International Journal of Scientific Research and Engineering Development

International Journal of Scientific Research and Engineering Development


( International Peer Reviewed Open Access Journal ) ISSN [ Online ] : 2581 - 7175

IJSRED » Archives


Submit Your Manuscript OnlineIJSRED

Drug Sales Forecasting with Metadata and ACF Supported LSTM



    International Journal of Scientific Research and Engineering Development (IJSRED)

Full Text:
pdf

Published Issue : Volume-3 Issue-6
Year of Publication : 2020
Unique Identification Number : IJSRED-V3I6P4
Authors : Volkan Demir, Dogan Tilkici, Metin Zontul
: Click Here


Abstract :

Data stored based on time in the form of seconds, minutes, hours, days, years is called time series. The process of predicting future values using time series is called time series forecasting. One of the common time series forecasting method is Long short-term memory (LSTM) which is an artificial recurrent neural network (RNN) with feedback connections in the field of deep learning. In this study, he forecasting models are constructed on weekly drug sales time series data by using a combination of Metadata, ACF and LSTM. Metadata is produced based on the time points with an error rate compared with a threshold value in training. ACF is used to determine he stationary status of the data and LSTM is used for drug sales time series forecasting.