Analysis of Sales Vitamins Drugs Covid-19 Pandemic with the Random Forest Method
Article Sidebar
Main Article Content
Abstract
During the covid-19 pandemic that occurred in Indonesia until the new normal period, consumer demand for a vitamin drug was fast and unpredictable, thus making pharmacies must be able to plan the optimal supply of vitamin drugs based on the graph of public demand during the pandemic and new normal. This means that the pharmacy does not experience a shortage of stock or excess stock. Therefore, all systems that can predict sales of vitamin drugs are needed during the new normal pandemic. To be able to make predictions, an appropriate method is needed to get accurate results. One of them is the Random Forest method. With Random Forest, the data is predicted based on attribute data so as to produce a conclusion about the value of the desired attribute. Based on this study, 200 sales data of vitamin drugs were taken during the pandemic and new normal with categories of vitamin B complex drugs, vitamins C, D, E, K and Multivitamins and the attributes used were vitamin brand, category, sales conditions, price and sales category. and doesn't work. The test results from this study, it was found that the prediction of vitamin drug sales during the new normal pandemic using the Random Forest method obtained 100% accuracy for testing data with a composition of 80:20, 70:30 and 60:40, so that vitamin drugs would still be sold in new normal.
Downloads
Article Details
[2] Jatmiko. Y.A., Padmadisastra.S., & Chadidjah.A. (2019), Comparative Analysis of the Performance of Cobentional Carts, Bagging and Random Forests on Ojek Classification: Results From Two Simulations, Journal of Media Statistics, vol.12, no.1, pp.1-12.
[3] Samudra, A. Y. (2019). Random Forest Approach for Forecasting Models of Cut Tobacco Prices in Temanggung Regency. Yogyakarta: Thesis.
[4] Sandag. (2020), App Store App Rating Prediction Using the Random Forest Algorithm, Cigito Smart Journal, vol.6, no.2, pp.167-178.
[5] Siburian. V.W., & Mulyana. I.E. (2018). Cellphone Price Prediction Using the Random Forest Method, Annual Research Seminar, vol.4, no.1, pp.144-147.
[6] Nugroho. Y. S. (2017), Variable Classification System for Consumer Acceptance of Cars Using the Random Forest Method, vol. 9, no. 1, p.6
[7] Dhawangkhara. M., & Riksakomara. E. (2017), Surabaya City Rain Intensity Prediction with Matlab using Random Forest and CART Techniques (Surabaya City Case Study), ITS Engineering Journal, vol. 6, no. 1.
[8] Byna. A. (2017), Comparative Analysis of the C.45 Algorithm, Random Forest With Chaid Decision Tree for Classification of Anxiety Levels of Pregnant Women, p. 6.
[9] Haristu, R. A. (2019). Application of the Random Forest Method to Predict the Win Ratio of Player Unknown Battleground Players. Yogyakarta: Thesis.
[10] Ceh, M. M. (2018). Estimating the Performance of Random Forest Versus Multiple Regression for Predicting Prices of the Apartments. International Journal of Geo-Information, 2 and 14.
[11] Chen, C. L. (2017). Comparative Analysis of Used Car Price Evaluation Models.
[12] AIP Conference Proceedings, 1-6.
[13] Destiadi, R. (2015). The Success of Photography in Representing a Leader. Design Journal. 2(2), 61-116.
[14] Hasan, M. A. (2015). Feature Selection for Intrusion Detection Using Random Forest. Journal of Information Security, 133-134.
[15] Hasyasin, Y. N. (2017). The Influence of Product Quality and Price on Consumer Purchase Decisions. Bandung: Thesis.
[16] Rohmawati, et al, "The Prediction System for the Number of Tourist Visitors Wego Kec. Sugio Kab. Lamongan Using the Fuzzy Time Series Method", JOUTICLA, Vol. 3, No.2, pp.67-74, 2017.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.