cs.LGApr 2, 2026

Bridging Deep Learning and Integer Linear Programming: A Predictive-to-Prescriptive Framework for Supply Chain Analytics

Authors: Khai Banh Nghiep, Duc Nguyen Minh, Lan Hoang Thi

Organizations: Tran Dai Nghia Secondary and High School, Vietnam · AI engineer Vietnam · University of Languages and International studies

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Although demand forecasting is a critical component of supply chain planning, actual retail data can exhibit irreconcilable seasonality, irregular spikes, and noise, rendering precise projections nearly unattainable. This paper proposes a three-step analytical framework that combines forecasting and operational analytics. The first stage consists of exploratory data analysis, where delivery-tracked data from 180,519 transactions are partitioned, and long-term trends, seasonality, and delivery-related attributes are examined. Secondly, the forecasting performance of a statistical time series decomposition model N-BEATS MSTL and a recent deep learning architecture N-HiTS were compared. N-BEATS and N-HiTS were both statistically, and hence were N-BEATS's and N-HiTS's statistically selected. Most recent time series deep learning models, N-HiTS, N-BEATS. N-HiTS and N-BEATS N-HiTS and N-HiTS outperformed the statistical benchmark to a large extent. N-BEATS was selected to be the most optimized model, as the one with the lowest forecasting error, in the 3rd and final stage forecasting values of the next 4 weeks of 1918 units, and provided those as a model with a set of deterministically integer linear program outcomes that are aimed to minimize the total delivery time with a set of bound budget, capacity, and service constraints. The solution allocation provided a feasible and cost-optimal shipping plan. Overall, the study provides a compelling example of the practical impact of precise forecasting and simple, highly interpretable model optimization in logistics.

More in this topic

Supply Chain Optimization

See all 19 papers

Explore similar work

CardsList
Mar 17, 2026

Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost

This study develops a digitalized forecasting-inventory optimization pipeline integrating traditional forecasting models, machine learning regressors, and deep sequence models within a unified inventory simulation framework. Using the M5 Walmart dataset, we evaluate seven forecasting approaches and assess their operational impact under single- and two-echelon newsvendor systems. Results indicate that Temporal CNN and LSTM models significantly reduce inventory costs and improve fill rates compared to statistical baselines. Sensitivity and multi-echelon analyses demonstrate robustness and scalability, offering a data-driven decision-support tool for modern supply chains.

Swata Marik, Swayamjit Saha, Garga Chatterjee

Department of Home Science, University of Calcutta, 20 E, Judges Court Road, Alipore, Kolkata, 700027, West Bengal, India. · Department of Computer Science and Engineering, Mississippi State University, 665 George Perry Street, Starkville, 39759, MS, USA. · Psychology Research Unit, Indian Statistical Institute Kolkata, 203, B.T. Road, Kolkata, 700108, West Bengal, India.

Inventory ControlTime Series ForecastingForecasting Benchmarks
AskPDF
Apr 23, 2026

Hybrid Deep Learning Approach for Coupled Demand Forecasting and Supply Chain Optimization

Supply chain resilience and efficiency are vital in industries characterized by volatile demand and uncertain supply, such as textiles and personal protective equipment (PPE). Traditional forecasting and optimization approaches often operate in isolation, limiting their real-world effectiveness. This paper proposes a Hybrid AI Framework for Demand-Supply Forecasting and Optimization (HAF-DS), which integrates a Long Short-Term Memory (LSTM)-based demand forecasting module with a mixed integer linear programming (MILP) optimization layer. The LSTM captures temporal and contextual demand dependencies, while the optimization layer prescribes cost-efficient replenishment and allocation decisions. The framework jointly minimizes forecasting error and operational cost through embedding-based feature representation and recurrent neural architectures. Experiments on textile sales and supply chain datasets show significant performance gains over statistical and deep learning baselines. On the combined dataset, HAF-DS reduced Mean Absolute Error (MAE) from 15.04 to 12.83 (14.7%), Root Mean Squared Error (RMSE) from 19.53 to 17.11 (12.4%), and Mean Absolute Percentage Error (MAPE) from 9.5% to 8.1%. Inventory cost decreased by 5.4%, stockouts by 27.5%, and service level rose from 95.5% to 97.8%. These results confirm that coupling predictive forecasting with prescriptive optimization enhances both accuracy and efficiency, providing a scalable and adaptable solution for modern textile and PPE supply chains.

Nusrat Yasmin Nadia, Md Habibul Arif, Habibor Rahman Rabby +3

Department of Information Technology, Washington University of Science and Technology, , Alexandria, 22314, VA, USA · Department of Information Technology, University of the Potomac, , Washington, D.C., 20005, DC, USA · Department of Computer Science, Campbellsville University, , Louisville, 40220, KY, USA +2

Time Series ForecastingSupply Chain Optimization
AskPDF
Jun 6, 2026

Integrating Deep Learning Demand Forecasting with Multi-Objective Optimization for Circular Coffee Supply Chains: A Data-Driven Framework for Cost, Emissions, and Freshness Management

The coffee supply chain is one of the most complex agri-food networks, marked by geographically dispersed production, multi-tier coordination, and high sensitivity to quality and freshness. While sustainability and digitalization have gained attention, demand forecasting, optimization, and traceability are often treated separately. This study presents a two-phase integrated framework. First, a hybrid CNN-LSTM model is used for demand forecasting. On the public Coffee Chain Sales dataset with chronological 70/15/15 splitting, the model achieves MAE of 22.87 and R^2 of 0.90, outperforming the best deep learning benchmark by ~12% and classical methods by over 30%. In the second phase, the forecasted demand feeds a tri-objective mixed-integer linear programming (MILP) model that jointly minimizes cost, minimizes carbon emissions, and maximizes product freshness in a multi-period, multimodal, closed-loop supply chain with circular recovery. Freshness is modeled via exponential decay based on inventory age. Using the epsilon-constraint method, 25 Pareto solutions are obtained. Sensitivity and policy analyses show that balanced sustainability policies can reduce emissions by 22.4% with only a 9.9% cost increase while maintaining near-optimal freshness. Keywords: Coffee supply chain; Deep learning; Demand forecasting; Multi-objective optimization; Circular economy; CNN-LSTM; Mixed-integer linear programming.

Gerçek Budak, Faraz Gholamzadeh Gharehgheshlaghi, Melika Barjesteh Vaezi +1

Department of Industrial Engineering, Ankara Yıldırım Beyazıt University, Keçiören, Ankara 06010, Türkiye · Department of Kinesiology and Sport Management, Texas Tech University, Lubbock, TX, United States · Department of Civil, Construction, and Environmental Engineering, University of Alabama, Tuscaloosa, AL, USA

Time Series ForecastingCombinatorial OptimizationSupply Chain OptimizationSupply Chain ManagementMulti-Objective Optimization
AskPDF