Universitas Ahmad Dahlan Journal
Not a member yet
5744 research outputs found
Sort by
A Machine Learning-Based Approach for Retail Demand Forecasting: The Impact of Spending Score and Algorithm Optimization
Full text linkDemand forecasting in the retail industry remains a critical challenge, with inaccurate predictions leading to substantial inventory inefficiencies, financial losses, and reduced customer satisfaction. Traditional forecasting methods, primarily reliant on historical sales data, often lack the capacity to effectively model the complexities of dynamic consumer behavior and rapid market fluctuations. To address this, this study proposes a refined demand forecasting approach through the introduction of the Spending Score, a novel synthetic feature that synthesizes customer purchase frequency and total spending to augment predictive accuracy. We implement and optimize machine learning algorithms, specifically Random Forest, Decision Tree, and Support Vector Machine (SVM), using rigorous hyperparameter tuning techniques to determine the most effective model for retail demand prediction. Utilizing detailed customer transaction data, this research aims to identify key purchasing patterns that significantly influence demand variability. By integrating the Spending Score into our predictive models, we provide a data-driven framework enabling retailers to optimize inventory management, enhance targeted marketing strategies, and minimize operational inefficiencies. Empirical results demonstrate that the inclusion of the Spending Score leads to more stable and accurate demand forecasts, facilitating improved alignment between supply and market demand. While acknowledging potential limitations, including data scalability issues and the risk of feature-induced bias, future research will explore the integration of real-time data streams, advanced deep learning methodologies, and expanded datasets to further improve predictive capabilities and model adaptability in the continuously evolving retail landscape
The law and the agitation for state police in Nigeria: Any point of convergence?
Full text linkIntroduction to the Problem: Every major security breach or threat to lives and property in any federating state of Nigeria renews the agitation for the creation of state police in Nigeria. The unitary command of the Nigeria Police Force (NPF) in a constitutional federalism such as Nigeria can at best be an aberration given the expansive unpoliced spaces within the country with their unavoidable security consequences.
Purpose/Study Objectives: This paper makes a constructive appraisal of the policing challenges in Nigeria, identifying the centralised command of the NPF as a major obstacle to effective policing in Nigeria.
Design/Methodology/Approach: Adopting the doctrinal research methodology, the paper evaluates the current policing structure and its effectiveness.
Findings: The paper finds that there is a need to unbundle the NPF, justifying the desirability for the establishment of autonomous state police as an ingredient of true federalism. It recommends the amendment of Sections 214 and 215(4) of the Constitution of the Federal Republic of Nigeria 1999 (CFRN) to align with the provisions of Section 176 of the CFRN and subsisting case-law authorities.
Paper Type: Research Articl
Legal protections against unfair competition in e-commerce: Analysis of Indonesian and Thailand framework adequacy
Full text linkIntroduction to the Problem: Unfair competition threatens economic growth and is harder to detect in the digital era. For Indonesia and Thailand, growing digital economies depend on fair online marketplaces, yet these platforms face risks like price manipulation and visibility bias. Addressing these issues is crucial to unlocking their global trade potential.
Purpose/Study Objectives: The purpose of this research is to analyze the normative potentials and challenges in enforcing antitrust laws in Indonesian and Thai online marketplaces, particularly in addressing antitrust challenges that are unique to the digital environment.
Design/Methodology/Approach: This research utilizes normative legal research method and a comparative legal approach to examine the frameworks for protecting against unfair competition in online marketplaces in Indonesia and Thailand.
Findings: Findings of this study highlight that the existing antitrust laws in Indonesia and Thailand are not equipped to address the unique challenges of digital markets, such as algorithm-driven price fixing, product visibility manipulation, and data monopoly. The study proposes a legal framework model focusing on enhancing algorithmic transparency, ensuring search neutrality, establishing robust market monitoring, and integrating data governance with antitrust measures. This model aims to bolster fair competition and consumer protection, positioning both nations to leverage their digital economy potentials effectively.
Paper Type: Research Articl
Indonesian Adaptation of the Cultural Intelligence Scale (CQS)
Full text linkIndonesia is a country with diverse cultural backgrounds, so intercultural interactions often occur. This research aims to adapt the Cultural Quotient Scale developed by Ang and Van Dyne (2008) into Indonesian to support various research on cultural intelligence. The CQS measuring tool consists of 20 statement items and is divided into 4-factors, namely metacognitive, cognitive, motivational, and behavioral. Testing was carried out using the Exploratory Factor Analysis (EFA) and Confirmatory Factor Analysis (CFA) methods involving 324 Satya Wacana Christian University students who were divided into 2 random sample groups (EFA, n=162 & CFA, n=162). The results of this research indicate that the 4-factor structure of the 17 items of the Indonesian version of the CQS statement has a "good fit" psychometric property model. This means that the Indonesian adaptation of CQS can be used in various related research. It is hoped that future research will be able to test the convergent validity of the adaptation of this measuring instrument
Unraveling FOMO: Exploring the Factors Behind Fear of Missing Out among College Students
Full text linkThe increasing use of social media among college students can trigger mental health problems such as FOMO (Fear of Missing Out). There are not many studies that look at the relationship between the intensity of social media use and FOMO in college students. This study aims to provide an overview of FOMO among college students and assess the factors associated with FOMO. This quantitative study used a cross-sectional design with purposive sampling. Data collection was conducted through an online survey filled out by 104 college students. The variables measured were respondent characteristics, duration of social media use, number of social media accounts, and FOMO scale. The results of this study showed that 73.1% of students were classified as high duration users, 77.9% had less than 10 accounts, and 43.3% had high FOMO. There was a significant relationship between age (p=0.003) and undergraduate program (p=0.001) with FOMO. This study also found the significant relationship between duration (p=0.012) and number of accounts (p=0.007) with FOMO. There was a significant relationship between age, undergraduate program, duration, and number of accounts with FOMO in undergraduate students
Development of guided inquiry based e module on immune system to increase student argumentation
Full text linkThis study explores the development and effectiveness of guided inquiry-based e-modules focused on the immune system to enhance students' argumentation skills. Conducted at MAN Kota Tegal, the research adopts a Research and Development approach with the ADDIE development model. The study aims to determine the feasibility of creating these e-modules and assess their impact on students' argumentation skills. Data collected, both qualitative and quantitative, includes validation from subject matter, instructional design, and media experts, as well as feedback from teachers and students. The e-modules received high validation scores, with 97.5% from subject matter experts, 93.8% from instructional design experts, and 96.2% from media experts, indicating their credibility. Teacher feedback and student responses further supported the effectiveness, with approval rates of 75% and 87.1%, respectively. The N-gain test categorized the effectiveness as moderately effective, and paired sample t-tests revealed a significant improvement in students' argumentation skills, reaching the highest level 6 in the posttest with an average score of 78.83. Overall, the study highlights the potential of guided inquiry-based e-modules in enhancing students' argumentation skills related to the immune system
Ki Hajar Dewantara's thoughts on shaping the character of generation Z towards a golden Indonesia
Full text linkThe character of Generation Z is facing a significant decline in moral values, presenting the impression of being increasingly unruly. As the next generation responsible for advancing the nation toward a Golden Indonesia, this degradation affects various aspects, including speech, behavior, lifestyle, and education. Character education is currently in decline due to the dominance of media and the rapid progress of science and technology. The challenges facing Generation Z, characterized by the aspiration for a Golden Indonesia, demand a thoughtful approach to address these issues an approach found in the ideas of Ki Hajar Dewantara. This study aims to explore Ki Hajar Dewantara’s thoughts on shaping the character of Generation Z in alignment with the vision of a Golden Indonesia. The research adopts a literature review methodology, gathering data from various sources. The data collection technique involves documentation, specifically collecting relevant library resources. The study is conducted systematically, processing and synthesizing the data to provide conclusions based on the literature. The findings reveal that Ki Hajar Dewantara’s ideas focus on character development through the consideration of educational patterns, teacher and student roles, and methods for instilling character education values in future leaders aligned with the vision of a Golden Indonesia
Prediksi Tingkat Kepuasan Pelanggan Maskapai Penerbangan Menggunakan Decision Tree
Full text linkPenelitian ini mengkaji penerapan algoritma Decision Tree Regression dalam memprediksi tingkat kepuasan pelanggan maskapai penerbangan. Dengan menggunakan dataset yang relevan, model Decision Tree berhasil dibangun dan dievaluasi. Hasil penelitian menunjukkan bahwa Decision Tree merupakan alat yang efektif untuk menganalisis data pelanggan dan mengidentifikasi faktor-faktor yang mempengaruhi kepuasan pelanggan. Penelitian ini memberikan kontribusi pada pengembangan model prediksi dalam bidang ilmu data, khususnya dalam konteks industri penerbangan.
Impact of Feature Selection on XGBoost Model with VGG16 Feature Extraction for Carbon Stock Estimation Using GEE and Drone Imagery
Full text linkCarbon stocks are critical to climate change mitigation by capturing atmospheric carbon and storing it in biomass. However, carbon stock estimation faces challenges due to data complexity and the need for efficient analytical methods. This study introduces a carbon stock estimation method that integrates the XGBoost algorithm with VGG16 feature extraction and feature selection techniques to analyze GEE and Drone image datasets. The model is evaluated through four scenarios: without feature selection, using Information Gain, using Feature Importance, and using Recursive Feature Elimination. These scenarios aim to compare feature selection methods to identify the best one for processing complex environmental data. The experimental results show that RFE significantly outperforms other methods, achieving an average RMSE of 6651.62, MAE of 2297.57, and R² of 0.7673. These findings underscore the importance of feature selection in optimizing model performance, particularly for high-dimensional environmental datasets. RFE shows superior accuracy and efficiency by retaining the most relevant features but requires more computational resources. For applications that prioritize time and resource efficiency, Information Gain or Feature Importance can serve as a practical alternative with slightly reduced accuracy. This research highlights the value of integrating feature selection techniques into machine learning models for environmental data analysis. Future research could explore alternative feature extraction methods, combine RFE with other approaches, or apply advanced techniques such as Boruta or genetic algorithms. These efforts will further refine carbon stock estimation models, paving the way for broader applications in environmental data analysis
ANALISIS KESALAHAN DALAM MENYELESAIKAN SOAL MATERI LINGKARAN YANG DILAKUKAN OLEH SISWA SMP BERDASARKAN TAHAPAN KASTOLAN
Full text linkKemampuan siswa SMP dalam memahami konsep geometri masih tergolong rendah. Hal ini harus segera diatasi dikarenakan geometri memiliki kedudukan penting untuk diajarkan di sekolah mengingat bahwa konsep geometri sering dimanfaatkan dalam berbagai aspek kehidupan. Tujuan penelitian ini adalah untuk menganalisis kesalahan siswa dalam menyelesaikan soal lingkaran yang merupakan salah satu materi dalam konsep geometri. Penelitian ini menggunakan metode kualitatif yang melibatkan 30 siswa kelas 8 di salah satu SMP kota Bandung. Triangulasi dalam pengumpulan data meliputi (1) pemberian instrumen tes kemampuan pemahaman matematis siswa terkait materi lingkaran, dan (2) instrumen non tes yang meliputi pedoman observasi dan wawancara siswa, serta studi dokumen. Berdasarkan hasil temuan dan pembahasan pada penelitian ini, diperoleh informasi bahwa dalam menyelesaikan soal lingkaran, kesalahan siswa teridentifikasi dalam 2 bentuk kesalahan dari 3 kesalahan yang dapat dikategorikan melalui tahapan Kastolan yaitu kesalahan konseptual yang meliputi kesalahan dalam menentukan definisi juring, kesalahan dalam menentukan rumus panjang busur lingkaran, dan lain-lain; serta kesalahan prosedural yang meliputi kesalahan yang diakibatkan karena tidak teraturnya langkah-langkah pengerjaan soal, dan kesalahan yang diakibatkan karena ketidaktelitian siswa memahami soal dan dalam melakukan perhitungan