syaputra, muhammad andrea (2025) PREDIKSI KEBERHASILAN USAHA MICRO KECIL MENENGAH (UMKM) BERBASIS WEB MENGGUNAKAN METODE REGRESSI LOGITIC DAN RANDOM FOREST. S1 thesis, universitas malikussaleh.

	Text cover.pdf Download (215kB)
	Text Abstrak.pdf Download (275kB)
	Text bab1.pdf Download (293kB)
	Text daftarpustaka.pdf Download (229kB)
	Text Muhammad Andrea Syaputra_210180112 (1).pdf Restricted to Registered users only Download (16MB)

Abstract

Micro, Small, and Medium Enterprises (MSMEs) are one of the main pillars supporting national economic growth in Indonesia. MSMEs play an essential role in absorbing labor, creating new job opportunities, and promoting equitable economic development across various regions. Their contribution not only increases community income but also strengthens economic resilience, especially during times of crisis. Despite these significant contributions, the failure rate of MSMEs has increased in recent years. This is due to several factors, such as limited capital, poor financial record-keeping, weak business strategies, lack of proper business planning, and insufficient experience in managing and developing a business.In response to these challenges, this research aims to develop a web-based MSME success prediction system that can assist business owner9s in estimating the likelihood of their business success more accurately. The system applies machine learning methods, namely Logistic Regression and Random Forest, to process data and generate predictions. The dataset used in this study was obtained from the Kaggle platform, consisting of 250 records containing important information about MSME characteristics, such as initial capital, financial records, business planning, and the use of digital technology.The evaluation results show that the Logistic Regression model achieved an accuracy of 94%, while the Random Forest model reached 90%. Based on these findings, the Logistic Regression model was selected for implementation in the web application. In addition to the prediction feature, the system also provides learning videos designed to enhance MSME owners’ knowledge and skills. With this application, it is expected that MSME owners can make better business decisions, increase their competitiveness, and improve their chances of success in the long term.

Item Type:	Thesis (S1)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Divisions:	Fakultas Teknik > 57201 - Jurusan Sistem Informasi
Depositing User:	andre syaputra
Date Deposited:	19 Sep 2025 07:50
Last Modified:	19 Sep 2025 07:50
URI:	https://rama.unimal.ac.id/id/eprint/15121

Actions (login required)

View Item