Start-ups have a very important role in economic growth, the existence of a start-up can open up many new jobs. However, not all start-ups that are developing can become successful start-ups. This is because start-ups have a high failure rate, data shows that 75% of start-ups fail in their development. Therefore, it is important to classify the successful and failed start-ups, so that later it can be used to see the factors that most influence start-up success, and can also predict the success of a start-up. Among the many classifications in data mining, the Decision Tree, kNN, and Naïve Bayes algorithms are the algorithms that the authors chose to classify the 923 start-up data records that were previously obtained. The test results using cross-validation and T-test show that the Decision Tree Algorithm is the most appropriate algorithm for classifying in this case study. This is evidenced by the accuracy value obtained from the Decision Tree algorithm, which is greater than other algorithms, which is 79.29%, while the kNN algorithm has an accuracy value of 66.69%, and Naive Bayes is 64.21%.
The increase in the use of motorized vehicles increases air pollution conditions, especially in big cities such as the capital city of Indonesia, Jakarta. The pollution that pollutes this city contains various kinds of chemical particles that are harmful to living things when they enter the body. several efforts to reduce this pollution have been carried out, one of which is by identifying the pollutants contained in the air. This study uses data obtained from monitoring stations to predict the content of pollutants in the air at some time in the future. the method used is data mining forecasting with a neural network model. by using rapid miner obtained several graphic descriptions of pollutant conditions in Jakarta that go up and down. pollutant levels of SO2, CO, PM10 and NO2 all increased in the November-December period and at the same time period, ozone was at its lowest point. Results from Prediction air quality using Artificial Neural Network with 5 parameters, shown on this pollutant PM10 had an RMSE of 9,477; SO2 had an RMSE 5,474; CO had an RMSE 8,392; O3 had an RMSE 18,250; NO2 had an RMSE 5,171. Can be concluded that the RMSE value of O3 is higher than the others and the lowest value of NO2.
Perbedaan pemahaman di kalangan masyarakat sering terjadi terkait diterbitkannya kebijakan baru oleh pemerintah. Diantaranya adalah kebijakan dalam menangani kasus kekerasan seksual di lingkungan kampus yang tertulis dalam Peraturan Menteri Pendidikan, Kebudayaan, Riset dan Teknologi Nomor 30 Tahun 2021 sehingga diperlukan kajian mendalam dengan melakukan analisis sentimen. Ada banyak algoritma yang digunakan dalam penelitian analisis sentimen, maka dalam penelitian ini peneliti menggunakan 4 algoritma klasifikasi machine learning, yaitu Support Vector Machine, K-Nearest Neighbor, Naïve Bayes Classifier, dan Logistic Regression untuk dilakukan perbandingan performa dari masing-masing algoritma. Data penelitian yang digunakan berjumlah 470 data dengan pembagian 236 tweet berlabel positif dan 238 tweet berlabel negatif yang diambil pada rentang bulan Oktober sampai Desember. Dalam penelitian ini menggunakan perangkat lunak RapidMiner dengan menerapkan teknik k-Fold Cross Validation untuk memisahkan data latih dan data uji secara acak. Terdapat perbedaan performa pada algoritma machine learning yang digunakan untuk analisis sentimen, dari algoritma yang telah diujikan, nilai akurasi tertinggi terdapat pada algoritma Support Vector Machine, yaitu sebesar 69,15%, kemudian nilai presisi tertinggi terdapat pada algoritma K-Nearest Neighbor, sebesar 69,07%, kemudian nilai recall tertinggi terdapat pada algoritma Support Vector Machine sebesar 71,98%, dan nilai f-measure tertinggi terdapat pada algoritma K-Nearest Neighbor yaitu sebesar 68,08%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.