News and Announcements
ARTICLE
Drug sales forecasting in the pharmaceutical market using deep neural network algorithms
Show Less
1
Department of Computer Science, Applied Science Private University, Amman,
Jordan
2
Department of Data Science, Princess Sumaya University for Technology, Amman,
Jordan
IJOSI 2024 , 8(3), 63–83;
https://doi.org/10.6977/IJoSI.202409_8(3).0006
Submitted: 21 September 2023 | Revised: 8 January 2024 | Accepted: 29 February 2024 | Published: 30 December 2024
© 2024 by the Author(s). Licensee AccScience Publishing, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract
Drug sales and price forecasting have become an attractive investigation topic due to their important role in the pharmaceutical industry, A sales forecast helps every business to make better business decisions in overall business planning, budgeting, marketing,and risk management. The traditional forecasting method focuseson a conven-tional statistical model, which highly depends on the availability of historical sales data. However, for new drug entities, where not enough historical data is available, new methods of Machine Learning are applied. The aim of this paper is toidentify an efficient Deep Neural Network algorithm suitable to forecast drug sales and pricing by applying Deep Neural Network Algorithms such as Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory, which are expected to perform well on this issue. The results are carried out to deter-mine the efficiency of these algorithms by evaluating the performances of the models using MAE and RMSE performance metrics to identify the best algorithm for Drug Sales and Price Forecasting. The accepted accuracy should be more than 80\% of the actual value for quantity which is less than three thousand by unit and less than two dollars(USD) for price, Based on the results of the experiments Long Short Term Memory performed better than MLP and CNN for generating predictions with average Root Mean Square Error of for sales is 1.28(k) and Mean Absolute Error of about 0.85(k), and with average Root Mean Square Error for USD Prices is about 0.75, and Mean Absolute Error is about 0.44. The forecasts are then used to adjust stock levels according to the predic-tions.
Keywords
Drug sales Forecasting
Multilayer Perceptron
Convolutional Neural Network
Long Short-Term Memory
References
- Andrawis, R. R., Atiya, A. F., & El-Shishiny, H. (2011). Forecast combinations of computational intelligence and linear models for the NN5 time series forecast-ing competition. International Journal of Forecasting,27(3), 672–688. https://doi.org/10.1016/J.IJFORE-CAST.2010.09.005
- Aras, S., & Kocakoç, T. D. (2016). A new model selec-tion strategy in time series forecasting with artificial neural networks: IHTS. Neurocomputing, 174, 974–987. https://doi.org/10.1016/J.NEU-COM.2015.10.036
- Benidis, K., Sundar Rangapuram, S., Flunkert, V., Re-search, A., Yuyang Wang, G., Maddix, D., Caner Turkmen, U., Gasthaus, J., Bohlke-schneider, M., Salinas, D., Stella, L., Aubet, F., Callot, L., Wang, Y., Turkmen, C., Bohlke-Schneider, M., Aubet, F.-X., Turkmen, C., Gasthaus, J., ... Maddix, D. (2022). Deep Learning for Time Series Forecasting: Tutorial and Literature Survey. ACM Computing Surveys, 55(6). https://doi.org/10.1145/3533382
- Bing, L., Chan, K. C. C., & Ou, C. (2014). Public senti-ment analysis in twitter data for prediction of a com-pany’s stock price movements. Proceedings -11th IEEE International Conference on E-Business Engi-neering, ICEBE 2014 -Including 10th Workshop on Service-Oriented Applications, Integration and Col-laboration, SOAIC 2014 and 1st Workshop on E-Commerce Engineering, ECE 2014, 232–239. https://doi.org/10.1109/ICEBE.2014.47
- Boyapati, S. N., & Mummidi, R. (2020). Predicting sales using Machine Learning Techniques. https://www.diva-por-tal.org/smash/get/diva2:1455353/FULLTEXT02
- Dai, J., Zhang, P., Mazumdar, J., Harley, R. G., & Ve-nayagamoorthy, G. K. (2008). A comparison of MLP, RNN and ESN in determining harmonic con-tributions from nonlinear loads. IECON Proceedings (Industrial Electronics Conference), 3025–3032. https://doi.org/10.1109/IECON.2008.4758443
- Ding, X., Zhang, Y., Liu, T., & Duan, J. (n.d.). Deep Learning for Event-Driven Stock Prediction.
- Doganis, P., Alexandridis, A., Patrinos, P., & Sarimveis, H. (2006). Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing. Journal of Food Engineering, 75(2), 196–204. https://doi.org/10.1016/J.JFOODENG.2005.03.056
- Ensafi, Y., Amin, S. H., Zhang, G., & Shah, B. (2022). Time-series forecasting of seasonal items sales using machine learning –A comparative analysis. Interna-tional Journal of Information Management Data In-sights, 2(1), 100058. https://doi.org/10.1016/J.JJIMEI.2022.100058
- García, S., Ramírez-Gallego, S., Luengo, J., Benítez, J. M., & Herrera, F. (2016). Big data preprocessing: methods and prospects. Big Data Analytics 2016 1:1, 1(1), 1–22. https://doi.org/10.1186/S41044-016-0014-0
- Hernández, E., Sanchez-Anguix, V., Julian, V., Palanca, J., & Duque, N. (2016). Rainfall prediction: A deep learning approach. Lecture Notes in Computer Sci-ence (Including Subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), 9648, 151–162. https://doi.org/10.1007/978-3-319-32034-2_13/COVER
- Hossen, T., Plathottam, S. J., Angamuthu, R. K., Ranga-nathan, P., & Salehfar, H. (2017). Short-term load forecasting using deep neural networks (DNN). 2017 North American Power Symposium, NAPS 2017. https://doi.org/10.1109/NAPS.2017.8107271
- Islek, I., & Oguducu, S. G. (2015). A retail demand fore-casting model based on data mining techniques. IEEE International Symposium on Industrial Elec-tronics, 2015-September, 55–60. https://doi.org/10.1109/ISIE.2015.7281443
- Ji, S., Yu, H., Guo, Y., & Zhang, Z. (2016). Research on sales forecasting based on ARIMA and BP neural network combined model. ACM International Con-ference Proceeding Series. https://doi.org/10.1145/3028842.3028883
- Kamruzzaman, J., Sarker, R. A., & Begg, R. (1 C.E.). Artificial Neural Networks: Applications in Finance and Manufacturing. Https://Services.Igi-Global.Com/Resolvedoi/Re-solve.Aspx?Doi=10.4018/978-1-59140-670-9.Ch001, 1–27. https://doi.org/10.4018/978-1-59140-670-9.CH001
- Kim, K. H., Lee, C. S., Jo, S. M., & Cho, S. B. (2016). Predicting the success of bank telemarketing using deep convolutional neural network. Proceedings of the 2015 7th International Conference of Soft Com-puting and Pattern Recognition, SoCPaR 2015, 314– 317. https://doi.org/10.1109/SOCPAR.2015.7492828
- Kraus, M., & Feuerriegel, S. (2017). Decision support from financial disclosures with deep neural networks and transfer learning. Decision Support Systems, 104, 38–48. https://doi.org/10.1016/J.DSS.2017.10.001
- Lakner, Z., Kiss, A., Popp, J., Zéman, Z., Máté, D., & Oláh, J. (2019). From Basic Research to Competi-tiveness: An Econometric Analysis of the Global Pharmaceutical Sector. Sustainability 2019, Vol. 11, Page 3125, 11(11), 3125. https://doi.org/10.3390/SU11113125
- Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transac-tions of the Royal Society A, 379(2194). https://doi.org/10.1098/RSTA.2020.0209
- Mehdiyev, N., Lahann, J., Emrich, A., Enke, D., Fettke, P., & Loos, P. (2017). Time Series Classification us-ing Deep Learning for Process Planning: A Case from the Process Industry. Procedia Computer Sci-ence, 114, 242–249. https://doi.org/10.1016/J.PROCS.2017.09.066
- Processing, N. A.-F. in S., & 2017, undefined. (2017). Neural networks for financial market risk classifica-tion. Isaac-Scientific.ComN AbroyanFrontiers in Signal Processing, 2017•isaac-Scientific.Com, 1(2). https://doi.org/10.22606/fsp.2017.12002
- Sci, A. S.-S. U. D. C., & 2014, undefined. (n.d.). Con-volutional networks for stock trading. Cs231n.Stan-ford.EduA SiripurapuStanford Univ Dep Comput Sci, 2014•cs231n.Stanford.Edu. Retrieved Septem-ber 21, 2023, from http://cs231n.stanford.edu/re-ports/2015/pdfs/ashwin_final_paper.pdf
- Siami-Namini, S., & Namin, A. S. (2018). Forecasting Economics and Financial Time Series: ARIMA vs. LSTM. https://arxiv.org/abs/1803.06386v1
- Taylor, D. (2015). The pharmaceutical industry and the future of drug development. Pharmaceutical in the Environment. https://pubs.rsc.org/en/content/chap-terhtml/2015/9781782622345-00001?isbn=978-1-
- Tiriveedhi, V. (2018). Impact of Precision Medicine on Drug Repositioning and Pricing: A Too Small to Thrive Crisis. Journal of Personalized Medicine 2018, Vol. 8, Page 36, 8(4), 36. https://doi.org/10.3390/JPM8040036
- Wang, C. H., & Yun, Y. (2020). Demand planning and sales forecasting for motherboard manufacturers considering dynamic interactions of computer prod-ucts. Computers & Industrial Engineering, 149, 106788. https://doi.org/10.1016/J.CIE.2020.106788
- Wang, Z., & Lou, Y. (2019). Hydrological time series forecast model based on wavelet de-noising and ARIMA-LSTM. Proceedings of 2019 IEEE 3rd In-formation Technology, Networking, Electronic and Automation Control Conference, ITNEC 2019, 1697–1701. https://doi.org/10.1109/IT-NEC.2019.8729441
- Yeasmin, N., Amin, S. H., & Tosarkani, B. M. (2022). Machine Learning Techniques for Grocery Sales Forecasting by Analyzing Historical Data. 21–36. https://doi.org/10.1007/978-3-030-85383-9_2
- Zhang, S., Zhang, C., & Yang, Q. (2003). Data prepara-tion for data mining. Applied Artificial Intelligence, 17(5–6), 375–381. https://doi.org/10.1080/713827180
