Enhancing Predictive Accuracy in Pharmaceutical Sales Through an Ensemble Kernel Gaussian Process Regression Approach

Authors: Shahin Mirshekari, Mohammadreza Moradi, Hossein Jafari, Mehdi Jafari, Mohammad Ensaf

Abstract:

This research employs Gaussian Process Regression (GPR) with an ensemble kernel, integrating Exponential Squared, Revised Matérn, and Rational Quadratic kernels to analyze pharmaceutical sales data. Bayesian optimization was used to identify optimal kernel weights: 0.76 for Exponential Squared, 0.21 for Revised Matérn, and 0.13 for Rational Quadratic. The ensemble kernel demonstrated superior performance in predictive accuracy, achieving an R² score near 1.0, and significantly lower values in MSE, MAE, and RMSE. These findings highlight the efficacy of ensemble kernels in GPR for predictive analytics in complex pharmaceutical sales datasets.

Keywords: Gaussian Process Regression, Ensemble Kernels, Bayesian Optimization, Pharmaceutical Sales Analysis, Time Series Forecasting, Data Analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.12602880

References:

[1] S. R. Dutta, S. Das, P. Chatterjee, ”Smart Sales Prediction of Pharmaceutical Products,” in 2022 8th International Conference on Smart Structures and Systems (ICSSS), pp. 1-6, Apr. 2022, IEEE.
[2] P. K. Mianaei, M. Aliahmadi, S. Faghri, M. Ensaf, A. Ghasemi, and A. A. Abdoos, “Chance-constrained programming for optimal scheduling of combined cooling, heating, and power-based microgrid coupled with flexible technologies,” Sustainable Cities and Society, vol. 77, p. 103502, 2022.
[Online]. Available: https://doi.org/10.1016/j.scs.2021.103502.
[3] R. Rathipriya, A. A. Abdul Rahman, S. Dhamodharavadhani, A. Meero, G. Yoganandan, ”Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model,” in Neural Computing and Applications, vol. 35, no. 2, pp. 1945-1957, 2023. .
[4] Y. Han, ”A forecasting method of pharmaceutical sales based on ARIMA-LSTM model,” in 2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT), pp. 336-339, Nov. 2020, IEEE.
[5] L. P. E. Yani, A. Aamer, ”Demand forecasting accuracy in the pharmaceutical supply chain: a machine learning approach,” in International Journal of Pharmaceutical and Healthcare Marketing, vol. 17, no. 1, pp. 1-23, 2023.
[6] M. R. Moradi, S. R. N. Kalhori, M. G. Saeedi, M. R. Zarkesh, A. Habibelahi, et al., “Designing a Remote Closed-Loop Automatic Oxygen Control in Preterm Infants,” Iran J Pediatr., vol. 30, no. 4, p. e101715, 2020.
[Online]. Available: https://doi.org/10.5812/ijp.101715.
[7] S. Ratre, J. Jayaraj, ”Sales Prediction Using ARIMA, Facebook’s Prophet and XGBoost Model of Machine Learning,” in Machine Learning, Image Processing, Network Security and Data Sciences: Select Proceedings of 3rd International Conference on MIND 2021, pp. 101-111, Jan. 2023, Springer Nature Singapore, Singapore.
[8] A. E. Jery, M. Aldrdery, N. Ghoudi, M. Moradi, I. H. Ali, H. H. Tizkam, S. S. Sammen, ”Experimental Investigation and Proposal of Artificial Neural Network Models of Lead and Cadmium Heavy Metal Ion Removal from Water Using Porous Nanomaterials,” in Sustainability, vol. 15, no. 19, p. 14183, 2023
[9] R. Gustriansyah, E. Ermatita, D. P. Rini, ”An approach for sales forecasting,” in Expert Systems with Applications, vol. 207, p. 118043, 2022.
[10] S. Punia, S. Shankar, ”Predictive analytics for demand forecasting: A deep learning-based decision support system,” in Knowledge-Based Systems, vol. 258, p. 109956, 2022.
[11] G. A. Chressanthis, A. Sfekas, P. Khedkar, N. Jain, P. Poddar, ”Determinants of pharmaceutical sales representative access limits to physicians,” in Journal of Medical Marketing, vol. 14, no. 4, pp. 220-243, 2014, doi: 10.1177/1745790415583866.
[12] J. F. Torres, D. Hadjout, A. Sebaa, F. Mart´ınez-A´ lvarez, A. Troncoso, ”Deep Learning for Time Series Forecasting: A Survey,” in Big Data, vol. 9, no. 1, Mary Ann Liebert Inc., pp. 3–21, Feb. 01, 2021, doi: 10.1089/big.2020.0159.