Author(s)

Ramchorn Gharami¹, Delwar Karim², Amit Kumar^2*, Rashid Khan²

Affiliation(s)

¹Department of Computer Application, National University, Khulna, Bangladesh.

²Independent Researcher, Dhaka, Bangladesh.

Corresponding Author

Amit Kumar

ABSTRACT

Sales trend forecasting is a critical function within modern business intelligence (BI) systems, enabling organizations to optimize inventory management, allocate resources effectively, and make strategic decisions in an increasingly volatile market. Traditionally, classical time series models such as ARIMA and Exponential Smoothing have been widely used due to their interpretability and robust theoretical foundations. However, the emergence of machine learning (ML) methods such as Random Forests, Gradient Boosting Machines, and Long Short-Term Memory (LSTM) networks has introduced new opportunities for capturing complex, non-linear patterns in sales data. This review provides a comprehensive comparison between classical and machine learning approaches for sales trend prediction, examining their strengths, limitations, and practical applications. Classical models offer simplicity, computational efficiency, and strong performance with stationary and linear data, making them suitable for well-structured datasets. Conversely, machine learning models excel in handling large, noisy, and multi-dimensional datasets, offering superior accuracy at the cost of higher computational demands and reduced interpretability. Real-world applications across retail, finance, supply chain management, and healthcare are explored, highlighting the transformative impact of time series forecasting in business operations. Key challenges including data quality, model maintenance, and the need for explainable AI are discussed alongside future directions such as real-time forecasting, transfer learning, and federated learning. By synthesizing insights from both classical and contemporary forecasting paradigms, this review aims to guide researchers, data scientists, and business leaders in selecting appropriate methodologies for enhancing predictive capabilities within business intelligence ecosystems.

KEYWORDS

Business intelligence; Classical models; Machine learning approaches; Sales trend prediction; Time series forecasting

CITE THIS PAPER

Ramchorn Gharami, Delwar Karim, Amit Kumar, Rashid Khan. Time series forecasting in business intelligence: a comparative study of classical and machine learning approaches for sales trend prediction. Journal of Trends in Financial and Economics. 2025, 2(3): 13-19. DOI: https://doi.org/10.61784/jtfe3047.

REFERENCES

[1] Alam G T, Chy M А R, Rozario E, et al. AI-Driven Optimization of Domestic Timber Supply Chains to Enhance U.S. Economic Security. Journal of Posthumanism, 2025, 5(1): 1581–1605. DOI: 10.63332/joph.v4i3.2083.

[2] Rahman M S, Islam S, Khan S I, et al. Redefining marketing and management strategies in digital age: Adapting to consumer behavior and technological disruption. Journal of Information Systems Engineering and Management, 2024, 9(4): 1–16. DOI: 10.52783/jisem.v9i4.32.

[3] Mahmud F, Barikdar C R, Hassan J, et al. AI-Driven Cybersecurity in IT Project Management: Enhancing Threat Detection and Risk Mitigation. Journal of Posthumanism, 2025, 5(4): 23–44. DOI: 10.63332/joph.v5i4.974.

[4] Hossain S, Karim F, Sultana S, et al. From Data to Value: Leveraging Business Analytics for Sustainable Management Practices. Journal of Posthumanism, 2025, 5(5): 82–105. DOI: 10.63332/joph.v5i5.1309.

[5] Hyndman R J, Athanasopoulos G. Forecasting: Principles and Practice (3rd ed.). 2021.

[6] Laptev N, Yosinski J, Li L E, et al. Time-series extreme event forecasting with neural networks at Uber. 2017.

[7] Miah M A, Ahmed M K, Bhuiyan M M R, et al. Big Data Analytics for Enhancing Coal-Based Energy Production Amidst AI Infrastructure Growth. Journal of Posthumanism, 2025, 5(5): 5061–5080. DOI: 10.63332/joph.v5i5.2087.

[8] Manik M M T G, Mohonta S C, Karim F, et al. AI-Driven Precision Medicine Leveraging Machine Learning and Big Data Analytics for Genomics-Based Drug Discovery. Journal of Posthumanism, 2025, 5(1): 1560–1580. DOI: 10.63332/joph.v5i1.1993.

[9] Moniruzzaman M, Islam M S, Mohonta S C, et al. Big Data Strategies for Enhancing Transparency in U.S. Healthcare Pricing. Journal of Posthumanism, 2025, 5(5): 3744–3766. DOI: 10.63332/joph.v5i5.1813.

[10] Hossain E, Ashik A A M, Rahman M M, et al. Big data and migration forecasting: Predictive insights into displacement patterns triggered by climate change and armed conflict. Journal of Computer Science and Technology Studies, 2023, 5(4): 265–274. DOI: 10.32996/jcsts.2023.5.4.27.

[11] Khan S I, Rahman M S, Ashik A A M, et al. Big Data and Business Intelligence for Supply Chain Sustainability: Risk Mitigation and Green Optimization in the Digital Era. European Journal of Management, Economics and Business, 2024, 1(3): 262-276. DOI: 10.59324/ejmeb.2024.1(3).23.

[12] Box G E P, Jenkins G M, Reinsel G C, et al. Time Series Analysis: Forecasting and Control (5th ed.). Wiley, 2015.

[13] Makridakis S, Spiliotis E, Assimakopoulos V. The M4 Competition: Results, findings, conclusion and way forward. International Journal of Forecasting, 2020, 36(1): 54-74. DOI: 10.1016/j.ijforecast.2019.04.014

[14] Makridakis S, Spiliotis E, Assimakopoulos V. Statistical and machine learning forecasting methods: Concerns and ways forward. Plos One, 2018, 13(3): e0194889. DOI: 10.1371/journal.pone.0194889.

[15] Manyika J, Chui M, Brown B, Bughin J, et al. Big data: The next frontier for innovation, competition, and productivity. McKinsey Global Institute, 2011.

[16] Islam M S, Manik M M T G, Moniruzzaman M, et al. Explainable AI in Healthcare: Leveraging Machine Learning and Knowledge Representation for Personalized Treatment Recommendations. Journal of Posthumanism, 2025, 5(1):1541–1559. DOI: 10.63332/joph.v5i1.1996.

[17] Bandara K, Bergmeir C, Smyl S. Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach. Expert Systems with Applications, 2020, 140: 112896. DOI: 10.1016/j.eswa.2019.112896.

[18] Brownlee J. Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery, 2018.

[19] Manik M M T G. An Analysis of Cervical Cancer using the Application of AI and Machine Learning. Journal of Medical and Health Studies, 2022, 3(2): 67-76. DOI: 10.32996/jmhs.2022.3.2.11.

[20] Sultana S, Karim F, Rahman H, et al. A Comparative Review of Machine Learning Algorithms in Supermarket Sales Forecasting with Big Data. Journal of Ecohumanism, 2024, 3(8): 14457. DOI: 10.62754/joe.v3i8.6762.

[21] Haldar U, Alam G T, Rahman H, et al. AI-Driven Business Analytics for Economic Growth Leveraging Machine Learning and MIS for Data-Driven Decision-Making in the U.S. Economy. Journal of Posthumanism, 2025, 5(4): 932–957. DOI: 10.63332/joph.v5i4.1178.                                                         

[22] Smyl S. A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. International Journal of Forecasting, 2020, 36(1): 75-85. DOI: 10.1016/j.ijforecast.2019.03.017

[23] Manik M M T G, Hossain S, Ahmed M K, et al. Integrating Genomic Data and Machine Learning to Advance Precision Oncology and Targeted Cancer Therapies. Nanotechnology Perceptions, 2022, 18 (2): 219-243. DOI: 10.62441/nano-ntp.v18i2.5443.

[24] Manik M M T G. Multi-Omics Integration with Machine Learning for Early Detection of Ischemic Stroke Through Biomarkers Discovery. Journal of Ecohumanism, 2023, 2(2): 175–187. DOI: 10.62754/joe.v2i2.6800.

[25] Manik M M T G, Saimon A S M, Islam M S, et al. Big Data Analytics for Credit Risk Assessment. In 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS), Prawet, Thailand, 2025:  1379-1390. DOI: 10.1109/ICMLAS64557.2025.10967667.

[26] Khair F B, Ahmed M K, Hossain S, et al. Sustainable Economic Growth Through Data Analytics: The Impact of Business Analytics on U.S. Energy Markets and Green Initiatives," 2024 International Conference on Progressive Innovations in Intelligent Systems and Data Science (ICPIDS), Pattaya, Thailand, 2024: 108-113. DOI: 10.1109/ICPIDS65698.2024.00026.

[27] Islam S, Hossain E, Rahman M S, et al. Digital Transformation in SMEs: Unlocking Competitive Advantage through Business Intelligence and Data Analytics Adoption. 2023, 5(6): 177-186. DOI: 10.32996/jbms.2023.5.6.14.

[28] Hossain D. A fire protection life safety analysis of multipurpose building. 2021. https://digitalcommons.calpoly.edu/fpe_rpt/135/.

[29] Alasa DK, Hossain D, Jiyane G. Hydrogen Economy in GTL: Exploring the role of hydrogen-rich GTL processes in advancing a hydrogen-based economy. International Journal of Communication Networks and Information Security (IJCNIS), 2025, 17(1): 81–91. https://www.ijcnis.org/index.php/ijcnis/article/view/8021.

[30] Hossain D, Asrafuzzaman M, Dash S, et al. Multi-Scale Fire Dynamics Modeling: Integrating Predictive Algorithms for Synthetic Material Combustion in Compartment Fires. Journal of Management World, 2024(5): 363-374. DOI: 10.53935/jomw.v2024i4.1133.

[31] Hossain S, Bhuiyan M M R, Islam M S, et al. Big Data Analysis and prediction of COVID-2019 Epidemic Using Machine Learning Models in Healthcare Sector. Journal of Ecohumanism, 2024, 3(8): 14468. DOI: 10.62754/joe.v3i8.6775.

[32] Hossain D. Fire dynamics and heat transfer: advances in flame spread analysis. Open Access Research Journal of Science and Technology, 2022, 6(2): 70-5. DOI: 10.53022/oarjst.2022.6.2.0061.

[33] Hossain D, Alasa DK, Jiyane G. Water-based fire suppression and structural fire protection: strategies for effective fire control. International Journal of Communication Networks and Information Security (IJCNIS), 2023, 15(4): 485-94. https://ijcnis.org/index.php/ijcnis/article/view/7982.

[34] Das K, Tanvir A, Rani S, et al. Revolutionizing Agro-Food Waste Management: Real-Time Solutions through IoT and Big Data Integration. Voice of the Publisher, 2025, 11: 17-36. DOI: 10.4236/vp.2025.111003.

[35] Bulbul IJ, Zahir Z, Tanvir A, et al. Comparative study of the antimicrobial, minimum inhibitory concentrations (MIC), cytotoxic and antioxidant activity of methanolic extract of different parts of Phyllanthus acidus (l.) Skeels (family: Euphorbiaceae). World Journal of Pharmacy and Pharmaceutical Sciences, 2018, 8(1): 12-57. DOI: 10.20959/wjpps20191-10735.

[36] Tanvir A, Jo J, Park SM. Targeting Glucose Metabolism: A Novel Therapeutic Approach for Parkinson’s Disease. Cells, 2024, 13: 1876. DOI: 10.3390/cells13221876.

[37] Manik M M T G. Biotech-Driven Innovation in Drug Discovery: Strategic Models for Competitive Advantage in the Global Pharmaceutical Market. Journal of Computational Analysis and Applications (JoCAAA), 2020, 28(6): 41–47. https://eudoxuspress.com/index.php/pub/article/view/2874.

[38] Manik M M T G. Multi-Omics System Based on Predictive Analysis with AI-Driven Models for Parkinson’s Disease (PD) Neurosurgery. Journal of Medical and Health Studies, 2021, 2(1): 42-52. https://doi.org/10.32996/jmhs.2021.2.1.5  

[39] Manik M M T G, Saimon A S M, Miah M A, et al. Leveraging Ai-Powered Predictive Analytics for Early Detection of Chronic Diseases: A Data-Driven Approach to Personalized Medicine. Nanotechnology Perceptions, 2021, 17 (3): 269-288. DOI: 10.62441/nano-ntp.v17i3.5444.

[40] Manik M M T G. An Analysis of Cervical Cancer using the Application of AI and Machine Learning. Journal of Medical and Health Studies, 2022, 3(2): 67-76. DOI: 10.32996/jmhs.2022.3.2.11.