Cluster-specific Bi-LSTM models for improved pharmaceutical sales forecasting

Indri Hapsari

Abstract


In the pharmaceutical sector, accurate forecasting is imperative due to the diverse range of medicines. Inadequate inventory levels risk patient well-being, whereas excessive stock can result in financial waste. This study categorizes historical sales data from a Denpasar-based pharmacy industry into clusters via K-Means clustering, analyzing 106 medicines over 60 months, with 54 months for training and six for testing. Four distinct Bi-LSTM (Bidirectional Long Short-Term Memory) based forecasting models emerged, tailored to each cluster's characteristics. Cluster 0's model, with two input neurons and three hidden layers, underwent 220 epochs of training, achieving an MAE of (0.0835) and an MSE of (0.0165). Cluster 1's model, more intricate with ten input neurons and two hidden layers, was trained for 136 epochs, resulting in an MAE of (0.1299) and an MSE of (0.0309). Cluster 2's model resembled Cluster 0 but with reduced neurons in the hidden layers, trained for 20 epochs, yielding an MAE of (0.0899) and an MSE of (0.0380). Finally, Cluster 3's model featured two input neurons and a single hidden layer with 128 neurons, trained for 150 epochs, attaining an MAE of (0.0239) and an MSE of (0.094). Forecast application of Cluster 0's model for individual medicine using Bi-LSTM demonstrated its efficacy in predicting demand compared with machine learning forecast models such as Random Forest, Gradient Boosting, Support Vector Machine, and Neural Network. The model's adaptability to demand fluctuations can guide pharmacies in managing their inventory and optimizing supply chain operations, sales, marketing strategies, and product development.

Keywords


Forecasting; Bi-LSTM; K-means clustering; Pharmacy; Machine Learning

Full Text:

PDF

References


G. Merkuryeva, A. Valberga, and A. Smirnov, “Demand forecasting in pharmaceutical supply chains: A case study,” Procedia Comput. Sci., vol. 149, pp. 3-10, 2019, doi: 10.1016/j.procs.2019.01.100.

F. Kochakkashani, V. Kayvanfar, and A. Haji, “Supply chain planning of vaccine and pharmaceutical clusters under uncertainty: The case of COVID-19,” Socio-Econ. Plan. Sci., vol. 87, 2023, doi: 10.1016/j.seps.2023.101602.

E. Hofmann, H. Sternberg, H. Chen, A. Pflaum, and G. Prockl, “Supply chain management and industry 4.0: Conducting research in the digital age,” Int. J. Phys. Distrib. Logist. Manag., vol. 49, pp. 945-955, 2019, doi: 10.1108/IJPDLM-11-2019-399.

I. C. Reinhardt, J. C. Oliveira, and D. T. Ring, “Current perspectives on the development of industry 4.0 in the pharmaceutical sector,” J. Ind. Inf. Integr., vol. 18, 2020, doi: 10.1016/j.jii.2020.100131.

T. Ramesh and V. Santhi, “Exploring big data analytics in health care,” Int. J. Intell. Netw., vol. 1, pp. 135-140, 2020, doi: 10.1016/j.ijin.2020.11.003.

D. N. Ouedraogo, “Interpretable machine learning model selection for breast cancer diagnosis based on K-means clustering,” Appl. Med. Inform. Original Res., vol. 43, no. 3, pp. 91-102, 2021.

G. S. Palupi and M. N. A. Fakhruzzaman, “Indonesian pharmacy retailer segmentation using recency frequency monetary-location model and ant K-means algorithm,” Int. J. Electr. Comput. Eng., vol. 12, no. 6, pp. 6132-6139, 2022, doi: 10.11591/ijece.v12i6.

L. T. Murry, J. Urmie, and A. Olson, “Item development for patient-centered care preferences using a three-archetype heuristic: An exploratory study,” Explor. Res. Clin. Soc. Pharm., vol. 9, 2023, doi: 10.1016/j.rcsop.2023.100251.

K. E. Setiawan, A. Kurniawan, A. Chowanda, and D. Suhartono, “Clustering models for hospitals in Jakarta using Fuzzy C-means and K-means,” Procedia Comput. Sci., vol. 216, pp. 356-363, 2023, doi: 10.1016/j.procs.2022.12.146.

A. Mousavi, M. Mohammadzadeh, and H. Zare, “A clustering approach to identify the organizational life cycle,” J. Open Innov. Technol. Market Complex, vol. 8, no. 3, 2022, doi: 10.3390/joitmc8030108.

N. N. Arief, A. Gustomo, M. R. Roestan, A. N. A. Putri, and M. Islamiaty, “Pharma 4.0: analysis on core competence and digital leveling implementation in the pharmaceutical industry in Indonesia,” Heliyon, vol. 8, no. 8, 2022, doi: 10.1016/j.heliyon.2022.e10347.

J. Devaraj et al., “Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?,” Results Phys., vol. 21, 2021, doi: 10.1016/j.rinp.2021.103817.

Z. Luo, L. Zhang, N. Liu, and Y. Wu, “Time series clustering of COVID-19 pandemic-related data,” Data Sci. Manag., vol. 6, no. 2, pp. 79-87, 2023, doi: 10.1016/j.dsm.2023.03.003.

S. Y. Ilu and R. Prasad, “Improved autoregressive integrated moving average model for COVID-19 prediction by using statistical significance and clustering techniques,” Heliyon, vol. 9, no. 2, 2023, doi: 10.1016/j.heliyon.2023.e13483.

G. Hole, A. S. Hole, and I. McFalone-Shaw, “Digitalization in the pharmaceutical industry: What to focus on under the digital implementation process?,” Int. J. Pharm., vol. 3, 2021, doi: 10.1016/j.ijpx.2021.100095.

N. S. Arden, A. C. Fisher, K. Tyner, L. X. Yu, S. L. Lee, and M. Kopcha, “Industry 4.0 for pharmaceutical manufacturing: Preparing for the smart factories of the future,” Int. J. Pharm., vol. 602, 2021, doi: 10.1016/j.ijpharm.2021.120554.

Y. Kim, E. Atukeren, and Y. Lee, “A new digital value chain model with PLC in biopharmaceutical industry: The implication for open innovation,” J. Open Innov. Technol. Market Complex, vol. 8, no. 2, 2022, doi: 10.3390/joitmc8020063.

A. A. Halwani et al., “Current status and vision of local pharmaceutical industries in Saudi Arabia: The focus on nano medicines,” Saudi Pharm. J., vol. 31, no. 8, 2023, doi: 10.1016/j.jsps.2023.06.007.

I. Duarte, B. Mota, T. Pinto-Varela, and A. P. Barbosa-Póvoa, “Pharmaceutical industry supply chains: How to sustainably improve access to vaccines?,” Chem. Eng. Res. Des., vol. 182, pp. 324-341, 2022, doi: 10.1016/j.cherd.2022.04.001.

H. S. Lee and B. Y. Chang, “A new stochastic SIQR (Susceptible-Infected -Quarantine-Removed) model with two delays: Forecasting COVID-19 diffusion,” Int. J. Ind. Eng.: Theory, Appl. Pract., vol. 30, no. 3, 2023, doi: 10.23055/ijietap.2023.30.3.8365.

S. Chandrasekar, K. Subburathinam, and K. Srihari, “Analysis for heart disease prediction using deep neural network and VGG_19 convolutional neural network”, Int. J. Ind. Eng.: Theory, Appl. Pract., pp. 876-889, 2023, doi: 10.23055/ijietap.2023.30.4.8603.

E. Hofmann and E. Rutschmann, “Big data analytics and demand forecasting in supply chains: a conceptual analysis,” Int. J. Logist. Manag., vol. 29, no. 2, pp. 739-766, 2018, doi: 10.1108/IJLM-04-2017-0088.

J. Lin, J. Ma, J. Zhu, and Y. Cui, “Short-term load forecasting based on LSTM networks considering attention mechanisms,” Int. J. Electr. Power Energy Syst., vol. 137, 2022, doi: 10.1016/j.ijepes.2021.107818.

H. Shubo et al., “Short-Term load forecasting based on mutual information and BI-LSTM considering fluctuation in importance values of features,” IEEE Access, 2023, doi: 10.1109/ACCESS.2023.3323403.

L. Zhou, C. Zhao, N. Liu, X. Yao, and Z. Cheng, “Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach,” Eng. Appl. Artif. Intell., vol. 122, 2023, doi: 10.1016/j.engappai.2023.106157.

S. Khalil, C. Amrit, T. Koch, and E. Dugundji, “Forecasting public transport ridership: management of information systems using CNN and LSTM architectures,” Procedia Comput. Sci., vol. 184, pp. 283-290, 2021, doi: 10.1016/j.procs.2021.03.037.

A. Rayan and A. S. Alaerjan, “An improved crow search optimization with Bi-LSTM model for identification and classification of COVID-19 infection from chest X-Ray images,” Alexandria Eng. J., vol. 76, pp. 787-798, 2023, doi: 10.1016/j.aej.2023.06.052.

B. Sirisha, K. K. C. Goud, and B. T. V. S. Rohit, “A Deep Stacked Bidirectional LSTM (SBiLSTM) model for petroleum production forecasting,” Procedia Comput. Sci., vol. 218, pp. 2767-2775, 2023, doi: 10.1016/j.procs.2023.01.248.

I. V. Pustokhina, D. A. Pustokhin, and E. L. Lydia, “Hyperparameter search based convolution neural network with Bi-LSTM model for intrusion detection system in multimedia big data environment,” Multimed. Tools Appl., vol. 81, pp. 34951-34968, 2022, doi: 10.1007/s11042-021-11271-7.

M. Ziaee, H. K. Shee, and A. Sohal, “Big data analytics in the Australian pharmaceutical supply chain,” Ind. Manag. Data Syst., vol. 123, no. 5, pp. 1310-1335, 2023, doi: 10.1108/IMDS-05-2022-0309.

S. Metlek, “A new proposal for the prediction of an aircraft engine fuel consumption: a novel CNN-BiLSTM deep neural network model,” Aircraft Eng. Aerosp. Technol., vol. 95, no. 5, pp. 838-848, 2023, doi: 10.1108/AEAT-05-2022-0132.

V. R. Kota and S. D. Munisamy, “High accuracy offering attention mechanisms based deep learning approach using CNN/Bi-LSTM for sentiment analysis,” Int. J. Intell. Comput. Cybern., vol. 15, no. 1, pp. 61-74, 2022, doi: 10.1108/IJICC-06-2021-0109.




DOI: http://dx.doi.org/10.62870/jiss.v10i2.26898

Refbacks

  • There are currently no refbacks.


  is supported by