Predicting the Spread of Covid-19 in Indonesia Using Machine Learning Models


  • Andi Maslan Universitas Putera Batam
  • Alfannisa Annurrallah Fajrin Universitas Putera Batam


covid-19, deep learning, neural network, support vector machine


This study aims to predict the end of covid-19 in Indonesia, by applying several methods from the prediction Support Vector Machine, Neural Network and Deep Learning concepts. Research conducted at the time the spread of Covid-19 in Indonesia was still increasing, this was seen based on the data on the spread that occurred very quickly, it was noted that in October 2020 there were daily cases and the community had carried out a lot of tests. So that in February 2020 there was a decrease in those exposed to Covid-19, but in July 2021 the daily cases continued to increase, there were 100,000 people exposed and the daily cases were also very high, at 60,000 people exposed to COVID-19. Based on this data, it is difficult to predict when the spread of COVID-19 in Indonesia will end, so this study aims to predict the increase in Covid-19 in Indonesia using three machine learning algorithms. The results show that the neural network can make predictions with an accuracy rate of 81.70%, precision of 88.70%, recall of 83.96%, while deep learning positional accuracy reaches 80%, and SVM level of 78.95%, precision of 88.39%, recall 78.87 %. so it can be concluded that covid-19 is still there and has not ended, while in 2022, it has decreased slightly, because people are starting to understand and follow the applicable Health protocols and the impact of Covid-19 in this study is that there will be an economic recession, health crisis and decrease in people's purchasing power


N. I. Widiastuti, E. Rainarli, and K. E. Dewi, “Summary and Support Vector Machine in Document Classification,” J. Infotel, vol. 9, no. 4, p. 416, 2017, doi:10.20895/infotel.v9i4.312.

H. A. Parhusip, “Study on COVID-19 in the World and Indonesia Using Regression Model of SVM, Bayesian Ridge and Gaussian,” J. Ilm. Science, vol. 20, no. 2, p. 49, 2020, doi:10.35799/jis.20.2.2020.28256.

A. Pertiwi, A. Triayudi, and E. T. E. Handayani, “Sentiment Analysis of the Impact of Covid-19 on Indonesia's Economy through Social Media Using the ANN Method,” J. Mantik, vol. 4, no. May, pp. 605–612, 2020.

D. T. Anantyo, A. A. Kusumaningrum, A. E. Rini, A. N. Radityo, K. B. Rahardjani, and G. I. Sarosa, “Coronavirus Disease 2019 (COVID-19) In Children (Literature Study),” Medica Hosp. J. Clin. Med., vol. 7, no. 1A, pp. 344–360, 2020, doi:10.36408/mhjcm.v7i1a.479.

M. Alazab, A. Awajan, A. Mesleh, A. Abraham, V. Jatana, and S. Alhyari, “COVID-19 prediction and detection using deep learning,” Int. J. Comput. inf. syst. eng. Manag. Appl., vol. 12, no. June, pp. 168–181, 2020.

A. Karim, "Comparison of Poverty Predictions in Indonesia Using the Support Vector Machine (SVM) with Linear Regression," J. Sains Mat. and Stat., vol. 6, no. 1, 2020, doi:10.24014/jsms.v6i1.9259.

E. dwi nurindah Sari, "Analysis of Customer Sentiment in Banking Services Using Binary Logistics Regression Method, Naïve Bayes Classifier (NBC), and Support Vector Machine (SVM)," J. Its Science And Art, vol. 8, no. 2, p. 177, 2019.

H. Putra and N. Ulfa Walmi, “Applying Prediction of Rice Production Using Artificial Neural Network Backpropagation Algorithm,” J. Nas. Technol. and Sis. Inf., vol. 6, no. 2, pp. 100–107, 2020, doi:10.25077/teknosi.v6i2.2020.100-107.

S. Aisyah Fany Achmalia, Walid, “Back-Propagation Neural Network Dan,” vol. 9, no. 8, pp. 6–21, 2000.

S. Divineyah and A. Nilogiri, "Implementation of Deep Learning in Identification of Plant Types Based on Leaf Image Using Convolutional Neural Network," JUSTINDO (Jurnal Sist. dan Teknol. Inf. Indones., vol. 3, no. 2, pp. .49–56, 2018.

Y. A. Hasma and W. Silfianti, “Implementation of Deep Learning Using Tensorflow Framework with Faster Regional Convolutional Neural Network Method for Acne Detection,” J. Ilm. Technol. and Engineering, vol. 23, no. 2, pp. 89–102, 2018, doi:10.35760/tr.2018.v23i2.2459.