RMRatih Hafsarah Maharrani

Ratih Hafsarah Maharrani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ratih Hafsarah Maharrani has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Detecting Social Engineering Incidents from Structured Cyber Incident Data: A Rule-Based Labeling Approach with Extra Trees and Gradient Boosting Classifiers

    by Ratih Hafsarah Maharrani, Laura Sari, Oman Somantri

    Social Engineering (SE) remains a major cybersecurity challenge because it exploits human behavior and is difficult to identify at the incident level, particularly in structured cyber incident repositories that do not provide explicit SE labels. This study proposes a weak-labeling approach to detect SE-related incidents in structured cyber incident data, using the EuRepoC v1.3 dataset. The SE label is operationally derived from phishing-related MITRE Initial Access indicators, user-interaction requirements, and selected incident patterns, while variables used in the labeling rule are excluded from prediction to reduce direct label leakage. Two ensemble classifiers, ExtraTrees and Gradient Boosting Classifier (GBC), are evaluated under baseline and tuned settings, with class imbalance addressed using ADASYN, BorderlineSMOTE, SMOTEENN, and SMOTETomek. Performance is assessed using PR-AUC, ROC-AUC, F1-score, accuracy, precision, recall, ablation analysis, and temporal validation. Under the full feature setting, all models achieve strong performance, with PR-AUC values ranging from 0.9695 to 0.9812. The best overall result is obtained by the baseline GBC, which reaches a PR-AUC of 0.9812, ROC-AUC of 0.9782, F1-score of 0.9507, and accuracy of 0.9414. Among the Extra Trees variants, tuned ET + SMOTETomek performs most competitively. However, ablation results show a substantial drop in performance, indicating that much of the predictive power depends on impact-related variables. Temporal validation further shows that the models remain effective for newer incidents under the full-feature setting, although the derived SE label should still be interpreted with caution as a weak proxy rather than as expert-validated ground truth.

  • Open Access

    Handling missing values and clustering industrial liquid waste using K-medoids

    by Ratih Hafsarah Maharrani, Prih Diantono Abda'U, Ganjar Ndaru Ikhtiagung, Nur Wahyu Rahadi, Zaenurrohman Zaenurrohman

    The textile industry is a significant contributor to environmental pollution due to its wastewater, which contains hazardous substances such as dyes, heavy metals, and chemicals that can severely harm aquatic ecosystems. Effective management of this wastewater is crucial to mitigate its environmental impact. This study focuses on classifying industrial liquid waste data using the K-medoids clustering method, chosen for its robustness to noise and outliers compared to K-means. To address challenges in wastewater data processing, such as missing values and varying data scales, two approaches are compared: replacing missing values with zero and K-nearest neighbors (KNN) imputation, alongside Z-score normalization for data uniformity. The clustering quality is evaluated using the Davies-Bouldin index (DBI) for cluster variations of k=2, 3, 4, and 5. The results show that the best clustering quality is achieved at k=2, with the smallest DBI values obtained using KNN imputation (0.139) and zero replacement (0.149). The superior performance of KNN imputation highlights its effectiveness in handling missing data. These findings provide valuable insights into the characteristics of textile industry wastewater pollution, offering a robust framework for effective wastewater management. The study concludes with practical recommendations for policymakers and industry stakeholders to adopt advanced data-driven approaches for sustainable wastewater treatment strategies.

  • Open Access

    Clustering method for criminal crime acts using K-means and principal component analysis

    by Ratih Hafsarah Maharrani, Prih Diantono Abda’u, Muhammad Nur Faiz

    Criminality is an act of violating the values and norms of society that causes a lot of harm. Much of the criminal data is often just a collection of data that has no information. Analysis of crime data is key in efforts to reduce crime rates that provide an overview of the incidence of crime, patterns, levels of vulnerability, and the level of security of an area. This research proposes data analysis that provides an understanding of crime using data mining techniques, especially the K-means cluster method, both traditional and with principal component analysis (PCA) dimension reduction. Before the PCA process, the values are transformed first with Z score normalization. From the processing through the davies bouldin index (DBI) performance test with 3 clusters, it is concluded that traditional K-means produces a DBI Index value of 0.019 and K-means PCA of 0.299. Meanwhile, to see the optimal cluster, several iterations were performed and resulted in the most optimal DBI index of 4 clusters in K-means of 0.014 and K-means PCA of 0.172. From the performance test value, it means that in the context of clustering the traditional criminal K-means data is declared more optimal than K-means PCA.


  • Open Access

    Sentiment review of coastal assessment using neural network and naïve Bayes

    by Oman Somantri, Santi Purwaningrum, Ratih Hafsarah Maharrani

    An assessment of a place will provide an overview for other people whether the place is feasible to be visited or not. Assessment of coastal places will provide a separate assessment for potential visitors in considering visitation. This article proposes a model using the neural network (NN) and naïve Bayes (NB) methods to classify sentiment toward coastal assessments. The proposed NN and NB models are optimized using information gain (IG) and feature weights, namely particle swarm optimization (PSO) and genetic algorithm (GA) which are carried out to increase the level of classification accuracy. Based on the experimental results, the best level of accuracy for the classification of coastal assessments is 87.11% and is named the NB IG+PSO model. The best model obtained is a model that can be used as a decision support for potential beach visitors in deciding to visit the place.


  • Open Access

    Penerapan Metode SMARTER pada Sistem Pendukung Keputusan Pemilihan Lahan Kayu Putih

    by Ratih Hafsarah Maharrani, Prih Diantono Abda’u, Hety Dwi Hastuti

    The productivity of eucalyptus in Indonesia is included in the low productivity group, the lack of raw materials resulting in a deficit in eucalyptus production is the cause of this. Meanwhile market demand is increasing. The large area of land in the Cilacap Regency area is not matched by its utilization, this is due to a lack of knowledge about potential land uses. There are 5 criteria for land, namely land "S1 (Highly Suitable), S2 (Quite Suitable), S3 (marginally suitable), N1 (currently not suitable) and N (not suitable forever). “Decision support methods can be used in determining land suitability, one of which is the SMARTER method. The method was chosen because determining the suitability of eucalyptus land was processed by "rank order centroid (ROC) weighting" where the existing criteria have weight based on the priority level adjusted to the ranking process. Of the 84 processed data, it was found that around 98% or 83 of the data stated that the Cilacap district was included in the S2 suitability range (Quite Appropriate). In addition, based on the results of the accuracy testing carried out, the percentage of accuracy was 80.95%. Seeing the high percentage, the decision support system using the SMARTER method is appropriate to be used to determine the suitability of eucalyptus land. “


  • Open Access

    SIPGANG: Sistem Pendukung Keputusan Rekomendasi Magang Industri Berbasis Multi Attribute Utility Theory (MAUT)

    by Ratih Hafsarah Maharrani, Abdul Rohman Supriyono, Lutfi Syafirullah

    Magang adalah proses penerapan bidang keilmuan dan keterampilan yang diperoleh di kampus pada dunia industry. Dalam pelaksanaannya, saat mahasiswa selesai melaksanakan magang ada beberapa mengeluhkan bahwa perusahaan tempat magang tidak sesuai dengan standar yang diinginkan, tidak sesuai bidang serta beban kerja yang berlebih sehingga dalam pelaksanaanya mahasiswa merasa tidak bisa optimal dalam menggunakan kemampuan yang dimiliki. Hal ini dikarenakan adanya subjektifitas dalam penentuan tempat magang, mahasiswa memilih sendiri tempat magang tersebut yang terkadang belum mengetahui job desk yang akan dikerjakan. Selain itu koordinator magang jurusan merekomendasikan tempat magang berdasarkan penilaian pembimbing magang saat visitasi padahal tidak mengetahui keadaan sebenarnya yang telah terlaksana. Sehingga dalam hal ini dibutuhkan adanya sebuah sistem yang mampu membantu dalam pengambilan keputusan rekomendasi tempat magang. Penelitian ini dibuat dengan menerapkan metode pengembangan system Rapid Development Prototyping (RAD) dan penilaian rekomendasi diperoleh menggunakan metode MAUT (Multi Attribute Utility Theory). Metode MAUT akan mengolah penilaian dari masing kriteria (jam kerja, bobot tugas yang diberikan selama magang, kesesuaian tugas dengan keahlian, standar perusahaan, penerapan K3 di perusahaan, fasilitas dan peralatan praktik untuk peserta magang serta bidang keahlian) sesuai dengan bobot yang ditentukan dengan tujuan memberikan penilaian dari sisi mahasiswa yang telah selesai pelaksanaan magang terhadap industri bersangkutan. Pengujian pada aplikasi SIPGANG penentuan rekomendasi industry menggunakan uji kuisioner dengan Sistem Usability Scale (SUS) dan didapatkan hasil akhir 72 yang menyatakan bahwa system dalam kategori layak untuk digunakan.


  • Open Access

    Grouping Industrial Class Placement Selection for Students Using Multi-Objective Optimization on the basis of Ratio Analysis

    by Ratih Hafsarah Maharrani, Oman Somantri

    The quality and success of a company is determined from the planning and efforts to meet the needs of Human Resources carried out in the selection process. This means that in an effective selection process good human resources can be obtained for a longer period of time. In this study, the effectiveness of student values ​​will be analyzed with a decision support system that is used to facilitate management in the selection stage of industrial class students. From the results of the assessment, the student will be recommended to become a new employee of PT BUMA who comes from the vocational level through an industry-based curriculum education program. There are 5 criteria in the process of calculating the assessment of industrial class students, including the average student report card grades, psychological test results, HRD interviews, physical checks and pre-medical. Value processing uses a decision support system with a Multi-Objective Optimization method on the basis of Ratio Analysis (MOORA) where if the greater the student's grade results, the better the rankings produced, the more in line with the criteria expected by the company. The MOORA method was chosen because it can provide ease in the ranking process by finding the best alternative from several alternatives.