Forecasting Post-Patent Time Series Pharmaceutical Sales: A Comparative Study of Statistical and Machine Learning Models

Sebastian Miguel; Sfenrianto Sfenrianto

doi:10.30595/juita.v14i1.29008

Authors

Sebastian Miguel Bina Nusantara University
Sfenrianto Sfenrianto Bina Nusantara University

DOI:

https://doi.org/10.30595/juita.v14i1.29008

Keywords:

Sales prediction, machine learning, AI, pharmaceutical sales, time series analysis.

Abstract

Volatility in the pharmaceutical industry can be caused by expiration of drug patents, leading to a gap between actual and target sales values, which necessitates accurate sales forecasting for pharmaceutical marketers. This study utilizes the sales data from PT. Q, an Indonesian pharmaceutical firm. The comparative performance within the specific context of the post-patent period for pharmaceutical sales remains relatively unexplored. This research aims to compare forecasting models for post-patent pharmaceutical sales. The research method utilized is based on the CRISP-DM data mining framework. The forecasting process is done on a 4.5-year timeframe using forecasting models such as ARIMA, SARIMA, LSTM, and Prophet. The results show that multivariate LSTM works better for forecasting in smaller aggregations in the dataset such as by product type and branch, with a R² score value of up to 0.64 in the aggregation level of Bandung_Sales, and with the smallest error metric values, such as MAE in many aggregation levels, example being regional sales, such as Lampung_Sales with 1.31 and Makassar_Sales with 0.26, which outperforms the other compared models in the majority of cases. This research concludes that multivariate LSTM is a better way to replace outdated methods to set sales targets.

Author Biographies

Sebastian Miguel, Bina Nusantara University

Information Systems Management Department

Sfenrianto Sfenrianto, Bina Nusantara University

Information Systems Management Department

References

[1] J. Li, Y. Lin, X. Li, and J. Zhang, “Economic evaluation of chelation regimens for β-Thalassemia Major: A systematic review,” Mediterr. J. Hematol. Infect. Dis., vol. 11, no. 1, pp. 1–15, 2019, doi: 10.4084/MJHID.2019.036.

[2] R. Mohamed, A. H. Abdul Rahman, F. Masra, and Z. Abdul Latiff, “Barriers to adherence to iron chelation therapy among adolescent with transfusion dependent thalassemia,” Front. Pediatr., vol. 10, no. October, 2022, doi: 10.3389/fped.2022.951947.

[3] C. Eziefula, F. T. Shah, and K. A. Anie, “Promoting Adherence to Iron Chelation Treatment in Beta-Thalassemia Patients,” Patient Prefer. Adherence, vol. 16, no. March, pp. 1423–1437, 2022, doi: 10.2147/PPA.S269352.

[4] K. Y. Wen, M. H. Joseph, and V. Sivakumar, “Big Mart Sales Prediction using Machine Learning,” EAI Endorsed Trans. Internet Things, vol. 10, pp. 1–6, 2024, doi: 10.4108/eetiot.6453.

[5] D. Jox, C. Borsum, D. Hummel, J. Hinrichs, and C. Krupitzer, “Enhancing dairy processing with machine learning and domain knowledge: A combined analysis of offline and time series data,” J. Food Eng., vol. 391, no. November 2024, p. 112423, 2025, doi: 10.1016/j.jfoodeng.2024.112423.

[6] S. C. M. W. Tummers, A. Hommersom, C. Bolman, L. Lechner, and R. Bemelmans, “A new data science trajectory for analysing multiple studies: a case study in physical activity research,” MethodsX, vol. 14, no. October 2024, p. 103104, 2025, doi: 10.1016/j.mex.2024.103104.

[7] R. Sebastian and C. Juliane, “Comparison of Data Mining Classification Algorithms for Stroke Disease Prediction Using the SMOTE Upsampling Method,” JUITA J. Inform., vol. 11, no. 2, pp. 311–321, 2023.

[8] S. Selvakumar, G. Renugadevi, N. Vinishah, and R. Yashwanth, “Sales Forecasting Based on Time Series Analysis,” Proc. 2024 Int. Conf. Sci. Technol. Eng. Manag. ICSTEM 2024, pp. 1–7, 2024, doi: 10.1109/ICSTEM61137.2024.10560659.

[9] D. Kobiela, D. Krefta, W. Król, and P. Weichbroth, “ARIMA vs LSTM on NASDAQ stock exchange data,” Procedia Comput. Sci., vol. 207, no. October, pp. 3830–3839, 2022, doi: 10.1016/j.procs.2022.09.445.

[10] F. Mbonyinshuti, J. Nkurunziza, J. Niyobuhungiro, and E. Kayitare, “Health supply chain forecasting: a comparison of ARIMA and LSTM time series models for demand prediction of medicines,” Acta Logist., vol. 11, no. 2, pp. 269–280, 2024, doi: 10.22306/AL.V11I2.510.

[11] N. Absar, N. Uddin, M. U. Khandaker, and H. Ullah, “The efficacy of deep learning based LSTM model in forecasting the outbreak of contagious diseases,” Infect. Dis. Model., vol. 7, no. 1, pp. 170–183, 2022, doi: 10.1016/j.idm.2021.12.005.

[12] M. Baloch, M. S. Honnurvali, A. Kabbani, T. Ahmed, S. T. Chauhdary, and M. S. Saeed, “Solar Energy Forecasting Framework Using Prophet Based Machine Learning Model: An Opportunity to Explore Solar Energy Potential in Muscat Oman,” Energies, vol. 18, no. 1, 2025, doi: 10.3390/en18010205.

[13] V. M. Vargas-Forero, D. F. Manotas-Duque, and L. Trujillo, “Comparative Study of Forecasting Methods to Predict the Energy Demand for the Market of Colombia,” Int. J. Energy Econ. Policy, vol. 15, no. 1, pp. 65–76, 2025, doi: 10.32479/ijeep.17528.

[14] M. A. Legarreta-González, “Selecting a Time-Series Model to Predict Drinking Water Extraction in a Semi-Arid Region in Chihuahua, Mexico,” Sustain., vol. 16, no. 22, pp. 1–22, 2024, doi: 10.3390/su16229722.

[15] W. Pangesti, N. Syukri, K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, “Performance Evaluation of ARIMA and GRU Models for Forecasting Chili Price in East Jawa,” JUITA J. Inform., vol. 13, no. 2, pp. 209–218, 2025, doi: 10.30595/juita.v13i2.26445.

[16] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.

[17] S. Widodo, F. S. Utomo, and Berlilana, “A Comprehensive Evaluation of CatBoost and LightGBM Algorithms for Honorarium Prediction on Categorical Datasets with Class Imbalance,” JUITA J. Inform., vol. 13, no. 3, pp. 359–370, 2025, doi: 10.30595/juita.v13i3.27363.

[18] K. P. Fourkiotis and A. Tsadiras, “Applying Machine Learning and Statistical Forecasting Methods for Enhancing Pharmaceutical Sales Predictions,” Forecasting, vol. 6, no. 1, pp. 170–186, 2024, doi: 10.3390/forecast6010010.

[19] M. Mothilal and A. Kumar, “Predictive modeling of ultimate tensile strength in dissimilar friction stir welded aluminum alloys via machine learning approach,” Philos. Mag. Lett., vol. 105, no. 1, 2025, doi: 10.1080/09500839.2025.2472669.