Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:The phenomenon of increasing attention toward environmental and sustainability issues has driven companies to improve information transparency, moving beyond mere financial reports to include non-financial disclosures. One…
ne form of this transparency is realized through website-based sustainability reporting, which allows companies to convey sustainability information more openly and accessibly to stakeholders. On the other hand, capital structure decisions remain a fundamental factor that can potentially influence market perceptions of firm value, as they relate to the balance between internal and external funding in supporting operational continuity and growth strategies. This study aims to determine the influence of website-based sustainability reporting and capital structure on firm value through multiple linear regression analysis. Using a quantitative approach and secondary data obtained from annual reports and official company websites, the study focuses on issuers consistently listed in the IDX ESG Leaders index during the 2023–2024 period. The sample selection utilized purposive sampling, resulting in 20 companies with a total of 40 data observations. Firm value was measured using the Tobin’s Q ratio, the level of sustainability reporting disclosure was proxied through the Sustainability Report Disclosure Index (SRDI) based on GRI 2021 standards, and capital structure was measured by the Debt to Equity Ratio (DER). The partial results of the study show that website-based sustainability reporting has a positive coefficient but no significant effect on firm value. Similarly, capital structure shows a positive direction but is not statistically significant. Furthermore, the two variables simultaneously have no significant effect on the firm value of IDX ESG Leaders issuers. These findings indicate that although website-based sustainability disclosure and capital structure tend to have a direct relationship with firm value, the influence is not yet strong enough to significantly affect market valuation within a group of issuers that already meet sustainability criteria. Consequently, the firm value of IDX ESG Leaders issuers is not solely determined by the level of website-based sustainability disclosure or the company's capital structure.
Abstract:This study aims to analyze the influence of Corporate Social Responsibility (CSR) disclosure on financial performance, with institutional ownership as a moderation variable. This research was conducted on companies that…
are members of the food and beverage sub-sector listed on the Indonesia Stock Exchange (IDX) during the 2021-2023 period using a quantitative approach. Sample selection was carried out by purposive sampling method, resulting in 39 samples of observation data for three consecutive years. The data analysis technique used is Structural Equation Modeling (SEM) which is operated through the WARP-PLS 7.0 program. The results of this study show that CSR has a positive but not significant effect on financial performance. Institutional ownership has a positive and significant effect on financial performance. Meanwhile, CSR moderated by institutional ownership has a positive and significant effect on financial performance.
Abstract:Sektor kelapa sawit menjadi penopang utama perekonomian Indonesia, termasuk di kawasan timur seperti Papua Selatan yang mulai berkembang sebagai wilayah penghasil sawit swadaya. Namun, perkembangan tersebut belum sepenuhnya…
nya diimbangi dengan tata kelola yang kuat dan penerapan sistem digitalisasi rantai nilai yang menjamin keberlanjutan serta transparansi. Sebagian besar petani sawit swadaya di Papua Selatan masih menghadapi kendala pada literasi digital, akses teknologi, kelembagaan yang lemah, serta belum adanya sistem ketertelusuran (traceability system) yang memenuhi standar keberlanjutan seperti Indonesian Sustainable Palm Oil (ISPO) dan European Union Deforestation Regulation (EUDR). Penelitian ini bertujuan menganalisis kesiapan petani sawit swadaya terhadap implementasi sistem pemetaan digital rantai nilai di Papua Selatan, dengan fokus pada tiga dimensi utama: kelembagaan lokal, kapasitas digital petani, dan dukungan kebijakan. Pendekatan penelitian menggunakan metode kualitatif deskriptif dengan teknik pengumpulan data melalui wawancara mendalam terhadap petani, aparat kampung, koperasi, dan dinas terkait di Kabupaten Merauke dan Boven Digoel, serta studi dokumentasi terhadap kebijakan daerah dan laporan keberlanjutan. Analisis data menggunakan model Miles dan Huberman (1994) yang meliputi reduksi data, penyajian data, dan penarikan kesimpulan. Hasil penelitian menunjukkan tingkat kesiapan digital petani masih tergolong rendah hingga sedang akibat minimnya literasi dan infrastruktur penunjang, namun terdapat potensi penguatan kelembagaan koperasi serta dukungan pemerintah daerah. Penelitian ini menawarkan kerangka kesiapan digital petani sawit berbasis konteks lokal Papua Selatan yang mengintegrasikan aspek kelembagaan, teknologi, dan kebijakan untuk mewujudkan sistem ketertelusuran berbasis komunitas yang inklusif dan berkelanjutan.
Abstract:Penelitian ini bertujuan untuk menganalisis bentuk kelembagaan dan model kolaborasi multi-pihak dalam pengelolaan sawit swadaya di Papua Selatan. Pengelolaan sawit swadaya memiliki potensi besar dalam meningkatkan kesejahteraan…
hteraan masyarakat lokal, namun dihadapkan pada tantangan kelembagaan yang lemah, rendahnya kapasitas petani, serta keterbatasan akses terhadap rantai pasok berkelanjutan. Metode penelitian yang digunakan adalah pendekatan kualitatif dengan teknik pengumpulan data melalui wawancara mendalam, observasi lapangan, dan studi dokumentasi. Hasil penelitian menunjukkan bahwa kelembagaan lokal memiliki peran penting sebagai penghubung antara petani, pemerintah daerah, dan pihak swasta. Model kolaborasi multi-pihak yang efektif ditandai oleh kejelasan peran, kepercayaan antar-aktor, serta komitmen terhadap prinsip keberlanjutan dan inklusivitas. Kajian ini merekomendasikan pembentukan kelembagaan koperasi berbasis digital (smart cooperative) yang mampu menjamin transparansi dan ketertelusuran (traceability) rantai nilai sawit swadaya di Papua Selatan.
Abstract:The palm oil industry plays a strategic role in Indonesia's economy, including in Merauke Regency, which is one of the developing palm oil plantation areas in Papua. However, challenges in production efficiency, environmental…
ental sustainability, and competitiveness remain obstacles in the industry's value chain. Innovation in various aspects of the value chain, such as productivity improvement through agricultural technology, processing efficiency, and product diversification based on palm oil, is a key factor in enhancing the industry's competitiveness. This study aims to analyze the role of innovation in the palm oil industry value chain in Merauke Regency by identifying the types of innovations applied and the factors that support or hinder their adoption. The research employs a qualitative approach, using data collection techniques such as in-depth interviews, observations, and document studies. The findings indicate that upstream sector innovations, such as the use of superior seedlings and digital plantation management, have improved productivity and efficiency. Meanwhile, downstream innovations in palm oil processing and value-added product diversification still face challenges, particularly in infrastructure and regulatory aspects. The study's implications suggest that optimizing innovation in the palm oil value chain requires more adaptive policies, increased investment in research and development, and capacity building for human resources. Thus, innovation can serve as a driving force in creating a more competitive, sustainable palm oil industry that contributes to local economic development in Merauke Regency.
Abstract:This study aims to analyze the influence of shipping cost efficiency and freight forwarder quality on export delivery performance at PT Sinar Sawit Sentosa, a palm oil exporting company facing challenges related to rising…
g logistics costs and increasing demands for delivery timeliness. The research problem focuses on the extent to which shipping cost efficiency and the quality of freight forwarder services can improve export delivery performance in a measurable and sustainable manner. A quantitative approach was applied by collecting survey data from the company’s logistics managers and export managers to capture perceptions and experiences related to the research variables. Data analysis was conducted using structural equation modeling to examine the causal relationships among shipping cost efficiency, freight forwarder quality, and export delivery performance. The results indicate that shipping cost efficiency has a positive and significant effect on export delivery performance through reduced operational costs, improved logistics coordination, and smoother export processes. Freight forwarder quality is also proven to have a positive and significant effect through enhanced service reliability, documentation accuracy, and delivery timeliness. The conclusion confirms that the combination of cost efficiency and logistics service quality constitutes a strategic factor determining the success of corporate export delivery. The novelty of this study lies in integrating the measurement of cost efficiency and freight forwarder quality using a SEM approach applied to the Indonesian palm oil export industry, a context that has received limited empirical attention. This contribution provides empirical evidence for the development of export logistics management and strategic decision-making, enriches the academic logistics literature, and offers practical implications for improving national export competitiveness, formulating corporate policies, and managing long-term logistics partnerships based on measurable performance and efficiency orientation. The findings are expected to serve as a reference for future research and professional practice in agribusiness sectors oriented toward global markets with high logistics risks and intense competition that demand continuous, data-driven managerial innovation grounded in reliable and context-specific empirical evidence for the future of national industries.
Abstract:Argo Mulyo adalah salah satu desa di kecamatan Bulik, Kabupaten Lamandau, Provinsi Kalimantan Tengah, Indonesia. Kecamatan Bulik, Kabupaten Lamandau, Provinsi Kalimantan Tengah merupakan desa yang memiliki luas wilayah 7.632,39…
ilayah 7.632,39 km².. Dari total luas wilayah tersebut,merupakan tegalan atau kebun yang sebagian besar ditanami kelapa sawit dan sayuran. Dengan luasnya tegalan atau kebun yang dimiliki oleh masyarakat sekitar banyak masyarakat yang memelihara unggas berupa ayam petelur sebagai mata pencarian disamping berkebun. Besarnya potensi unggas yang dihasilkan berdampak sama pengeluaran biaya pakan yang dikeluarkan oleh karena diperlukan pakan alternatif untuk mensiasatinya. Prospek penerapan inovasi dalam pakan alternatif untuk ternak unggas di desa Argamulya kabupaten Lamandau diharapkan mampu mengurangi faktor kendala keuangan peternak unggas dalam pembelian pakan kosentrat. Pakan alternatif dengan menggunakan fermentasi Azolla microphylla diharapkan dapat meningkatkan produktivitas ternak unggas sehingga didapatkan hasil daging dan telur yang berkualitas tinggi. Kegiatan pengabdian ini dilakukan dalam 2 sesi. Pada sesi pertama pemateri memfokuskan pada pemberian informasi mengenai Azolla microphylla, manfaatnya dan cara pembuatan pakan alternatif. Sesi berikutnya, fokus pada praktek pengaplikasian terhadap ayam petelur. Akhir kegiatan di dalam ruang adalah tanya jawab. Sementara untuk kegiatan di luar ruangan sesudah pelaksanaan praktik penerapan pakan alternatif pada ayam petelur. Dengan adanya pakan alternatif Azolla microphylla menjadikan masyarakat dapat melakukan penghematan akan pakan yang digunakan tanpa mengurangi kualitas.
Abstract:Teknologi otomasi telah berkembang pesat dan banyak diterapkan di berbagai bidang, termasuk pengelolaan sumber daya air. Salah satu aplikasi yang relevan adalah sistem otomatis penggerak mesin air, yang dirancang untuk meningkatkan…
eningkatkan efisiensi dan mempermudah pengelolaan suplai air. Saat ini, PT. Padasa Enam Utama, sebuah perusahaan perkebunan kelapa sawit, menghadapi kendala dalam pengoperasian manual mesin air, khususnya dalam mematikan pompa air saat tangki sudah penuh. Proses manual ini sering menyebabkan pemborosan air dan energi serta membutuhkan pengawasan yang intensif. Sistem otomatis penggerak mesin air yang dirancang menggunakan sensor, mikrokontroler, dan aktuator bertujuan untuk mengatasi masalah ini. Teknologi tersebut memungkinkan pemantauan real-time terhadap level air dan pengambilan keputusan otomatis tanpa campur tangan manusia. Sistem ini menawarkan berbagai manfaat, termasuk efisiensi energi, penghematan air, kemudahan penggunaan, dan keandalan tinggi dalam merespons perubahan kondisi. Proyek ini berfokus pada perancangan dan implementasi sistem yang handal dengan pendekatan berbasis sensor dan logika kontrol. Melalui solusi ini, diharapkan pengelolaan mesin air menjadi lebih efisien, hemat sumber daya, dan mendukung praktik keberlanjutan dalam pengelolaan air.
Abstract:Abstract: Palm oil is a key commodity that requires accurate production planning to support budget and operational efficiency. PT Buana Sawit Indah, a company managing palm oil plantations, faces challenges in forecasting…
g future production, necessitating a computerized forecasting system. This study aims to develop a forecasting system using the Single Exponential Smoothing (SES) and Single Moving Average (SMA) methods to predict palm oil production. The results indicate that both methods are effective; however, SMA with a Moving Average (MA) of 5 provides the best forecasting results, with a MAD of 165,941.64, an MSE of 65,823,372,491.27, and an MAPE of 15.66%, categorized as "good" forecasting. Meanwhile, the SES method with α = 0.9 yields the lowest error compared to other alpha values, with a MAD of 154,586.25, an MSE of 33,192,818,696.83, and an MAPE of 16.91%, also classified as "good" forecasting. Based on these findings, the SMA method with MA 5 is recommended as it produces lower forecasting errors than the SES method. Therefore, this forecasting system can assist the company in planning palm oil production more accurately and efficiently, supporting better decision-making in the future.
Keywords: palm oil; forecasting; production; single exponential smoothing; single moving average
Abstrak: Kelapa sawit merupakan komoditas utama yang memerlukan perencanaan produksi yang akurat untuk mendukung efisiensi anggaran dan operasional. PT Buana Sawit Indah, salah satu perusahaan yang mengelola perkebunan kelapa sawit, sedang menghadapi kesulitan dalam memperkirakan hasil produksi di masa mendatang, sehingga diperlukan sistem peramalan berbasis komputer. Penelitian ini bertujuan mengembangkan sistem peramalan menggunakan metode Single Exponential Smoothing (SES) dan Single Moving Average (SMA) untuk memprediksi produksi kelapa sawit. Hasil penelitian menunjukkan bahwa kedua metode cukup efektif, namun SMA dengan Moving Average (MA) 5 memberikan hasil peramalan terbaik dengan nilai MAD sebesar 165.941,64, MSE sebesar 65.823.372.491,27, dan MAPE sebesar 15,66%, yang dikategorikan sebagai peramalan “bagus.†Sementara itu, metode SES dengan α = 0,9 menunjukkan nilai kesalahan lebih rendah dibanding nilai alpha lain, dengan MAD sebesar 154.586,25, MSE sebesar 33.192.818.696,83, dan MAPE sebesar 16,91%, yang juga termasuk kategori peramalan “bagus.†Berdasarkan hasil tersebut, metode SMA dengan MA 5 lebih direkomendasikan karena menghasilkan tingkat kesalahan yang lebih rendah dibandingkan metode SES. Dengan demikian, sistem peramalan ini dapat membantu perusahaan dalam merencanakan produksi kelapa sawit secara lebih akurat dan efisien untuk mendukung pengambilan keputusan yang lebih baik di masa mendatang.
Kata kunci: kelapa sawit; peramalan; produksi; single exponential smoothing; single moving average