Improving business process performance in SMEs through predictive modeling: a comparative study of statistical and machine learning models
Bibliographic record
Abstract
Purpose This study investigates how predictive modeling can improve business process performance in small and medium-sized enterprises (SMEs) by enhancing demand forecasting. This paper examines statistical, machine learning and hybrid models to support process improvement by forecasting business outcomes, enabling data-driven decision-making. Using real-world data from a make-to-stock SME in the manufacturing sector, the research identifies context-aware forecasting strategies that align with business triggers and can be practically implemented without requiring extensive digital infrastructure. Design/methodology/approach A quantitative, comparative modeling approach is applied to real-world demand data from make-to-stock items, with a range of forecasting models evaluated using hyperparameter tuning. These models incorporate both endogenous demand trends and exogenous variables, and the results are critically assessed through a business process lens to evaluate practical relevance, scalability and workflow integration potential. Findings Hybrid and ensemble models, particularly Random Forest Regressor and Multi-Prophet, consistently outperform statistical approaches in forecasting non-linear, event-driven demand patterns. Feature-importance analysis confirms that episodic business events are stronger demand drivers than macroeconomic indicators, especially in project-based supply chains. Originality/value Drawing on operational data from an SME, this research moves beyond accuracy to focus on practical implementation, interpretability and process alignment. It positions predictive modeling as a decision-support subprocess embedded in SME operations, offering a replicable framework for data-driven forecasting in resource-constrained, real-world environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".