Prediction of the Use of Liquid Chemical Materials using Machine Learning Method: A Case Study at XYZ Company
Prediction of the Use of Liquid Chemical Materials using Machine Learning Method: A Case Study at XYZ Company |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-9 |
||
| Year of Publication : 2025 | ||
| Author : Muhammad Furqon, Tuga Mauritsius | ||
| DOI : 10.14445/22315381/IJETT-V73I9P107 | ||
How to Cite?
Muhammad Furqon, Tuga Mauritsius,"Prediction of the Use of Liquid Chemical Materials using Machine Learning Method: A Case Study at XYZ Company", International Journal of Engineering Trends and Technology, vol. 73, no. 9, pp.66-78 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I9P107
Abstract
Control over the availability of liquid chemical materials as raw materials is a crucial factor in the production process at XYZ Company. A shortage of raw materials leads to losses due to additional shipping costs and the inability to meet customer demands. On the other hand, ordering excessive raw materials creates another problem, as the limited warehouse capacity and the presence of dead stock also result in financial losses. Therefore, a more accurate forecasting method is needed compared to the current approach, which relies only on raw material usage in the same month of the previous year and the average of the last three months. To address this issue, two popular forecasting methods are applied: the traditional machine learning method Autoregressive Integrated Moving Average (ARIMA) and the modern deep learning method Long Short-Term Memory (LSTM). This study adopts the Cross-Industry Process for Data Mining (CRISP-DM) framework and utilizes Python software. The aim is to evaluate forecasting accuracy across different time frames by comparing RMSE and MAPE values. The results show that both ARIMA and LSTM perform well, with MAPE values ranging from 9.0% to 18.7%. The ARIMA method, when applied with a monthly time frame, achieved an MAPE of 9.0%, indicating a very high level of accuracy.
Keywords
ARIMA, CRISP-DM, Forecasting, LSTM, Python.
References
[1] Cyril Koch et al., “A Matheuristic Approach for Solving a Simultaneous Lot Sizing and Scheduling Problem with Client Prioritization in Tire Industry,” Computers & Industrial Engineering, vol. 165, pp. 1-61, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Keely L. Croxton et al., “The Demand Management Process,” The International Journal of Logistics Management, vol. 13, no. 2, pp. 51-66, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Emrah Cengiz, “Measuring Customer Satisfaction: Must or Not?,” Journal of Naval Science and Engineering, vol. 6, no. 2, pp. 76-88, 2010.
[Google Scholar] [Publisher Link]
[4] Ricardo P. Masini, Marcelo C. Medeiros, and Eduardo F. Mendes, “Machine Learning Advances for Time Series Forecasting,” Journal of Economic Surveys, vol. 37, no. 1, pp. 76-111, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Pramit Pandit et al., “ARIMA-Genetic Algorithm Approach for Forecasting Milk Production in India,” Asian Journal of Dairy and Food Research, vol. 43, no. 4, pp. 784-789, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Faisal Rizki Kurniawan, and Rudi Sutomo, “Forecasting Rice Inventory in Indonesia Using the ARIMA Algorithm Method,” Journal of Multidisciplinary Issues, vol. 1, no. 2, pp. 1-12, 2021.
[CrossRef] [Publisher Link]
[7] Ahamad Zaki Mohamed Noor et al., “Data Prediction of Reject Unit from Manufacturing Company using Auto Regressive Integrated Moving Average (ARIMA) Algorithm,” International Journal of Emerging Trend in Engineering Research, vol. 8, no. 9, pp. 6164-6169, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Anna Manowska, and Anna Bluszcz, “Forecasting Crude Oil Consumption in Poland Based on LSTM Recurrent Neural Network,” Energies, vol. 15, no. 13, pp. 1-23, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ali Javaid et al., “Forecasting Hydrogen Production from Wind Energy in a Suburban Environment Using Machine Learning,” Energies, vol. 15, no. 23, pp. 1-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Uppala Meena Sirisha, Manjula C. Belavagi, and Girija Attigeri, “Profit Prediction Using ARIMA, SARIMA and LSTM Models in Time Series Forecasting: A Comparison,” IEEE Access, vol. 10, pp. 124715-124727, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Chien-Chih Wang, Chun-Hua Chien, and Amy J. C. Trappey, “On the Application of ARIMA and LSTM to Predict Order Demand Based on Short Lead Time and On-Time Delivery Requirements,” Processes, vol. 9, no. 7, pp. 1-20, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Taha Falatouri et al., “Predictive Analytics for Demand Forecasting - A Comparison of SARIMA and LSTM in Retail SCM,” Procedia Computer Science, vol. 200, pp. 993-1003, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Bryan Alfason Sunjaya, Syarifah Diana Permai, and Alexander Agung Santoso Gunawan, “Forecasting of Covid-19 Positive Cases in Indonesia using Long Short-Term Memory (LSTM),” Procedia Computer Science, vol. 216, pp. 177-185, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Tej Bahadur Shahi et al., “Stock Price Forecasting with Deep Learning: A Comparative Study,” Mathematics, vol. 8, no. 9, pp. 1-15, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Michael David Angelo, Ilhas Fadhiilrahman, and Yudy Purnama, “Comparative Analysis of ARIMA and Prophet Algorithms in Bitcoin Price Forecasting,” Procedia Computer Science, vol. 227, pp. 490-499, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xuanyi Song et al., “Time-Series well Performance Prediction based on Long Short-Term Memory (LSTM) Neural Network Model,” Journal of Petroleum Science and Engineering, vol. 186, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Emmanuel Dave et al., “Forecasting Indonesia Exports using a Hybrid Model ARIMA-LSTM,” Procedia Computer Science, vol. 179, pp. 480-487, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Fariza Tolesh, and Svitlana Biloshchytska, “Forecasting International Migration in Kazakhstan using ARIMA Models,” Procedia Computer Science, vol. 231, pp. 176-183, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Guru Dayal Kumar, Kalandi Charan Pradhan, and Shekhar Tyagi, “Deep Learning Forecasting: An LSTM Neural Architecture based Approach to Rainfall and Flood Impact Predictions in Bihar,” Procedia Computer Science, vol. 235, pp. 1455-1466, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] J.F. Torres, F. Martínez-Álvarez, and A. Troncoso, “A deep LSTM Network for the Spanish Electricity Consumption Forecasting,” Neural Computing and Applications, vol. 34, no. 13, pp. 10533-10545, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sanjiv Jaggia et al., “Applying the CRISP-DM Framework for Teaching Business Analytics,” Decision Sciences Journal of Innovative Education, vol. 18, no. 4, pp. 612-634, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Tingxin Wen et al., “Modeling and Forecasting CO2 Emissions in China and its Regions using a Novel ARIMA-LSTM Model,” Heliyon, vol. 9, no. 11, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Dongyan Fan et al., “Well Production Forecasting based on ARIMA-LSTM Model Considering Manual Operations,” Energy, vol. 220, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]