.png){kind=icon}
.png){kind=icon}
Return
Machine learning-driven demand forecasting for multi-objective sustainable inventory control under uncertainty
.png){kind=icon}
PRE
AI
A
M
S
S
G
DOI：10.1080/17509653.2026.2658608.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the face of increasing uncertainty and sustainability challenges, inventory management must develop to balance financial, environmental, and social objectives. This study presents a multi-objective sustainable inventory model that integrates machine learning for demand prediction, addressing uncertainty through robust programming. By using machine learning techniques, demand forecasting is made more accurate, even under uncertain conditions, improving decision-making in inventory control. Preservation and green technologies are employed to reduce product deterioration and decrease carbon emissions. Additionally, the model accounts for the influence of inflation on costs, ensuring financial sustainability over time. Weighted goal programming approach is adopted to address three key objectives: maximum profit, increasing labour payment and decreasing carbon emissions. This method allows for balancing the conflicting goals by optimizing inventory levels, ultimately promoting sustainability while ensuring labour payments and emissions. The results demonstrate that the proposed model can successfully achieve sustainable and social responsible inventory management, and the proposed model is the superior model of traditional model. Sensitivity analyses are conducted to assess the robustness of the proposed model under varying parameters, providing valuable insights for decision-makers. The study concludes with a discussion of the findings and suggestions for future research directions.
Keywords:
Economic production quantity
multi-objective optimization
carbon emissions
goal and robust programming
machine learning
M11
M37
Journal
IF:
2.6
Papers:
237
Citations:
739
Organization
Cited Papers