Claim Missing Document
Check
Articles

Found 37 Documents
Search

Optimisasi Penilaian Kinerja Karyawan PT. Tolan Tiga Indonesia Estate Perlabian Dengan Algoritma C4.5 Sipahutar, Rizka Nurfatni; Munthe, Ibnu Rasyid; Juledi, Angga Putra
Jurnal Informatika Vol 12, No 2 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i2.5677

Abstract

In the face of fierce competition in the current global era, companies are required to prepare and always adjust their strategies to the changes that occur so that the company remains able to compete and survive. Employees who are in a company are workers which is the most important asset that must be owned and indispensable in the company and of course must be considered by all parties in order to create good performance as well as have goals to be achieved in the assessment of employee performance at PT. There Are Three Types Of Indonesian Real Estate. Employee performance appraisal in the company is seen as the driving force of the company because human resources play an active role in the running of an organization or company and the decision-making process. Machine learning tools used in predicting the assessment, using the C4.5 algorithm, the data obtained is more accurate. Machine learning is an artificial intelligence that can process data that is useful for consideration in making decisions and solving problems. C4.5 algorithm is one of the algorithms in data mining that serves to classify a class. This algorithm is a development of the ID3 algorithm. How the C4.5 algorithm works by forming a decision tree to produce a decision.
Implementation of Stacking Technique Combining Machine Learning and Deep Learning Algorithms Using SMOTE to Improve Stock Market Prediction Accuracy Munthe, Ibnu Rasyid; Rambe, Bhakti Helvi; Hanum, Fauziah; Amanda, Ade Trya; Hutagaol, Anita Sri Rejeki; andrianto, Richi
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.421

Abstract

This study introduces a stacking technique that integrates machine learning (ML) and deep learning (DL) algorithms to enhance the accuracy of stock market trend predictions. The stacking model utilizes XGBoost and Random Forest as base models from the ML domain, while Logistic Regression and LSTM (Long Short-Term Memory) function as meta models to optimize predictive accuracy. A significant challenge in stock market data is class imbalance, where certain trends, such as stock price drops, are underrepresented. To mitigate this, we applied the Synthetic Minority Over-sampling Technique (SMOTE) to generate synthetic data for the minority class. This approach helps the model better capture patterns from the underrepresented data while preserving essential information from the majority class. The implementation of SMOTE, coupled with the stacking technique, yielded a substantial improvement in prediction accuracy. The results showed that the Random Forest algorithm achieved an accuracy of 85% with precision, recall, and F1-score all at 85%, while XGBoost and Logistic Regression achieved accuracies of 82% and 81% respectively. For the deep learning models, LSTM reached an accuracy of 83%, while the Stacking Meta Model with LSTM achieved an accuracy of 83% with slightly better precision and recall at 84%. The stacking model, with Logistic Regression as the meta model, ultimately achieved the highest accuracy of 86%, outperforming individual models such as SVM (Support Vector Machine), LSTM, Random Forest, and Logistic Regression (LR). These findings demonstrate the efficacy of combining SMOTE with stacking to address data imbalance and improve stock market predictions. The novelty of this study lies in the integration of advanced ML and DL models within a stacking framework to handle class imbalance in financial datasets. Future research will explore the deployment of this model in a real-time web-based application to support investor decision-making in stock market trend analysis.
Optimalisasi dan Strategi Penjualan Baju Thrifting Melalui Implementasi E-commerce CMS PrestaShop di Jalan Sigambal Rantauprapat Ardiansyah, Sandi; Harahap, Syaiful Zuhri; Munthe, Ibnu Rasyid
Journal of Computer Science and Information System(JCoInS) Vol 5, No 4: JCoInS | 2024
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v5i4.6813

Abstract

Abstract This study aims to explore effective digital marketing strategies for enhancing thrift clothing sales in the era of information technology. With the rapid development of technology and increasing market competition, businesses that previously relied solely on social media platforms like Instagram now need to adapt by utilizing more professional e-commerce platforms. This research compares specific thrift platforms with websites using CMS Prestashop in attracting consumer attention. The methods employed include observation, interviews, and literature reviews, aiming to understand the interaction patterns between sellers and buyers, as well as the operational dynamics within thrift businesses. The findings are expected to provide valuable insights for entrepreneurs in formulating more effective digital marketing strategies, thereby increasing competitiveness and sustainability in an increasingly competitive market.
SISTEM PENDUKUNG KEPUTUSAN PENERIMAAN PEGAWAI BIRO AKADEMIK MENGGUNAKAN MOOSRA Pertiwi, Nur Fajar Kurnia; Munthe, Ibnu Rasyid; Sihombing, Volvo
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1538

Abstract

This study aims to design and develop a decision support system (DSS) for the employee selection process at the academic bureau of Labuhan Batu University using the MOOSRA method. The main issue faced is the use of subjective and non-standardized traditional selection methods, which can reduce the accuracy and efficiency in selecting the right candidates. The method applied in this study is MOOSRA, which can process various selection criteria such as educational qualifications, work experience, information technology skills, communication skills, and discipline. The results of the calculation of values ​​and rankings indicated that alternative A4 was the best candidate, followed by A9 and A1. The results of the study indicate that the use of the MOOSRA method in the decision support system can provide more objective and efficient recommendations in the employee selection process at the academic bureau of Labuhan Batu University.
SISTEM PENDUKUNG KEPUTUSAN PENILAIAN KINERJA APARATUR DESA DENGAN METODE TOPSIS Tiara, Dewi; Munthe, Ibnu Rasyid; Sihombing, Volvo
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1543

Abstract

This study aims to develop a decision support system based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method to evaluate the performance of village officials more objectively, quickly, and accurately at the Bagan Sari Village Office, South Labuhan Batu Regency. The main problem faced is that the assessment of the performance of officials is still carried out manually, which has the potential to produce subjective and inconsistent data. This study uses a quantitative approach with the following stages: determining criteria and weights, collecting data, and processing data using the TOPSIS method. The criteria used include discipline, attendance, cooperation, and loyalty. The results of the study indicate that the TOPSIS-based system can produce village official performance ratings with high accuracy, minimize bias, and accelerate the decision-making process. This system is expected to be able to provide strategic guidance for the Village Head in improving the quality of service and motivating officials to improve their performance. The implementation of this technology is also a strategic step in modernizing village governance.
SISTEM PENDUKUNG KEPUTUSAN PENERIMA BANTUAN JAMKESDA MENGGUNAKAN METODE WASPAS Sitompul, Joni Awendri; Munthe, Ibnu Rasyid; Sihombing, Volvo
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1539

Abstract

Jamkesda is a program that is more focused on the poor with the same service coverage as BPJS PBI (Penerima Bantuan Iuran). This program managed by the local government reaches poor people who are not registered with BPJS or Jamkesmas or who need additional health support at the regional level. One of the main challenges in implementing Jamkesda is determining who is entitled to receive benefits from this program, the recipient selection process must be based on clear and objective criteria, such as income, occupation, age, health conditions, and ownership of a Certificate of Inability to Pay (SKTM). To overcome this, a decision support system is used to facilitate the objective assessment process, namely the Weighted Aggregated Sum Product Assessment (WASPAS). This study obtained a final matrix result that was more significant than other alternatives with a value of 0.65498> 0.57926 which indicates A001> from A007 and is more significant than other alternatives.
Evaluasi Sistem Informasi Manajemen Risiko untuk Pengendalian Proyek IT di Perusahaan Besar Lumban Gaol, Tid Verawati; Munthe, Ibnu Rasyid; Sihombing, Volvo
Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan Vol. 4 No. 2 (2025): Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan
Publisher : Utiliti Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/justikpen.v4i2.143

Abstract

Evaluasi Sistem Informasi Manajemen Risiko (SIMR) dalam pengendalian proyek IT di perusahaan besar sangat penting untuk memastikan keberhasilan proyek dan meminimalkan potensi kerugian. SIMR berfungsi sebagai alat yang membantu mengidentifikasi, menganalisis, dan mengelola risiko yang mungkin muncul sepanjang siklus hidup proyek IT. Penelitian ini bertujuan untuk mengevaluasi efektivitas penerapan SIMR dalam proyek IT pada perusahaan besar dengan fokus pada kemampuan sistem dalam mendukung identifikasi risiko, mitigasi risiko, serta pelaporan risiko secara real-time. Selain itu, evaluasi dilakukan terhadap sejauh mana SIMR dapat membantu meningkatkan pengambilan keputusan, mempercepat respons terhadap risiko, serta mengurangi dampak negatif yang mungkin timbul terhadap anggaran, jadwal, dan kualitas proyek. Metode yang digunakan dalam penelitian ini mencakup studi kasus dan wawancara dengan pihak-pihak terkait di perusahaan besar yang telah mengimplementasikan SIMR, serta analisis data kuantitatif mengenai performa proyek. Hasil evaluasi menunjukkan bahwa sistem ini mampu meningkatkan efisiensi pengelolaan risiko, kolaborasi antar tim, dan transparansi dalam pelaporan risiko. Namun, terdapat beberapa tantangan dalam hal integrasi dengan sistem lain, penyesuaian dengan dinamika proyek IT yang cepat berubah, dan kebutuhan akan komitmen manajemen dalam penggunaan sistem ini. Rekomendasi dari penelitian ini meliputi peningkatan fitur otomatisasi dan interoperabilitas, penguatan kebijakan internal terkait manajemen risiko, serta pelatihan yang lebih intensif bagi tim proyek IT terkait penggunaan SIMR. Dengan demikian, SIMR dapat lebih efektif dalam mendukung pengendalian proyek IT di perusahaan besar, meningkatkan peluang keberhasilan proyek, dan mengurangi risiko kegagalan
Analisis Keberhasilan Implementasi Sistem CRM Berbasis Cloud di Industri Perbankan Rusmiana, Rusmiana; Sihombing, Volvo; Munthe, Ibnu Rasyid
Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan Vol. 4 No. 2 (2025): Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan
Publisher : Utiliti Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/justikpen.v4i2.144

Abstract

Penelitian ini bertujuan untuk menganalisis keberhasilan implementasi Customer Relationship Management (CRM) berbasis cloud di industri perbankan, khususnya dalam meningkatkan kepuasan pelanggan dan efisiensi operasional. Masalah utama yang dihadapi adalah resistensi internal dari karyawan, keterbatasan infrastruktur teknologi sebelumnya, serta kurangnya pelatihan terkait penggunaan teknologi baru. Penelitian ini menggunakan pendekatan kuantitatif dengan survei yang melibatkan 150 responden dari berbagai level manajemen di bank yang telah mengimplementasikan sistem CRM berbasis cloud. Data yang dikumpulkan dianalisis menggunakan model Technology Acceptance Model (TAM) dan metode statistik deskriptif. Hasil penelitian menunjukkan bahwa faktor kemudahan penggunaan, kepercayaan terhadap keamanan data, dan dukungan manajemen berperan signifikan dalam keberhasilan implementasi sistem ini. Sistem CRM berbasis cloud terbukti mampu meningkatkan efektivitas pelayanan pelanggan hingga 35% dan mengurangi biaya operasional sebesar 20%. Studi ini memberikan rekomendasi bagi bank untuk meningkatkan investasi pada pelatihan karyawan dan keamanan data guna memastikan keberlanjutan sistem
PEMBERDAYAAN UMKM DESA AFDELING 1 RANTAUPRAPAT MELALUI PEMASARAN DIGITAL, KEMASAN, DAN INOVASI PRODUK Munthe, Ibnu Rasyid; Fitriandika Sari, Novi; Helvi Rambe, Bhakti; Gulo, Nur'ainun; Trya Amanda, Ade; Rasyid Munthe, Shabrina
Jurnal Masyarakat Berdikari dan Berkarya (Mardika) Vol 3 No 1 (2025): Jurnal Masyarakat Berdikari dan Berkarya (MARDIKA)
Publisher : Fakultas Teknik, Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/mardika.v3i1.11684

Abstract

The community service activity conducted in Afdeling 1 Village, Rantau Prapat, aimed to enhance the capacity of Micro, Small, and Medium Enterprises (UMKM) through training in three important aspects: digital marketing, packaging design, and product innovation. The main problems faced by local UMKM included marketing limited to the local market, unattractive product packaging, and a lack of product innovation. The methods used in this activity included training on the use of social media and e-commerce platforms for digital marketing, training on attractive and professional packaging design, and the development of new product variations to increase competitiveness. The results of the activity showed a significant increase, with 90% of UMKM actors now utilizing digital marketing, 80% of products experiencing improved packaging design, and 75% of UMKM actors successfully developing new products. The positive impacts of this activity included increased UMKM income, expanded market reach, and increased consumer confidence in the products offered. Overall, this activity successfully empowered UMKM to compete better in a wider market and contributed to local economic empowerment in Afdeling 1 Village, Rantau Prapat. The sustainability of this program requires further mentoring and support from various parties so that UMKM can continue to grow and be competitive
Implementasi Data Mining Algoritma Apriori untuk Meningkatkan Penjualan Harist N, Abdul; Munthe, Ibnu Rasyid; Juledi, Angga Putra
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 6 No. 1 : Tahun 2021
Publisher : LPPM UNIKA Santo Thomas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54367/jtiust.v6i1.1276

Abstract

Setiap perusahaan atau organisasi yang ingin bertahan perlu menentukan strategi bisnis yang tepat. Data penjualan produk yang dilakukan oleh Lakoe Dessert Pondok Kacang pada akhirnya akan menghasilkan data yang menumpuk, sehingga sangat disayangkan jika tidak dianalisis kembali. Produk yang ditawarkan bervariasi dengan variasi produk sebanyak 45 produk, untuk mengetahui produk yang paling banyak penjualannya dan keterkaitan antara produk yang satu dengan produk yang lain diperlukan salah satu algoritma dalam algoritma data mining yaitu apriori algoritma untuk mengetahuinya, dan dengan bantuan aplikasi Rapidminer 5, dengan nilai dukungan 2,4% dan nilai kepercayaan 50%, produk yang sering dibeli atau diminati pelanggan dapat ditemukan. Penelitian ini menggunakan data penjualan bulan Maret 2020 yang berjumlah 209 data transaksi. Dari penelitian tersebut, ditemukan item dengan nama Pudding Strawberry dan Pudding Vanilla merupakan produk yang paling banyak dibeli oleh konsumen. Dengan mengetahui produk yang paling banyak terjual dan pola pembelian barang yang dilakukan oleh konsumen, Lakoe Dessert Pondok Kacang dapat mengembangkan strategi pemasaran untuk memasarkan produk lain dengan menganalisis keuntungan dari penjualan produk yang paling banyak terjual dan mengantisipasi kehabisan atau kosongnya stok atau bahan pada suatu saat. tanggal kemudian