Using Bi-LSTM and FastText Amalia, Junita; Matondang, Dian Filia; Hutajulu, Gibert E.M.; Hasibuan, Agustina
Jurnal Sistem Informasi Bisnis Vol 14, No 4 (2024): Volume 14 Nomor 4 Tahun 2024
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21456/vol14iss4pp353-362

Abstract

Sentiment analysis categorizes a collection of texts in a document as either positive or negative. However, sometimes it cannot give accurate results due to sarcastic sentences. Sarcasm involves the use of positive language to convey negative meanings, So sarcasm detection is needed for sentiment classification to provide better results. One method that can be used to perform Sentiment classification is Bidirectional Long Short-Term Memory (Bi-LSTM). However, text data cannot be processed by Bi-LSTM, so it requires word embedding to convert text data into vectors. In this study, the word embedding used is FastText because it can learn the form of words by considering subword information. The results showed that sentiment classification with sarcasm detection could improve evaluation results by 0.08 for precision, 0.07 for recall, 0.07 for F1-score, and 0.07 for accuracy. A paired sample t-test was conducted on precision, recall, F1-score, and accuracy to examine whether there is a difference between sentiment classification with and without sarcasm detection. The obtained p-values are 2.84.10-9, 4.63.10-7, and 2.40.10-8, 6.22.10-8, respectively. This indicates a difference between sentiment classification with and without sarcasm detection. Therefore, with a 95% confidence level, it can be concluded that sarcasm detection impacts sentiment classification.
Enhancing Credit Risk Classification Using LightGBM with Deep Feature Synthesis Tambunan, Sarah Rosdiana; Amalia, Junita; Sitorus, Kristina Margaret; Sibuea, Yehezchiel Abed Rafles; Hutabarat, Lucas Ronaldi
Journal of Information System and Informatics Vol 6 No 4 (2024): December
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i4.902

Abstract

In the digital financial services era, Peer-to-Peer (P2P) lending has emerged as a significant innovation in fintech. However, credit risk remains a major concern due to the potential for payment failures, which can cause losses for platforms and investors. This research explores the impact of Deep Feature Synthesis (DFS) on credit risk classification and evaluates the performance of the Light Gradient Boosting Machine (LightGBM) algorithm with and without DFS. The data used in this study was sourced from Kaggle, a peer-to-peer lending company based in San Francisco, California, United States. The dataset contains 74 attributes, with a total of 887,379 rows. DFS automatically generates new attributes, while LightGBM is used for selecting the most important features, aiming to optimize credit risk predictions and simplify the model's complexity. The results of credit risk classification models using DFS and without it. Findings reveal that DFS enhances the accuracy of the credit risk classification, achieving a 0.99 accuracy rate compared to 0.97 without DFS, achieving a recall and F1-score of 0.94 and 0.96 with DFS and 0.68 and 0.81 without DFS. These results suggest that DFS is an effective feature engineering technique for boosting credit risk model performance. This research contributes significantly to the P2P lending industry by demonstrating that combining DFS with LightGBM can improve credit risk management, making it a valuable approach for financial platforms.
Performance Analysis of MobileNetV3-based Convolutional Neural Network for Facial Skin Disorder Classification Herimanto; Arie Satia Dharma; Junita Amalia; David Largo; Christin Adelia Pratiwi Sihite
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 6 (2024): December 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i6.5982

Abstract

Accurately identifying facial skin types is essential for recommending the right skincare treatments and products. Misidentifying skin types can lead to negative consequences, such as irritation or worsening of skin conditions. This study investigated methods for classifying facial skin types into five categories: oily, acne-prone, dry, normal, and combination. A dataset of 1725 augmented facial images was used. Data augmentation techniques likely increased the dataset's diversity, which helps improve the model's generalization ability. The data underwent preprocessing, including rescaling, before being applied to two deep learning models, CNN and MobileNetV3. The models were evaluated based on accuracy and execution time to determine the most effective approach for classifying facial skin types. The CNN model achieved an accuracy of 64%, demonstrating its potential for image classification tasks. However, the MobileNetV3 model significantly outperformed CNN with an accuracy of 84%. This superior performance is attributed to MobileNetV3's advanced architecture, which is optimized for efficient feature extraction, and particularly relevant for capturing the subtle variations in facial skin types. Therefore, MobileNetV3 emerged as the more effective method for classifying facial skin types with higher accuracy.
Enhancing Hate Speech Detection: Leveraging Emoji Preprocessing with BI-LSTM Model Amalia, Junita; Tambunan, Sarah Rosdiana; Purba, Susi Eva Maria; Simanjuntak, Walker Valentinus
Journal of Information System and Informatics Vol 7 No 2 (2025): June
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i2.1147

Abstract

Microblogging platforms like Twitter enable users to rapidly share opinions, information, and viewpoints. However, the vast volume of daily user-generated content poses challenges in ensuring the platform remains safe and inclusive. One key concern is the prevalence of hate speech, which must be addressed to foster a respectful and open environment. This study explores the effectiveness of the Emoji Description Method (EMJ DESC), which enhances tweet classification by converting emojis into descriptive text or sentences. These descriptions are then encoded into numerical vector matrices that capture the meaning and emotional tone of each emoji. Integrated into a basic text classification model, these vectors help improve detection performance. The research examines how different emoji preprocessing strategies affect the performance of a BI-LSTM model for hate speech classification. Results show that removing emojis significantly reduces accuracy (68%) and weakens the model’s ability to distinguish between hate and non-hate speech, due to the loss of valuable semantic context. In contrast, retaining emoji semantics either through textual descriptions or embeddings boosts classification accuracy to 93% and 94%, respectively. The highest performance is achieved through emoji embedding, highlighting its ability to capture subtle non-verbal cues critically for accurate hate speech detection. Overall, the findings emphasize the importance of incorporating emoji-aware preprocessing techniques to enhance the effectiveness of social media content classification.
Creditworthiness Classification Utilizing AHP-SVM Based on 5C Criteria Amalia, Junita; Manalu, Agnes Judika Margaretha; Ambarita, Jeremia Nico Pratama; Sihombing, Dwita
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 3 (2025): Article Research July 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i3.15049

Abstract

Credit risk occurs when borrowers fail to meet loan repayment obligations, posing significant challenges to the financial stability of lending institutions. Accurate classification of creditworthiness is essential to mitigate such risks. This study proposes a hybrid approach that integrates the Analytical Hierarchy Process (AHP) and Support Vector Machine (SVM) to evaluate borrower eligibility based on the 5C model: Character, Capacity, Capital, Collateral, and Condition. The AHP method is used to assign weights to credit attributes based on expert judgment, while SVM performs the classification. Three experiments were conducted to compare the effectiveness of different feature selection strategies: (1) expert-defined 5C attributes, (2) AHP weighting conducted by experts, and (3) AHP weighting conducted by non-experts. Experimental results show that the 5C-SVM model achieved the highest performance with 96% accuracy, followed by AHP-SVM (expert) with 95% and AHP-SVM (non-expert) with 93%. The findings indicate that expert involvement in the feature selection process significantly improves model performance. This study demonstrates the effectiveness of combining domain knowledge with machine learning in building intelligent decision support systems for credit risk analysis. The proposed approach offers practical value for financial institutions seeking more objective, accurate, and consistent credit evaluation processes. Furthermore, it opens new opportunities for integrating expert-based reasoning with automated analytics in financial decision-making.  
Optimalisasi Kemampuan Matematika Siswa Toba Melalui Kompetisi Del Mathematics And Science 2022 Siagian, Andrew Rolas; Junita Amalia; Regina Ayunita Tarigan; Sahat Pandapotan Nainggolan; Yoli Agnesia
Jurnal Pengabdian Masyarakat Mandira Cendikia Vol. 3 No. 6 (2024)
Publisher : YAYASAN PENDIDIKAN MANDIRA CENDIKIA

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

Abstract

Kegiatan pengabdian melalui kolaborasi yang dibangun oleh dosen dan mahasiswa Institut Teknologi DEL dalam bentuk kompetisi matematika dan sains yang dilaksanakan di kampus IT DEL. Salah satu arah kebijakan program pembangunan pendidikan nasional dalam bidang pendidikan salah satunya adalah mengembangkan kualitas sumber daya manusia sedini mungkin, secara terarah, khususnya kemampuan matematis. Dalam mendukung hal tersebut, UPT Sains dan Matematika, Institut Teknologi Del, memfasilitasi dengan melakukan kegiatan lomba sains dan matematika untuk tingkat SMA. Lomba sains dan matematika masih sangat perlu disosialisasikan kepada siswa, orangtua siswa, guru, pengawas, Dinas Pendidikan dan berbagai pihak terkait. Kegiatan dibagi atas 2 tahapan yaitu babak semifinal dan babak Final. Peserta yang telah mendaftarkan diri untuk ikut dalam babak semifinal ada 255 siswa, dengan masing-masing bidang studi adalah sebagai berikut: 70 siswa untuk bidang studi matematika, 57 siswa untuk bidang studi fisika, 63 siswa untuk bidang studi kimia, dan 65 siswa untuk bidang studi biologi. Maanfaat yang terlihat dari kegiatan ini adalah meningkatnya minat belajar siswa SMA terhadap mata pelajaran sains dan matematika, meningkatnya kemampuan matematis siswa. Selain itu, manfaat untuk guru, dosen dan mahasiswa yang dapat memberikan aspirasinya dalam pembangunan pendidikan nasional juga sangat kuat dalam kegiatan ini.
Dari Sitoluama untuk Indonesia : Menumbuhkan Generasi Ilmuwan Melalui DMSC 2024 Regina Ayunita Tarigan; Asido Saragih; Junita Amalia; Jaya Santoso; Ana Muliyana; Sari Muthia Sari; Andrew Rolas Siagian
KREATIF: Jurnal Pengabdian Masyarakat Nusantara Vol. 5 No. 2 (2025): Jurnal Pengabdian Masyarakat Nusantara
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/kreatif.v5i2.6023

Abstract

The proficiency of Indonesian students in mathematics and science remains relatively low, as reflected in the 2022 PISA survey, which ranked Indonesia 69th out of 81 participating countries. This low level of mathematical and scientific literacy has become a major concern in efforts to improve the quality of education. This community service activity aims to foster interest and motivation among senior high school students (SMA/SMK/MA or equivalent) in the fields of mathematics, physics, chemistry, and biology through the organization of the Del Mathematics and Science Competition (DMSC) in 2024. The competition was conducted in two stages: an online preliminary round on November 2, 2024, and an on-site final round on November 9, 2024, at Institut Teknologi Del, coinciding with World Scientiest Day. The implementation method included competition promotion, online participant selection, and in-person contest execution with an objective scoring system. The findings indicated high enthusiasm among participants from various regions of Indonesia, along with improved understanding and confidence in solving concept-based problems. The implications of this activity suggest that science-based competitions can serve as effective platforms to raise public awareness of the importance of mastering science and support national efforts to enhance the quality of education in mathematics and science