Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Foristek Owner : Riset dan Jurnal Akuntansi Jurnal Ilmiah Intech : Information Technology Journal of UMUS Jurnal Algoritma
Dessy Santi
Jurusan Teknologi Informasi, Fakultas Teknik, Universitas Tadulako, Palu
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Implementasi Naïve bayes Clasifier dalam Klasifikasi Jenis Berita Dessy Santi; Jumadil Nangi; Natalis Ransi
Foristek Vol. 10 No. 1 (2020): Foristek
Publisher : Foristek

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (362.383 KB) | DOI: 10.54757/fs.v10i1.52

Abstract

Sometimes the classification of news categories is still an obstacle. Classification can be wrong because it is still subjective. As a result, the selected category does not match the uploaded news description. Based on these problems, the authors feel the need to make Classification of News Types with the Naïve Bayes Classifier Algorithm. The importance of this system is to be able to classify news and help news seekers to get the news they want. Based on the test results, the Naïve Bayes Classifier algorithm has a good performance for the classification of news types. This is evidenced in testing using news data taken from www.kompasiana.com, then news is classified into four categories namely politics, economics, sports, and entertainment. The classification results using 16 test news obtained an accuracy of 87.5%.
Sistem Informasi Pengarsipan Surat-Surat Pada PT Sinergi Perkebunan Nusantara Dessy Santi; Meri Kristina Tongkuru
Jurnal Teknik Informatika UMUS Vol 2 No 01 (2020): Mei
Publisher : Universitas Muhadi Setiabudi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (808.206 KB) | DOI: 10.46772/intech.v2i01.186

Abstract

Pengelolaan surat dalam suatu organisasi memegang peranan penting dalam proses administrasi. Dalam hal ini sistem tata persuratan menjadi salah satu faktor yang berpengaruh dalam pengelolaan surat. Pada PT. Sinergi Perkebunan Nusantara,Pengelolaan surat masuk dan surat keluar dilakukan secara manual mulai dari pencatatan surat, proses pencarian, dan penyimpanan yang membutuhkan waktu dan biaya yang tidak efektif dan efisien. Sistem informasi pengarsipan adalah solusi dari permasalahan ini. Sistem informasi Pengarsipan ini juga memudahkan proses komunikasi data antar bagian. Sistem informasi ini dibuat dengan menggunakan PHP sebagai bahasa pemrograman , MySQL sebagai database dengan menngunakan Metode Rapid Application Development (RAD). Hasil dari penelitian ini adalah sebuah sistem informasi pengarsipan yang memberikan banyak kemudahan dalam proses pengelolaan surat surat termasuk pencarian surat, disposisi surat serta pendokumentasian dan pengarsipan surat-surat
CLUSTERING DAERAH TERDAMPAK SAMPAH DI INDONESIA MENGGUNAKAN ALGORITMA DBSCAN. Santi, Dessy; Maharani, Wulan; Syahrullah, Syahrullah; Nugraha, Deny Wiria; Mukhlis, Baso; Kali, Agustinus
Foristek Vol. 15 No. 1 (2025): Foristek
Publisher : Foristek

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54757/fs.v15i1.751

Abstract

The waste problem in Indonesia is a complex and evolving environmental issue, particularly in areas with high population density and economic activity. This study aims to cluster regions affected by waste issues using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. DBSCAN was chosen for its ability to identify spatial patterns and detect outliers without requiring a predefined number of clusters. The data used includes spatial and non-spatial information related to waste volume and regional characteristics across various provinces in Indonesia. The results show that DBSCAN effectively groups waste-affected areas into several clusters based on data density and spatial proximity. These clusters can serve as a foundation for determining policy priorities for regional and national waste management. This research is expected to contribute to the development of more targeted and data-driven waste management strategies.
Dinamika Kebijakan Dividen Pasca-Pandemi: Studi Empiris pada Perusahaan Manufaktur di Indonesia Arisanti, Dessy; Burhanudin, Burhanudin
Owner : Riset dan Jurnal Akuntansi Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/owner.v10i1.2942

Abstract

This study examines the dynamics of dividend policy in manufacturing companies listed on the Indonesia Stock Exchange during the post-pandemic period of 2020–2024. Using panel data regression analysis, 40 manufacturing firms were selected through purposive sampling and analyzed using Eviews 12 software. Empirical evidence on corporate dividend policy behaviour in the post-pandemic period, particularly in developing countries, is still limited and shows inconsistent results. The results show that leverage and profitability have a negative and significant effect on dividend policy. This finding contradicts the signalling theory perspective and is important because it indicates that in the post-pandemic period, manufacturing companies in Indonesia prioritise profit retention to strengthen financial resilience and support reinvestment rather than using dividends as a performance signal. Furthermore, the negative and significant influence of leverage indicates that the higher a company's dependence on debt-based financing, the more limited its ability to distribute dividends to shareholders. Meanwhile, collateral assets, free cash flow, and investment opportunity set did not show a significant influence. The main contribution of this study lies in confirming that the relationship between profitability and dividend policy is contextual and not universal, especially in post-crisis emerging markets. In practical terms, the results of this study have implications for investor and company managers in evaluating the sustainability of dividends in uncertain economic conditions.
Implementation of Long Short-Term Memory Algorithms on Cryptocurrency Price Prediction with High Accuracy on Volatile Assets Nursiana Zasqia, Andi Nirina; Laila, Rahmah; Trezandy Lapatta, Nouval; Yazdi Pusadan, Mohammad; Santi, Dessy; Wirdayanti
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2422

Abstract

Cryptocurrencies have emerged as one of the most popular digital assets, characterized by high volatility, which presents a significant challenge in forecasting their price movements accurately. This study aims to implement the Long Short-Term Memory (LSTM) algorithm to predict the prices of selected cryptocurrencies, including Bitcoin (BTC), Binance Coin (BNB), Ethereum (ETH), Dogecoin (DOGE), Solana (SOL), and Shiba Inu (SHIB). The LSTM model is trained using the Adam optimizer and employs early stopping to mitigate overfitting. Model performance is evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²). The results indicate that the LSTM model achieves strong predictive accuracy for relatively low-volatility assets such as Dogecoin and Solana, with R² scores of 0.9795 and 0.9523, respectively. In contrast, its performance declines when applied to highly volatile assets like Bitcoin and Binance Coin. The findings also suggest that LSTM performs best in short-to-medium-term forecasts (7 to 30 days), but shows limitations in long-term predictions. This study contributes to the field by demonstrating the applicability of LSTM in financial forecasting and highlighting its strengths and constraints across different volatility profiles. Practically, the findings can assist traders and financial analysts in making data-driven decisions by applying LSTM models for more reliable short-term predictions, while emphasizing the need to integrate external market factors to enhance long-term forecast accuracy.
Co-Authors Agustinus Kali Baso Mukhlis Burhanudin Burhanudin Deny Wiria Nugraha Jumadil Nangi Maharani, Wulan Meri Kristina Tongkuru Mohammad Yazdi Pusadan Natalis Ransi Nouval Trezandy Lapatta Nursiana Zasqia, Andi Nirina Rahmah Laila Syahrullah Syahrullah Wirdayanti