Open research questions in Forecasting Techniques and Applications

What the literature leaves open

• We presented KUP-BI, a knowledge-utilization paradigm that augments time series forecasting with a continuation- style auxiliary stream. The auxiliary stream is constructed from training-only chains using simple ratio-style trans- formations, and is fused with the main stream through a lightweight feature-level gated module. Across multiple datasets and backbones, KUP-BI achieves small but consis- tent error reductions with modest computational overhead, suggesting that leveraging post-target continuations from the training data provides a useful structural bias for long- horizon forecasting. KUP-BI also has limitations. First, the current retrieval strategy is relatively simple and does not explicitly handle phase shifts, which may lead to imperfect matches and noisy auxiliary signals. Although our design alleviates this issue to some extent by distilling relative evolution cues and using feature-level gating to suppress unreliable proxies (see Appendix E for an analysis of the relationship between retrieval quality and model gains), explicitly addressing phase shifts remains necessary to achieve better prediction accuracy. Second, to fully unlock its potential, KUP-BI may benefit from backbone-specific tuning rather than being a purely plug-and-play method. This can increase the training cost and may limit its direct applicability to large foundation models. Addressing these limitations will be an important direction for future work. KUP-BI

  Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting · 2026

• Investigating other approaches to improve the reliability of forecasts for extreme events, - Exploring the use of different scoring rules and their impact on forecast calibration

  Enforcing tail calibration when training probabilistic forecast models · 2026 · DOI

• State-of-the-art models do not issue calibrated forecasts for extreme events. The choice of scoring rule influences the behavior of the resulting forecasts. There is a need for strategies to reduce and better control variability in tail calibration.

  Enforcing tail calibration when training probabilistic forecast models · 2026 · DOI

• The gap is that traditional time series forecasting models do not account for dynamic covariates. The paper identifies the need to improve the predictive accuracy of these models by incorporating dynamic covariates.

  Leveraging temporal patterns in forecasting · 2026 · DOI

• Affective forecasting is often unreliable, especially when it comes to intensity and duration. It can both overestimate and underestimate our future emotional reactions. The paper identifies the challenge of understanding the direction of fit of affective forecasting and its implications for decision-making.

  The direction of fit of affective forecasting · 2026 · DOI

• The traditional view of affective forecasting as indicative is challenged. There is a lack of understanding of the direction of fit of affective forecasting. The paper identifies a gap in the understanding of affective forecasting and its implications for decision-making.

  The direction of fit of affective forecasting · 2026 · DOI

• Whether the same phenomenon emerges when the “crowd” consists of large language models (LLMs) is an open question with both theoretical and practical implications.

  Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles · 2026 · DOI

• The assumption that 50 percent of cotton imports are from developed countries and 50 percent from developing countries is a simplification that may not reflect actual trade patterns.

  Empirical and Machine Learning Forecasting for Offline Retail: Nonlinear Weather Effects and Heterogeneity · 2026 · DOI

• The need for improved inventory management in the energy sector. The lack of identification of the best forecasting models for different demand types.

  Combining demand classification and forecasting models in spare parts inventory management for the energy sector · 2026 · DOI

• Technical sectors should replace subjective model choices with multicriteria analysis methods such as CRITIC to ensure statistically robust selection based on variability and conflict of multiple metrics.

  Combining demand classification and forecasting models in spare parts inventory management for the energy sector · 2026 · DOI

• Rapid technological innovation and constant market fluctuations. Lack of historical sales data for new product launches. Accelerating product life cycles and globalized supply chains.

  Demand Forecasting Strategies for New Product Launches in the Consumer Electronics Sector: A 2025 Perspective · 2026 · DOI

• The study does not provide a comprehensive evaluation of the hybrid forecasting approach in different market conditions. The use of social media sentiment scores may be limited by the availability and quality of the data. The study does not provide a detailed analysis of the computational complexity of the hybrid forecasting approach.

  Demand Forecasting Strategies for New Product Launches in the Consumer Electronics Sector: A 2025 Perspective · 2026 · DOI

• This review is addressed to a broad readership: academic researchers and early career scholars tracing the intellectual and methodological history of the field, practitioners seeking reliable and transparent methods for operational forecasting, and management mathematicians and quantitative analysts from cognate disciplines—operational research, decision analytics, and management science—for whom benchmark forecasting methods constitute an essential but underexplored toolkit.

  Benchmarks in univariate time series forecasting: a historical and methodological review · 2026 · DOI

• Traditional demand forecasting methods have not fully addressed the challenges of food demand prediction. The consequences of inaccurate demand forecasting extend beyond financial impact, contributing to resource wastage, inefficient supply chains, and increased operational costs.

  An AI-Based Approach to Food Demand Forecasting Incorporating External Market Factors · 2026 · DOI

• The project identifies a gap in the development of a machine learning-based system that can forecast future sales based on historical data. The project aims to fill this gap by comparing the performance of different machine learning models in sales forecasting.

  Sales Forecast Prediction Using Machine Learning · 2026 · DOI

• Nonlinear dependencies and irregular demand patterns. Cold-start situations with limited historical records. Interpretability and scalability of machine learning models.

  Pharmaceutical Sales Forecasting using Machine Learning · 2026 · DOI

• Future research should focus on real-world applications of machine learning models for pharmaceutical sales forecasting. There is a need to address the limitations of machine learning models, such as interpretability and scalability.

  Pharmaceutical Sales Forecasting using Machine Learning · 2026 · DOI

• Most existing demand forecasting studies focus on improving predictive accuracy while neglecting human cognitive constraints. Existing attention-based forecasting models do not consider user-specific or context-aware factors. There is a need to integrate cognitive load modeling into deep learning-based forecasting frameworks.

  CLASNet: A Cognitive Load–Aware CNN-LSTM-Attention Framework for Supply Chain Demand Forecasting and Adaptive Human–Computer Interaction · 2026 · DOI

• The limitations of classical statistical approaches in handling complex trends and multiple seasonalities. The need for a comparative study of different forecasting models.

  Comparative Analysis of Statistical and Feature Based Time Series Forecasting Models on the BEED Dataset · 2026 · DOI

• The under-researched domain of inventory management in the Indian home-lift and elevator sector. The lack of a systematic inventory classification approach for the Indian elevator industry.

  Inventory Optimization Using FSN Analysis in Spare Parts Planning · 2026 · DOI

• Existing methods struggle with temporal misalignment of multi-source signals. Existing methods struggle with enforcing operational constraints. Limited work on constraint-aware forecasting frameworks for pallet demand forecasting.

  SC-DGLA: constraint-aware pallet demand forecasting with dynamic graph and learnable lag alignment · 2026 · DOI

• Traditional pricing methods are insufficient due to their static or rule-based nature, failing to reflect nonlinearities and swiftly changing market environments. Prior work has limitations in terms of demand forecasting and pricing optimization.

  Dynamic Price Allocation and Optimization for E-Commerce Platforms Using Reinforcement Learning and Deep Learning · 2026 · DOI

• Although the proposed Transformer-LSTM and Soft Actor- Critic based dynamic pricing framework demonstrates strong performance, several directions can be explored to further enhance its capabilities. Page 486 www.rsisinternational.org INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING, MANAGEMENT & APPLIED SCIENCE (IJLTEMAS) ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026 One important extension is the incorporation of multi-agent reinforcement learning, where multiple competing sellers dy- namically adjust prices in a shared market environment. This would enable the system to model realworld competitive pricing scenarios more effectively. Another promising direction is the integration of uncertainty-aware forecasting techniques, such as Bayesian deep learning or probabilistic Transformers, to better quantify prediction confidence and improve robustness under highly volatile demand conditions. The current system assumes a single-product or independent pricing setup. Future work can extend the framework to multi-product pricing with cross-elasticity modeling, where the demand of one product depends on the pricing of related products. In addition, fairness-aware pricing and ethical constraints can be incorporated to ensure that pricing strategies remain transparent and do not lead to unintended price discrimination or regulatory concerns. From a system perspective, deploying the framework in a real-world production environment with live user traffic would provide valuable insights into performance under real- time constraints. Integration with edge computing or streaming pipelines could further reduce latency and improve scalability. Finally, advanced techniques such as causal inference and offline reinforcement learning can be explored to improve sam- ple efficiency and enable learning from limited or historical data without requiring extensive online interaction. These directions provide opportunities to further improve the adaptability, robustness, and real-world applicability of dynamic pricing systems. REFERENCES 1) J. Liu et al., “Dynamic Pricing on E-Commerce Platform with Deep Reinforcement Learning: A Field Experiment,” arXiv preprint arXiv:1912.02572, 2021. 2) H. Yin and Q. Han, “Dynamic Pricing Model of E-Commerce Plat- forms Based on Deep Reinforcement Learning,” Computer Modeling in Engineering & Sciences, 2021. 3) J. Sun et al., “Dynamic Pricing Model for E-Commerce Products Based on DDQN,” 2024. A. Holovko and T. Firman, “Batch Reinforcement Learning for Dynamic Pricing,” 2021. 4) F. Lange et al., “Reinforcement Learning vs Dynamic Programming for Pricing,” 2025. 5) L. Guo and X. Zhang, “Dynamic Pricing using LSTM,” IEEE Access, 2025. 6) S. Kumar et al., “Weight Optimized LSTM for Pricing,” 2023. 7) L.

  Dynamic Price Allocation and Optimization for E-Commerce Platforms Using Reinforcement Learning and Deep Learning · 2026 · DOI

• Future research can focus on developing AI-driven solutions tailored to the dynamic nature of modern supply chains. Future research can explore the application of AI in demand forecasting in other sectors. Future research can investigate the use of explainable and ethical AI in demand forecasting.

  Investigating the role of using AI and machine learning for demand forecasting in supply chain management · 2026 · DOI

• The study identifies a gap in the current demand forecasting methods, which are not quick enough to accurately forecast demand in fast-changing markets. The study identifies a need for hybrid AI-driven models that can adapt to rapidly changing retail environments. The study identifies a lack of a single AI model capable of effectively forecasting demand across a wide range of products and industries.

  Investigating the role of using AI and machine learning for demand forecasting in supply chain management · 2026 · DOI

Most-cited papers in Forecasting Techniques and Applications

• Another look at measures of forecast accuracy · International Journal of Forecasting · 2006 · 4,646 citations
• Forecasting with artificial neural networks: · International Journal of Forecasting · 1998 · 3,315 citations
• DeepAR: Probabilistic forecasting with autoregressive recurrent networks · International Journal of Forecasting · 2019 · 2,287 citations
• Forecasting at Scale · The American Statistician · 2017 · 2,271 citations
• The Delphi technique as a forecasting tool: issues and analysis · International Journal of Forecasting · 1999 · 1,750 citations
• Forecasting Sales by Exponentially Weighted Moving Averages · Management Science · 1960 · 1,534 citations
• Forecasting and testing in co-integrated systems · Journal of Econometrics · 1987 · 1,240 citations
• Forecasting seasonals and trends by exponentially weighted moving averages · International Journal of Forecasting · 2004 · 1,229 citations
• 25 years of time series forecasting · International Journal of Forecasting · 2006 · 1,220 citations
• Recurrent Neural Networks for Time Series Forecasting: Current status and future directions · International Journal of Forecasting · 2020 · 1,115 citations

Most recent work

• Transformers for Multivariate Time Series Forecasting: Comprehensive Analysis, Challenges, Research Opportunities, and Future Prospects · IEEE Access · 2026
• The AI Energy-Demand Forecast Scorecard: a reproducible audit of how the field forecasts data-centre electricity demand · Zenodo (CERN European Organization for Nuclear Research) · 2026
• Recovery-informed forecasting strategy enhancement · Annals of Tourism Research · 2026
• Beyond forecast leaderboards: Measuring individual model importance based on contribution to ensemble accuracy · International Journal of Forecasting · 2026
• CLASNet: A Cognitive Load–Aware CNN-LSTM-Attention Framework for Supply Chain Demand Forecasting and Adaptive Human–Computer Interaction · Journal of Computer Science and Frontier Technologies · 2026
• Bayesian forecasting of zero-inflated time-series of counts · International Journal of Forecasting · 2026
• Improving high-frequency demand forecasts for omnichannel grocery retail · International Journal of Forecasting · 2026
• Empirical and Machine Learning Forecasting for Offline Retail: Nonlinear Weather Effects and Heterogeneity · Journal of Systems Science and Systems Engineering · 2026
• Combining demand classification and forecasting models in spare parts inventory management for the energy sector · The International Journal of Advanced Manufacturing Technology · 2026
• Simulation Studies on the Impact of Using Demand Forecasts Based on Deep Neural Networks for Inventory Replenishment Efficiency · Logforum · 2026

Related topics in Decision Sciences