Recurrent Long-Short Term Memory-Deep Learning based Drug Consumption Analysis and Forecasting

Hadab Khalid Obayes

The provision of pharmaceutical drugs in quantities appropriate to consumption is an important point in the pharmaceutical industry and storage of medicines, as the production of large quantities of unnecessary drugs lead to the storage of drugs longer and that most medicines have a short shelf life. When the amount of production is less than what is required this affects the satisfaction of the customer and the marketing of the drug. Time series analysis is the appropriate solution to this problem. Deep learning has been adapted for the purpose of time series analysis and a prediction of the of required quantities drugs. Recurrent neural network with Long-Short Term Memory LSTM has been used by deep learning. The proposed methodology based on seasonal number of prescription required quantities and number of quarter as indicators. The aim of the research is to forecast drugs amount for one year. The proposed method is assessed using two types of evaluation. The first one based on MSE and visualization of the actual data and forecasting data. The proposed method has reached low value of MSE and the visualization graph is semi-identical, the second evaluation method is comparing the result of the proposed method with traditional forecasting method. Multiple linear regression traditional prediction method used with the data set, the results of the proposed method are good and promising compared to the results of the traditional method.

Volume 11 | 10-Special Issue

Pages: 742-751

DOI: 10.5373/JARDCS/V11SP10/20192865