Home / Current Issue / Paper 1722411
Data-Driven Financial Reporting and Forecasting for Small and Mid-Sized Enterprises: A Practical Framework for Decision-Ready Accounting Analytics
Subject area: Management and Commerce · Area of research: Accounting and Auditing
DOI: 10.64388/IREV10I2-1722411
Abstract
This study develops and empirically illustrates a practical accounting-analytics framework for improving the quality, timeliness, and decision usefulness of financial reporting and short-horizon forecasting in small and mid-sized enterprises (SMEs). The paper responds to a persistent challenge in the SME literature: many firms operate with fragmented transaction records, limited management-accounting adoption, weak reconciliation discipline, and highly reactive budgeting routines, even though they face acute pressure to make fast, informed operating decisions. Using the Online Retail II transaction dataset accessed through Kaggle and originally archived by the UCI Machine Learning Repository the study constructs a decision-ready reporting layer based on gross revenue, returns, net revenue, order activity, customer activity, concentration patterns, and short-term forecast baselines. A cleaned sample of 1,041,670 positive sales rows and 19,494 cancellation/return rows was aggregated into a 24-month management dashboard and tested with simple forecast models appropriate for SME settings. The results show pronounced seasonality, material return-rate variation, and strong associations between net revenue and operational demand indicators such as orders and active customers. A Holt linear model produced the best out-of-sample performance over the last six months of the sample, with a MAPE of 11.47%, outperforming both a naïve benchmark and a trailing moving-average approach. The paper translates these findings into a five-layer framework covering transaction capture and reconciliation, diagnostic reporting, liquidity visibility, rolling forecasting, and governance cadence. The contribution is therefore both analytical and practical: it shows how SME finance functions can move from static compliance reporting toward integrated, decision-ready accounting analytics without requiring overly complex systems.
Keywords
SMEs; financial reporting; forecasting; management accounting; dashboard analytics; liquidity monitoring; variance analysis.
References
[1] Ayankoya, M.B., Omotoso, S.S., Ogunlana, A.A. et al. (2025) ‘Data Driven Financial Optimization for Small and Medium Enterprises (SMEs): A Framework to Improve Efficiency and Resilience in U.S. Local Economies’, International Journal of Management and Organizational Research, 4(4), pp. 90–97. doi: 10.54660/IJMOR.2025.4.4.90-97.
[2] Chen, D. (2012) Online Retail II [Dataset]. UCI Machine Learning Repository. doi: 10.24432/C5CG6D.
[3] Ciampi, F., Giannozzi, A., Marzi, G. and Altman, E.I. (2021) ‘Rethinking SME default prediction: a systematic literature review and future perspectives’, Scientometrics, 126, pp. 2141–2188. doi: 10.1007/s11192-020-03856-0.
[4] Franke, F. and Hiebl, M.R.W. (2023) ‘Big data and decision quality: the role of management accountants’ data analytics skills’, International Journal of Accounting and Information Management, 31(1), pp. 93–127. doi: 10.1108/IJAIM-12-2021-0246.
[5] Gonçalves, C.T., Gonçalves, M.J.A. and Campante, M.I. (2023) ‘Developing Integrated Performance Dashboards Visualisations Using Power BI as a Platform’, Information, 14(11), 614. doi: 10.3390/info14110614.
[6] Jenčová, S., Vašaničová, P., Košíková, M. and Miškufová, M. (2025) ‘A Time Series Approach to Forecasting Financial Indicators in the Wholesale and Retail Trade’, World, 6(1), article 5. doi: 10.3390/world6010005.
[7] Kaggle (n.d.) Online Retail II UCI. Available at: https://www.kaggle.com/datasets/mashlyn/online-retail-ii-uci (Accessed: 21 June 2026).
[8] Netshifhefhe, K., Netshifhefhe, M.V., Mupa, M.N. and Murapa, K.A. (2024) ‘The Role of Forensic Audits in Strengthening Corporate Governance and Mitigating Compliance Risks’, Iconic Research and Engineering Journals, 8(4), pp. 427–445.
[9] Nhemachena, T.L., Shambare, A.M., Kufandada, D., Chingezi, E., Taanisa, T., Yelduora, P.G., Chawatama, B. and Mupa, M.N. (2026) ‘Data-driven budget control, cash-flow visibility, and receivables optimization for U.S. small businesses: A practical accounting-analytics framework’, World Journal of Advanced Research and Reviews, 30(1). doi: 10.30574/wjarr.2026.30.1.1164.
[10] OECD (2024) Financing SMEs and Entrepreneurs 2024: An OECD Scoreboard. Paris: OECD Publishing. doi: 10.1787/fa521246-en.
[11] Sastararuji, D., Hoonsopon, D., Pitchayadol, P. and Chiwamit, P. (2022) ‘Cloud accounting adoption in Thai SMEs amid the COVID-19 pandemic: an explanatory case study’, Journal of Innovation and Entrepreneurship, 11, 43. doi: 10.1186/s13731-022-00234-3.
[12] SBA Office of Advocacy (2026) Frequently Asked Questions About Small Business 2026. Washington, DC: U.S. Small Business Administration.
[13] Wang, W. and Guedes, M.J. (2025) ‘Firm failure prediction for small and medium-sized enterprises and new ventures’, Review of Managerial Science, 19(7). doi: 10.1007/s11846-024-00742-4.
[14] Ylä-Kujala, A., Kouhia-Kuusisto, K., Ikäheimonen, T., Laine, T. and Kärri, T. (2023) ‘Management accounting adoption in small businesses: interfaces with challenges and performance’, Journal of Accounting & Organizational Change, 19(6), pp. 46–69. doi: 10.1108/JAOC-07-2022-0100.
How to cite this paper
@article{1722411,
author = {Ashley Munashe Shambare, Nelia Mlambo, Melody Rachael Chitukutuku, Deline Kufandada, Munashe Naphtali Mupa},
title = {Data-Driven Financial Reporting and Forecasting for Small and Mid-Sized Enterprises: A Practical Framework for Decision-Ready Accounting Analytics},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {2130-2139},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1722411.pdf},
abstract = {This study develops and empirically illustrates a practical accounting-analytics framework for improving the quality, timeliness, and decision usefulness of financial reporting and short-horizon forecasting in small and mid-sized enterprises (SMEs). The paper responds to a persistent challenge in the SME literature: many firms operate with fragmented transaction records, limited management-accounting adoption, weak reconciliation discipline, and highly reactive budgeting routines, even though they face acute pressure to make fast, informed operating decisions. Using the Online Retail II transaction dataset accessed through Kaggle and originally archived by the UCI Machine Learning Repository the study constructs a decision-ready reporting layer based on gross revenue, returns, net revenue, order activity, customer activity, concentration patterns, and short-term forecast baselines. A cleaned sample of 1,041,670 positive sales rows and 19,494 cancellation/return rows was aggregated into a 24-month management dashboard and tested with simple forecast models appropriate for SME settings. The results show pronounced seasonality, material return-rate variation, and strong associations between net revenue and operational demand indicators such as orders and active customers. A Holt linear model produced the best out-of-sample performance over the last six months of the sample, with a MAPE of 11.47%, outperforming both a naïve benchmark and a trailing moving-average approach. The paper translates these findings into a five-layer framework covering transaction capture and reconciliation, diagnostic reporting, liquidity visibility, rolling forecasting, and governance cadence. The contribution is therefore both analytical and practical: it shows how SME finance functions can move from static compliance reporting toward integrated, decision-ready accounting analytics without requiring overly complex systems.},
keywords = {SMEs; financial reporting; forecasting; management accounting; dashboard analytics; liquidity monitoring; variance analysis.},
month = {August},
doi = {https://doi.org/10.64388/IREV10I2-1722411}
}