Advertisement

Forecast in the Pharmaceutical Area – Statistic Models vs Deep Learning

  • Raquel Ferreira
  • Martinho Braga
  • Victor Alves
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 747)

Abstract

The main goal of this work was to evaluate the application of statistical and connectionist models for the problem of pharmacy sales forecasting. Since R is one of the most used software environment for statistical computation, we used the functions presented in its forecast package. These functions allowed for the construction of models that were then compared with the models developed using Deep Learning algorithms. The Deep Learning architecture was constructed using Long Short-Term Memory layers. It is very common to use statistical models in time series forecasting, namely the ARIMA model, however, with the arising of Deep Learning models our challenge was to compare the performance of these two approaches applied to pharmacy sales. The experiments studied, showed that for the used dataset, even a quickly developed LSTM model, outperformed the long used R forecasting package ARIMA model. This model will allow the optimization of stock levels, consequently the reduction of stock costs, possibly increase the sales and the optimization of human resources in a pharmacy.

Keywords

ARIMA Deep Learning Forecast LSTM Pharmacy sales 

Notes

Acknowledgments

This work has been supported by COMPETE: POCI-01-0145-FEDER-007043 and FCT – Fundação para a Ciência e Tecnologia within the Project Scope: UID/CEC/00319/2013.

References

  1. 1.
    Yousefi, N., Alibabaei, A.: Information flow in the pharmaceutical supply chain. Iran. J. Pharm. Res. 14(4), 1299–1303 (2015)Google Scholar
  2. 2.
    Microsoft: Business Intelligence for Healthcare : The new prescription for boosting Cost Management, Productivity and Medical Outcomes. Business Intelligence for Healthcare: The New Prescription for Boosting Cost Management, Productivity and Medical Outcomes. BusinessWe, February 2009Google Scholar
  3. 3.
    Ashrafi, N., Kelleher, L., Kuilboer, J.-P.: The impact of business intelligence on healthcare delivery in the USA. Interdiscip. J. Inf. 9(9), 117–130 (2014)Google Scholar
  4. 4.
    Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice, pp. 46–51. OTexts, Australia (2014)Google Scholar
  5. 5.
    Shumway, R.H., Stoffer, D.S.: Time Series Analysis and Its Applications, 3rd edn. Springer, Heidelberg (2017)CrossRefzbMATHGoogle Scholar
  6. 6.
    Ohri, A.: Why every business analyst needs to learn R? (2012). http://analyticstraining.com/2012/why-every-business-analyst-needs-to-learn-r/. Accessed 01 June 2017
  7. 7.
    Verma, E.: A Quick Guide to R Programming Language for Business Analytics (2015). https://www.simplilearn.com/r-programming-language-business-analytics-quick-guide-article. Accessed 01 June 2017
  8. 8.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  9. 9.
    Deng, L., Yu, D., Deep Learning : Methods and Applications (2013)Google Scholar
  10. 10.
    Russakovsky, O.: Convolutional Neural Networks for Visual Recognition (2015)Google Scholar
  11. 11.
    Olah, C.: Understanding LSTM Networks (2015)Google Scholar
  12. 12.
    Alahi, K., Goel, V., Ramanathan, A., Robicquet, Fei-Fei, L., Savarese, S.: Social LSTM : Human Trajectory Prediction in Crowded Spaces (2014)Google Scholar
  13. 13.
    Zaytar, M.A., El Amrani, C.: Sequence to sequence weather forecasting with long short-term memory recurrent neural networks. Int. J. Comput. Appl. 143(11), 975–8887 (2016)Google Scholar
  14. 14.
    May, M.: An Overview of Python Deep Learning Frameworks (2017)Google Scholar
  15. 15.
    Community, S.: SciPy Reference Guide (2015)Google Scholar
  16. 16.
    TensorFlow: https://www.tensorflow.org/. Accessed 01 Nov 2017
  17. 17.
    Keras: https://keras.io/. Accessed 01 Nov 2017
  18. 18.
    Brownlee, J.: Deep Learning With Python. https://machinelearningmastery.com/deep-learning-with-python/. Accessed 18 June 2017
  19. 19.
    Steinberg, D.: Why Data Scientists Split Data into Train and Test (2014). http://info.salford-systems.com/blog/bid/337783/Why-Data-Scientists-Split-Data-into-Train-and-Test. Accessed 11 June 2017
  20. 20.
    Hyndman, R.J.: New in forecast 4.0 (2012). https://robjhyndman.com/hyndsight/forecast4/. Accessed 12 June 2017
  21. 21.
    Brownlee, J.: How to Normalize and Standardize Time Series Data in Python (2016). http://machinelearningmastery.com/normalize-standardize-time-series-data-python/. Accessed 18 June 2017
  22. 22.
    Dieterle, D.F.: Overfitting, Underfitting and Model Complexity (2016)Google Scholar
  23. 23.
    Wesner, J.: MAE and RMSE — Which Metric is Better? (2016). https://medium.com/human-in-a-machine-world/mae-and-rmse-which-metric-is-better-e60ac3bde13d. Accessed 15 June 2017
  24. 24.
    Mukaka, M.M.: Statistics corner: a guide to appropriate use of correlation coefficient in medical research. Malawi Med. J. 24(3), 69–71 (2012)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of InformaticsUniversity of MinhoBragaPortugal
  2. 2.Tlantic Portugal SIPortoPortugal
  3. 3.Algoritmi CentreUniversity of MinhoBragaPortugal

Personalised recommendations