Abstract:This research aims to apply the Naïve Bayes method to determine the eligibility of receiving the Smart Indonesia Program (PIP) at the 017107 Kisaran Naga State Elementary School by analyzing 207 student data. The CRISP-DM…
DM approach was used through six stages: business understanding, data understanding, data preparation, modeling, evaluation, and implementation. The variables analyzed included means of transportation, KPS and KIP recipients, worth a pip, reasons for eligibility, number of siblings, distance from home to school, and parents' income.
The results showed that this method achieved 89% accuracy, 85% precision for the positive class, and 92% for the negative class. A total of 125 students (59.9%) were declared eligible to receive assistance, while 82 students (40.1%) did not meet the criteria. The Naïve Bayes method is effective in supporting decision-making for the provision of targeted educational assistance
Abstract:Education plays an important role in improving the quality of human life, but economic constraints often prevent many students from continuing their education. The Smart Indonesia Program (PIP) was launched to address these…
ese issues by providing educational assistance. However, in its implementation, the selection of PIP recipients at IT Al-Ikhsan Private Junior High School is still inaccurate. This research aims to classify the eligibility of PIP recipients using the Naive Bayes method. This method is applied to student data from the school's Dapodik in 2024 which consists of 265 students. The data is processed through CRISP-DM data mining stages, namely Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. As a result, the Naive Bayes model showed an accuracy of 92.31% with a precision value for the “Yes” class of 89%, recall 100%, and F1-score 94%. In conclusion, variables such as means of transportation, KPS and KIP recipients, parents' income, and distance from home to school affect the eligibility of PIP recipients.
Abstract:The development of information technology provides solutions for increasing efficiency and accuracy in decision-making, such as in determining students eligible for BLT at SD Swasta IT ABI Husni. This study aims to implement…
ment the Naive Bayes algorithm to support a more objective BLT recipient selection process. The method used is CRISP-DM, starting from understanding the problem, data preparation, to model implementation. The data analyzed included type of residence, KPS recipients, parents' income, KIP recipients, number of siblings, distance from home and reasons for eligibility for BLT used were data from students of SD Swasta IT ABI Husni in the odd semester of 2024/2025, with a total of 137 data. The results of the study showed that the Naive Bayes algorithm was able to achieve an accuracy level of 98% with precision and recall of up to 100%, proving the effectiveness of the model in minimizing classification errors. In conclusion, the use of the Naive Bayes algorithm can help make decisions that are more targeted, transparent, and fair in the distribution of BLT.
Abstract:This research is motivated by the large number of prospective students who simply choose a major when they want to enter a vocational school without considering their abilities. The Decision Tree or C45 method is used because…
cause it is able to make decision trees that are easy to describe, and has a level of efficiency in handling discrete and numeric attribute data. While the Naive Bayes method is used because it has a high accuracy of results. This research was conducted based on data from students of SMK Muhammadiyah 10 Kisaran which contained questions about feelings of wrong majors, interests, and determinants of other majors. Data is divided into 2 labels, namely free labels (y) and bound labels (x). Followed by dividing the dataset into training data and testing data with a ratio of 70:30 in both methods to get the level of accuracy. From the results given, it can be seen that the C45 algorithm has an accuracy of 85% and the Naive Bayes algorithm has an accuracy of 26%. This shows that the C45 algorithm is more effective in classifying the available datasets compared to the Naive Bayes.
Abstract:Graduation marks the completion of a certain level of schooling. This study aims to predict the graduation of students at SDN 016528 BP Mandoge based on their abilities. The goal of this research is to reduce the rate of…
student failure to graduate by making predictions based on examination scores collected by the institution. The method used in this study is Naive Bayes, a technique in Data Mining that utilizes probability and statistics to predict future outcomes based on previous data. This method was chosen due to its advantage in predicting graduation rates from concrete data, ensuring the results are reliable and applicable for future predictions. The dataset used in this study includes graduation data for SDN 016528 BP Mandoge students for the 2019/2020 academic year, comprising 171 students, with 120 students used for training data and 51 students for testing data, achieving a model accuracy of 98%.
Abstract:Everbright has become one of the distributing companies selling various products, one of which is the Dettol product. In optimizing the stock and marketing of Dettol products, the company faces difficulties in identifying…
g the best-selling products and those less favored by customers. This research data originates from the sales transaction data of Dettol soap in November, comprising 77 sales data. Through the use of data mining, particularly the K-means Clustering method, it becomes a relevant approach to solving this issue. The objective of this research is to avoid excess inventory that remains unsold while meeting the diverse needs of customers. The results of this study show the visualization of the distribution of Dettol soap product clusters and grouping based on sales levels. There were 21 best-selling item data, 31 well-selling item data, and 25 less popular item data, enabling the company to manage inventory based on the best-selling items.
Abstract:The Self-Help Housing Stimulant Assistance (BSPS) is a government house renovation program aimed at low-income communities. This program aims to enhance self-sufficiency in construction and improve the quality of houses,…
facilities, infrastructure, and public utilities through the principle of mutual cooperation. BSPS recipients must meet several criteria, such as income, house ownership status, house size, floor type, wall type, roof type, and water source. To address issues based on these criteria, Data Mining techniques using the Naive Bayes method were employed. This study utilized a dataset of BSPS recipients in Air Genting Village, Air Batu Sub-district, comprising 88 samples. The classification results from applying Naive Bayes yielded a precision value of 84%, a recall value of 81%, an F1-score of 82%, and an accuracy of 81%. The objective of this research is to facilitate the classification of eligible and rightful recipients of government assistance in the form of BSPS. The results of this study are expected to provide an alternative solution in determining BSPS recipients in Air Genting Village, Air Batu Sub-district
Abstract:The use of smartphones in Indonesia has been steadily increasing each year. In the era of the Fourth Industrial Revolution, smartphones have become a lucrative business sector, leading to intense market competition. Consequently,…
equently, smartphone companies must pay closer attention to the market segmentation desired by consumers. Data mining is the process of discovering significant relationships and patterns by analyzing large datasets using statistical and mathematical techniques. This study aims to identify and analyze the market segments of Android smartphone users among students at STMIK Royal. The data used in this research were collected from 122 student respondents. The study employs clustering using the K-means algorithm. The resulting data modeling will categorize market segments into several clusters. This segmentation yields three clusters: Cluster 1 (features), consisting of 36 respondents who prioritize price, battery, camera, and warranty; Cluster 2 (product), with 49 respondents who value all attributes except warranty; and Cluster 3 (superiority), comprising 37 respondents who prioritize camera, brand, and RAM.
Abstract:The independent curriculum provides opportunities for educators and students at SMP Muhammadiyah 51 Sidikalang to obtain information. Non-formal education can be obtained by participating in various activities, one of which…
ich is socialization outside of school. This socialization provides additional knowledge, it turns out that mathematics and biology can be connected, for example regarding learning Biomathematics which can help model populations from the spread of disease, in this case the model for the spread of Covid-19. The aim of this event is so that educators and students can apply and model the spread of disease and read real phenomena through data. The method used in this event is assistance which helps in explaining the modeling of the Covid-19 disease and analyzing the data so that conclusions can be drawn on the spread of the population so that the spread can be stopped. The results of this event were that 85% of educators and students were able to take part in this socialization by being able to form and model in a simple way the formation of disease models both by analyzing data.
Abstract:The purpose of this research is to determine the effect of using the Group Investigation model on the ability to write book reviews at XIth Class of SMK Taman Siswa Suka Damai. The population in this study are all XIth class…
lass students, totaling 127 students. The sample in this research is XIth class Accounting which are taken using a simple random sampling technique totaling 22 students. The data collection technique uses a performance test in writing a book review. Based on the research results, at the pretest the average score obtained was 66.1 and at the posttest 90.31. The significant value obtained is greater than ttable, namely tcount > ttable, namely 80.7>1.68 and 80.7>2.41. This proves that Ho is rejected and Ha is accepted, namely that there is a significant influence from the use of the Group Investigation model on the ability to write book reviews in class.