Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal INTERNATIONAL JOURNAL OF SOCIETY REVIEWS (INJOSER) INTERNATIONAL JOURNAL OF FINANCIAL ECONOMICS (IJEFE)
Agus Iskandar
Universitas Nasional, Indonesia
Religion Humanities Economics, Econometrics & Finance Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
COMPARISON OF DECISION TREE AND RANDOM FOREST ALGORITHMS IN PREDICTING STUDENT GRADUATION BASED ON ACADEMIC DATA Marlan Marlan; Ahmad Rifqi; Agus Iskandar
INTERNATIONAL JOURNAL OF SOCIETY REVIEWS Vol. 3 No. 3 (2025): MARCH
Publisher : Adisam Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research aims to compare the performance of the Decision Tree and Random Forest algorithms in predicting student graduation based on academic data. By utilizing data such as Grade Point Average (GPA), the number of credit hours, and course grades, this study focuses on analyzing the accuracy of both algorithms in predicting students who are at risk of not graduating on time. The results of the study indicate that the Random Forest algorithm achieves higher accuracy compared to the Decision Tree, particularly in terms of recall and precision. While Decision Tree is simpler and easier to interpret, it tends to have overfitting issues that can affect prediction results. In contrast, Random Forest overcomes these issues by producing more stable predictions through an ensemble process. This study is expected to contribute to the development of student graduation prediction systems in educational institutions. As such, institutions can use these findings as a foundation for designing intervention strategies for students at risk of not graduating on time.
LOCAL SHOE SELECTION DECISIONS WITH A DECISION SUPPORT SYSTEM USING THE SIMPLE ADDITIVE WEIGHTING METHOD Tio Adi Kurniawan; Agus Iskandar
INTERNATIONAL JOURNAL OF SOCIETY REVIEWS Vol. 1 No. 9 (2024): INTERNATIONAL JOURNAL OF SOCIETY REVIEWS (INJOSER)
Publisher : Adisam Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Shoes are a basic need that is very essential in everyday life. provides protection, comfort and adaptability to a variety of activities and environments. (Juliana iHutapea iet ial., i2018) However, when choosing shoes, the task can become quite complicated considering the many choices and factors that need to be considered. In Indonesia, there are many local shoe brands, each with its own characteristics and appeal. The diversity of shoe models available often creates confusion for buyers, who are looking for shoes that suit their needs and preferences. (Mario i& iLero, in.d.) To overcome this challenge, this research aims for the same. to develop a decision support system designed to provide assistance to buyers in choosing shoes. This research involves three main criteria, namely price, comfort, and quality, which are considered key factors in carrying out the decision-making process. purchasing shoes. By applying the Simple Additive Weighting (SAW) method (Apriani iet ial., i2020), this research attempts to produce weights for each criterion and provide a ranking of shoes that could be the right choice. Thus, this decision support system is expected to have the ability to provide advice or recommendations. shoes that suit customers' needs and preferences, helping them overcome the confusion in choosing among the various shoe models available in the market.
DATA MINING CUSTOMER CLUSTERING USING K-MEANS METHOD Agus Iskandar; Rifqi Aldy Al Hafizh Harahap; Achmad Gilang Ramadhan
INTERNATIONAL JOURNAL OF FINANCIAL ECONOMICS Vol. 1 No. 12 (2025): INTERNATIONAL JOURNAL OF FINANCIAL ECONOMICS (IJEFE)
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The company recognizes the crucial role of customers in achieving business success and as the main source of revenue. Therefore, it is important for companies to understand the needs and desires of customers in order to build a mutually beneficial relationship. Customers have functional and emotional needs that they want to fulfill through the products or services they buy. Customer experience, both positive and negative, has a significant impact on satisfaction, loyalty and corporate image. This research faces the challenge of decreasing the number of customers who make purchases at these companies or service providers. To overcome this problem, companies need to adopt an effective market strategy to improve operational efficiency and better understand customer needs. One approach used is to understand customer needs through grouping, so that companies can develop products or services that are more suitable for each customer group. This helps improve the product's relationship with customer needs and provides services that match their expectations. Customer grouping was performed using the K-means algorithm, with 47 customers grouped based on relevant attributes. Determining the optimal number of clusters is done by comparing the performance of the clusters that are formed, and the results produce two new clusters with different numbers of customers. The K-means algorithm is implemented using the RapidMiner application to simplify the process. The final analysis shows that the second cluster has more customers than the first cluster. This research confirms the importance of understanding customer needs, classifying them appropriately, and taking effective actions to maintain customer satisfaction. The K-means algorithm and the RapidMiner application prove to be very useful in this process, enabling companies to strengthen customer relationships and create significant added value. The final results of this study indicate that the first cluster (cluster 0) contains 22 customers, while the second cluster (cluster 2) contains 25 customers. Therefore, the second cluster has a larger number of customers compared to the first cluster.
Co-Authors Achmad Gilang Ramadhan Ahmad Rifqi Marlan Marlan Rifqi Aldy Al Hafizh Harahap Tio Adi Kurniawan