Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting

2025-06-06

AI Summary

Retail sales forecasting in brick-and-mortar settings faces practical challenges including intermittent demand, missing values, and rapid SKU turnover—limiting the performance of existing global neural models. This paper proposes a localized modeling paradigm: instead of imputation, it dynamically clusters similar SKUs using tree-based models (XGBoost/LightGBM) guided by hierarchical grouping logic. We systematically demonstrate—for the first time—that, on high-resolution retail data, data preprocessing strategies—particularly the grouping logic—exert greater influence on both prediction accuracy (reducing MAPE by 12–28%) and computational efficiency (accelerating training by 5–20×) than model complexity. Extensive comparisons against state-of-the-art neural models (N-BEATS, NHITS, TFT) and multiple imputation-augmented variants confirm that tree-based models consistently outperform their imputation-enhanced neural counterparts. The work delivers an interpretable, lightweight, plug-and-play modeling framework and provides actionable guidelines for operational forecasting deployment in retail.

Technology Category

• Machine Learning: Ensemble Methods
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate forecasting is key for all business planning. When estimated sales are too high, brick-and-mortar retailers may incur higher costs due to unsold inventories, higher labor and storage space costs, etc. On the other hand, when forecasts underestimate the level of sales, firms experience lost sales, shortages, and impact on the reputation of the retailer in their relevant market. Accurate forecasting presents a competitive advantage for companies. It facilitates the achievement of revenue and profit goals and execution of pricing strategy and tactics. In this study, we provide an exhaustive assessment of the forecasting models applied to a high-resolution brick-and-mortar retail dataset. Our forecasting framework addresses the problems found in retail environments, including intermittent demand, missing values, and frequent product turnover. We compare tree-based ensembles (such as XGBoost and LightGBM) and state-of-the-art neural network architectures (including N-BEATS, NHITS, and the Temporal Fusion Transformer) across various experimental settings. Our results show that localized modeling strategies especially those using tree-based models on individual groups with non-imputed data, consistently deliver superior forecasting accuracy and computational efficiency. In contrast, neural models benefit from advanced imputation methods, yet still fall short in handling the irregularities typical of physical retail data. These results further practical understanding for model selection in retail environment and highlight the significance of data preprocessing to improve forecast performance.

Problem

• Compare ML models for accurate retail sales forecasting
• Address retail data issues like intermittent demand and missing values
• Evaluate tree-based vs neural models for forecasting performance

Innovation

• Comparative analysis of tree-based and neural models
• Localized modeling with non-imputed data
• Advanced imputation for neural network performance