Claim Missing Document
Check
Articles

Found 6 Documents
Search

Penerapan Algoritma Decision Tree C4.5 Pada Test MBTI Berbasis Web: Studi Kasus: Universitas Katolik Musi Charitas Elvira, Redempta Rista; Fery Herdiatmoko
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

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

Abstract

A major problem in student personality assessment is the manual process of completing and interpreting test results, which leads to subjective bias and delays in counseling services. To address this, this study applies the Decision Tree C4.5 algorithm to a web-based MBTI test to produce an objective and efficient personality type classification. This study discusses the implementation of the Decision Tree C4.5 algorithm in a web-based Myers-Briggs Type Indicator (MBTI) test to classify students’ personality types at Musi Charitas Catholic University. The research objectives are (1) to apply and evaluate the Decision Tree C4.5 algorithm in personality classification based on MBTI test results, and (2) to develop a counseling support system capable of providing automatic, objective, and easy-to-understand classification results. The research method employed is development research (Research and Development) using the Waterfall model, including requirement analysis, system design, implementation, testing, and evaluation. The C4.5 algorithm was implemented to construct a classification model based on decision rules, which was then integrated into the web application. System testing using Black-Box and White-Box methods ensured that the system operates according to specifications and that all logical paths have been tested. Evaluation results indicate a classification accuracy of approximately 86% with consistent precision, recall, and F1-score values, demonstrating the effectiveness of the C4.5 algorithm in personality type classification. The system improves efficiency, accessibility, and objectivity in personality assessment compared to manual methods and can support sustainable student counseling and development services.
Prediksi Kualitas Udara DKI Jakarta Menggunakan Algoritma Random Forest Berbasis Time-Lag Feature Heronimus Diego Prasetya; Jeremia Sandy Pratama; Alifah Khoirunnisaa; Hendrik Fery Herdiatmoko
Journal Of Informatics And Busisnes Vol. 3 No. 4 (2026): Januari - Maret
Publisher : CV. ITTC INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jibs.v3i4.3933

Abstract

The volatility of air quality in Jakarta, which often deteriorates abruptly, demands a proactive early warning mechanism rather than mere real-time monitoring. A major limitation in environmental datasets is the class imbalance, where extreme hazardous conditions are recorded much less frequently than normal conditions, causing them to be overlooked by standard prediction models. This study aims to develop an H+1 (next-day) air quality prediction system by integrating the Random Forest algorithm with the SMOTE (Synthetic Minority Over-sampling Technique) data balancing technique. A Time-Lag feature engineering approach was applied to transform historical data from 2010-2025 into future predictive variables. Experimental results demonstrate that the application of SMOTE successfully improved the model's sensitivity in recognizing 'Unhealthy' categories that were previously difficult to detect. Feature analysis revealed that the accumulation of surface Ozone (O3) and Particulate Matter (PM10) serve as the most dominant indicators triggering air status changes for the following day. This system is intended to serve as a health mitigation reference for the public prior to outdoor activities.
Optimasi Support Vector Machine Menggunakan Feature Selection Chi-Square untuk Klasifikasi Sentimen Program Makan Siang Gratis I Komang Darmawan; Aji Prayogo; Steven Chan; Hendrik Fery Herdiatmoko
Journal Of Informatics And Busisnes Vol. 3 No. 4 (2026): Januari - Maret
Publisher : CV. ITTC INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jibs.v3i4.3943

Abstract

The Free Nutritious Lunch program policy has triggered massive public discourse on social media X, reflecting diverse public perceptions toward government policy effectiveness. This study aims to optimize the performance of the Support Vector Machine (SVM) algorithm by implementing Chi-Square Feature Selection to address high data dimensionality and noise challenges in social media text. A dataset of 10,524 tweets was acquired and processed through preprocessing, TF-IDF weighting, and lexicon-based automatic labeling. The results show that Chi-Square feature selection integration successfully reduced dimensions from 16,394 to the 1,000 best features without degrading accuracy. The linear kernel SVM model achieved an optimal accuracy rate of 91.12%. However, this study identifies that this high accuracy is heavily influenced by the dominance of the positive class, whereas performance on the negative and neutral classes remains limited due to data imbalance. Overall, feature optimization proved to increase computational efficiency while maintaining accuracy stability in mapping public responses to strategic national policies.
Analisis Sentimen Ulasan Aplikasi Bibit Menggunakan TF-IDF dan Support Vector Machine Marselinus Dewadaru Bayu Adeodatus; Sepiyana Nopitasari; Wirda Arta Meivia; Hendrik Fery Herdiatmoko
Journal Of Informatics And Busisnes Vol. 3 No. 4 (2026): Januari - Maret
Publisher : CV. ITTC INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jibs.v3i4.3973

Abstract

The rapid growth of financial technology (fintech) applications has increased the number of user reviews on digital platforms. These reviews contain valuable information regarding application quality, yet they are unstructured and difficult to analyze manually. This study aims to classify user review sentiments of the Bibit investment application into positive and negative categories using the Term Frequency–Inverse Document Frequency (TF-IDF) method and the Support Vector Machine (SVM) algorithm. The dataset was obtained from Kaggle, consisting of user reviews of the Bibit application collected from Google Play Store. The data were processed through several preprocessing stages, including cleaning, case folding, tokenization, stopword removal, and stemming. Feature extraction was performed using TF-IDF, and classification was conducted using SVM with a linear kernel. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the combination of TF-IDF and SVM provides good performance in classifying the sentiment of Bibit application user reviews.
Penerapan Algoritma Decision Tree C4.5 Pada Test MBTI Berbasis Web: Studi Kasus: Universitas Katolik Musi Charitas Redempta Elvira; Fery Herdiatmoko
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No2.pp316-322

Abstract

A major problem in student personality assessment is the manual process of completing and interpreting test results, which leads to subjective bias and delays in counseling services. To address this, this study applies the Decision Tree C4.5 algorithm to a web-based MBTI test to produce an objective and efficient personality type classification. This study discusses the implementation of the Decision Tree C4.5 algorithm in a web-based Myers-Briggs Type Indicator (MBTI) test to classify students’ personality types at Musi Charitas Catholic University. The research objectives are (1) to apply and evaluate the Decision Tree C4.5 algorithm in personality classification based on MBTI test results, and (2) to develop a counseling support system capable of providing automatic, objective, and easy-to-understand classification results. The research method employed is development research (Research and Development) using the Waterfall model, including requirement analysis, system design, implementation, testing, and evaluation. The C4.5 algorithm was implemented to construct a classification model based on decision rules, which was then integrated into the web application. System testing using Black-Box and White-Box methods ensured that the system operates according to specifications and that all logical paths have been tested. Evaluation results indicate a classification accuracy of approximately 86% with consistent precision, recall, and F1-score values, demonstrating the effectiveness of the C4.5 algorithm in personality type classification. The system improves efficiency, accessibility, and objectivity in personality assessment compared to manual methods and can support sustainable student counseling and development services.
Implementasi Hierarchical Clustering untuk Analisis FDMC Narrative Crypto Berbasis Web M. Fathir Adha; Hendrik Fery Herdiatmoko
JITU Vol 10 No 1 (2026)
Publisher : Universitas Boyolali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36596/jitu.v10i1.2255

Abstract

This study implements the Hierarchical Clustering algorithm with Ward linkage and Euclidean distance methods to analyze 26 crypto narratives based on the Fully Diluted Market Cap (FDMC) metric. Using a hybrid method that integrates Waterfall, Cross-Industry Standard Process for Data Mining (CRISP-DM), and Knowledge Discovery in Databases (KDD), data was obtained from the CoinGecko API, manually clustered, and aggregated per narrative. Pre-processing involved logarithmic transformation (log-10) and Z-Score normalization to address power-law distributions and outliers, resulting in a more stable cluster structure. The clustering results mapped the market into five clusters: Bluechip (L1 with FDMC $2.76T), Growth (PAY, MEME, CEX, DEX, DeFi totaling $468.22B), Growth (AI, DePIN, DAO, L2, RWA, ORC, GameFi, XCH, DID, PRC, LST with $192.91B), Speculative (NFT, MET, SocialFi, BTC Eco, W3I with $17.55B), and Speculative (LPD, GambleFi, FTO, SEC with $2.34B). The model was validated with a Silhouette Score of 0.650 and a Cophenetic Correlation Coefficient of 0.647, indicating cohesive and representative clusters. A web-based implementation using Django, D3.js, and Chart.js provides interactive visualizations and portfolio recommendations. Contributions include a novel fundamental valuation approach, an adaptive clustering model, and practical analytical tools for investors, with potential expansion to multidimensional metrics in the future.