Implementasi Metode Promethee Dalam Menentukan Calon Penerima Bantuan PKH Berbasih Web (Studi Kasus: Desa Tengguli Kecamatan Sajad)

Mohani,; Suhery, Cucu; Ristian, Uray

doi:10.26418/coding.v8i2.41496

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While test data is used to assess and evaluate the performance of the model discovered at the testing stage, train data is used to instruct the algorithm on how to develop a suitable model. As was done in reference to earlier research journals, the distribution of the number of train data and test data in this study uses a percentage of 70:30 [23]. In tests that use a dataset of 30% testing data and 70% training data, the accuracy value can reach 90.33% [24].…”

Section: Methodsmentioning

confidence: 91%

Comparison of Machine Learning Algorithms for Classification of Ultraviolet Index

Syahab

Widiyanto

Anuggilarso

et al. 2023

J. teknol. inf. pendidik.

View full text Add to dashboard Cite

Indonesia is a tropical climate country which has the potential for high intensity of sunlight exposure. Several types of exposure that receives are ultraviolet rays. According to the National Agency for Meteorology, Climatology and Geophysics, it provides information regarding the impact on human activities in an ultraviolet index which has a risk scale. The aim of this research was creating a recommender system based on the ultraviolet index category in providing daily activity advice to users. The methods used the K-nearest Neighbor algorithm and Support Vector Machine with a Collaborative Filtering Model-Based approach that could recommend items based on the results of a model trained to identify input data patterns. The stages carried out in this study included data collection, data pre-processing, data division into test data and train data, dataset testing, analysis of the results of models that had been trained in the accuracy values using the algorithm tested. The results of the confusion matrix calculation produced test evaluations in accuracy values, precision values, and recall values. The comparison of result had the highest performance in K-nearest Neighbor with an accuracy value of 99.69%, a precision value of 99.00%, and a recall value of 96.20%. In research used the Support Vector Machine showed the lowest performance with an accuracy value of 97.91%, a precision value of 93.20%, and a recall value of 86.40%.

show abstract

Section: Methodsmentioning

confidence: 91%