Prediction of Education Level in Population Data Using Naïve Bayes Algorithm
| Autor: | Pungkas Subarkah, Siti Alvi Solikhatin, Irma Darmayanti, Ali Nur Ikhsan, Debby Ummul Hidayah, Rayinda Maya Anjani |
|---|---|
| Rok vydání: | 2022 |
| Zdroj: | TIERS Information Technology Journal. 3:69-75 |
| ISSN: | 2723-4541 2723-4533 |
| DOI: | 10.38043/tiers.v3i2.3865 |
| Popis: | Education is the key to improving human resources. The Ministry of National Education is implementing a curriculum that requires students to study it (MoNE) and as part of this program, all Indonesian citizens are required to attend three years of primary education, which includes SD, MI/Equivalent, three years for SMP/Equivalent, and three years for high school/equivalent level. This study aims to determine whether or not a government program that requires Indonesian citizens to study for 12 years is required, therefore it is necessary to test predictions of data on the level of education in Blitar Regency. This study conducted a prediction test by implementing the Naive Bayes algorithm on education-level data in Blitar Regency as of 2020 which was taken from the satudata.go.id website. In the data processing, there are values of precision, recall, f-measure, Weighted Avg, and also Confusion Matrix. The accuracy results of the Naive Bayes Algorithm on education level data in Blitar district show that the district has implemented government policies regarding the 12-year compulsory education program, this is based on the results of data processing which shows an accuracy value of 98.4848% and category good classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|