Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Building of Informatics, Technology and Science KLIK: Kajian Ilmiah Informatika dan Komputer
Ken Dhita Tania
Universitas Sriwijaya, Palembang
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Perancangan User Interface Pada Aplikasi Lapor Menggunakan Knowledge Management Muhammad Chandra Prawira; Ken Dhita Tania
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 3 No. 6 (2023): Juni 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v3i6.968

Abstract

School is an educational institution that organizes the teaching and learning process. School activities for teachers and students also depend on good learning, collection and management of knowledge. Because the teacher is one of the key success factors for any educational endeavor, teachers are therefore expected to act as educators, instructors, and mentors to improve student learning outcomes and motivate students to learn. The role of a teacher is very influential in realizing the quality of education, especially teacher performance. Therefore, teacher performance is one of the most important conditions for successful learning. SMP Negeri 60 Palembang has problems handling student and teacher cases and this school is also a new school where there are constraints on inadequate and incomplete facilities with a large number of students, causing the teaching and learning process to be slightly hampered. The design thinking method can understand users, present evidence, and overcome problems in devising strategies to find solutions. Therefore, design thinking is considered capable of solving problems in creating solutions based on user needs. To support the process of information purposes at SMPN 60 Palembang without being limited by distance and time so that the information can be used optimally by both students and teachers.
Leakage-Aware Random Forest Regression for Predicting Job Automation Risk Using Structured Labor Market Data Alya Zalfa Chairunnisa; Nawirah Athqiyah; Vanisa Amalia Putri; Ken Dhita Tania; Allsela Meiriza
Building of Informatics, Technology and Science (BITS) Vol 8 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v8i1.9706

Abstract

This study aims to predict job automation risk in the era of artificial intelligence (AI) using a leakage-aware Random Forest Regression approach. The automation risk score, defined as a composite index derived from task exposure to AI, occupational routine intensity, and technological susceptibility indicators sourced from the AI Impact Jobs Dataset, serves as the target variable. The dataset comprises 5,000 job vacancy records from 44 countries across 9 industries spanning 2010 to 2025. A rigorous methodological framework is applied by systematically identifying and eliminating potential data leakage features, including ai_intensity_score, reskilling_required, and ai_mentioned, which were found to share mathematical or conceptual derivation paths with the target variable. The model is evaluated using R², RMSE, MAE, and MAPE with 5-fold cross-validation. The results show that the model achieves an R² score of 0.8087 on testing data, with RMSE of 0.1129 and MAE of 0.0893. Feature importance analysis reveals that salary_change_vs_prev_year_percent is the most influential predictor (55.85%), which, although indicative of dominance bias typical in synthetic datasets, aligns with economic theories linking wage dynamics to automation incentives. The findings demonstrate that leakage control significantly reduces inflated performance estimates (from R² = 0.8857 to 0.8087), and that Random Forest Regression provides a robust predictive framework for tabular socio-economic data when combined with rigorous preprocessing. This study contributes a methodological template for preventing data leakage in labor market prediction tasks.
Comparison of Clustering Algorithms for Analyzing the Impact of Conflict on Poverty and Inflation M Raykah Alam Ramadan; Dhio Pratama Wiransyah; Satria Ramadhani; Rayya Ramadhan Simangunsong; Ken Dhita Tania; Alsella Meiriza; Ahmad Rifai
Building of Informatics, Technology and Science (BITS) Vol 7 No 4 (2026): March 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i4.9512

Abstract

Armed conflict can have significant impacts on the social and economic conditions of a region, particularly on poverty levels and inflation. This study aims to analyze the impact of conflict on key economic indicators using a Knowledge Management System (KMS) approach and to compare the performance of clustering algorithms in identifying underlying data patterns. The research applies clustering analysis by comparing K-Means, DBSCAN, and Hierarchical Clustering algorithms to group data based on similarities in economic characteristics. The dataset used in this study consists of several indicators, including poverty levels before and during conflict, extreme poverty rates, inflation rates, GDP changes, and currency devaluation. Data preprocessing techniques such as normalization are applied to ensure comparability among variables. The evaluation of clustering performance is conducted using Silhouette Score and Davies–Bouldin Index to determine the most effective algorithm. The results show that clustering methods are able to identify distinct grouping patterns of regions based on the level of conflict impact on economic conditions. Among the evaluated algorithms, DBSCAN demonstrates superior performance in handling complex and uneven data distributions. The analysis also indicates a consistent tendency for poverty and inflation to increase during periods of conflict, highlighting the economic vulnerability of affected regions. Furthermore, the integration of clustering results into a Knowledge Management System enables the transformation of analytical outputs into structured knowledge that can support data-driven decision making. These findings are expected to contribute to the development of more effective economic policies and analytical frameworks in conflict-affected areas.
Comparative Customer Segmentation Pipelines for E-Commerce Using K-Means-KNN and UMAP-K-Means-XGBoost Dzidan Aditya Gumilang; Endang Lestari Ruskan; Ardina Ariani; Ken Dhita Tania; Ahmad Rifai
Building of Informatics, Technology and Science (BITS) Vol 8 No 2 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v8i2.10794

Abstract

The rapid expansion of e-commerce has generated massive volumes of customer data that remain underutilized for supporting Customer Relationship Management (CRM) strategies. Conventional customer segmentation approaches commonly employ a pipeline consisting of K-Means clustering followed by K-Nearest Neighbors (KNN) classification. However, this approach exhibits limitations in handling high-dimensional data and maintaining classification performance on large-scale datasets. This study presents a comparative analysis of two customer segmentation pipelines: the conventional K-Means-KNN pipeline and the proposed Uniform Manifold Approximation and Projection (UMAP)-K-Means-XGBoost pipeline. The experiments were conducted using the E-Commerce Shopper Behavior & Lifestyle dataset, comprising approximately one million customer records and eight selected features representing transactional, psychographic, and financial behavioral characteristics. Clustering performance was evaluated using the Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Index, while classification performance was assessed using accuracy, precision, recall, and F1-score. Experimental results demonstrate that incorporating UMAP improves cluster separability by preserving the intrinsic structure of high dimensional data, whereas XGBoost consistently outperforms KNN in downstream classification, achieving an accuracy exceeding 99%. These findings indicate that the UMAP-K-Means-XGBoost pipeline provides a more robust, scalable, and interpretable framework for customer segmentation, thereby offering more reliable decision support for data-driven CRM strategies in e-commerce environments.
Co-Authors Ahmad Rifai Allsela Meiriza, Allsela Alsella Meiriza Alya Zalfa Chairunnisa Ardina Ariani Dhio Pratama Wiransyah Dzidan Aditya Gumilang Endang Lestari Ruskan M Raykah Alam Ramadan Muhammad Chandra Prawira Nawirah Athqiyah Rayya Ramadhan Simangunsong Satria Ramadhani Vanisa Amalia Putri