A Profit Function-Maximizing Inventory Backorder Prediction System Using Big Data Analytics

Hájek, Petr; Abedin, Mohammad Zoynul

doi:10.1109/access.2020.2983118

Cited by 49 publications

(27 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shaikh et al [ 12 ] studied a fuzzy inventory model with allowable delayed payments considering inventory backlog and out-of-stock problem with the help of particle swarm algorithm. Hajek et al [ 13 ] constructed a maximized inventory backorder prediction system based on a machine learning model to improve the robustness of storage/inventory cost and sale profit variation. Simic et al [ 14 ] also proposed a particle swarm optimization and purely adaptive search global optimization algorithm for production inventory system model to minimize inventory quantity, value, and production cost.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Pharmaceutical Reagent Inventory Strategy Based on Contract Shelf Life and Patient Demand

Liu

Qian

Zhao

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

As the function and R&D level of in vitro diagnostic reagents continue to improve, the need for hospitals for in vitro diagnostic reagents in clinical diagnosis also keeps increasing. However, under the influence of management, process, technology, equipment, materials, employees, and other unexpected disturbing factors, the output of reagents often has random uncertainty, and it is difficult to provide the finished products required by orders on time, in quality and quantity. A secondary supply chain consisting of reagent manufacturers, distributors, and hospitals is constructed, and the inventory control models of in vitro diagnostic reagent supply chain under three strategies of centralized decision-making, hospital-owned inventory, and reagent distributor-managed inventory are established, respectively, and the maximum expected returns of the supply chain system under different strategies are analyzed to achieve the optimal production decision of reagent manufacturers and the optimal procurement decision of hospitals. The results show that reducing the random output probability and patient demand uncertainty has a significant effect on improving the expected return of in vitro diagnostic reagent supply chain, and as the random output probability of reagent manufacturers and patient consumption demand uncertainty increase, the strategy of managing inventory by distributors in collaboration is always better than the strategy of managing inventory by hospitals' own warehouses, which can achieve higher expected return and better inventory quantity, but when the out-of-stock cost of hospitals is too high above a certain threshold, the hospital will tend to adopt the self-inventory strategy.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Pharmaceutical Reagent Inventory Strategy Based on Contract Shelf Life and Patient Demand

Liu

Qian

Zhao

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Oversampling techniques reduce class inequity by generating new minority class instances. Contrary to oversampling techniques, undersampling procedures reshape class inequity by decreasing the number of positive class instances [29]. Besides oversampling and undersampling techniques, this study presents the hybrid data-level solutions RUSSMOTE, MChanUS, and USOS to show the effect of different forms of imbalance learning.…”

Section: Class Imbalance Problemmentioning

confidence: 99%

Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk

Abedin

Chi

Hájek

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The proposed ensemble classifier hybridizes WSMOTE and Bagging with sampling composite mixtures to guarantee the robustness and variability of the generated synthetic instances and, thus, minimize the small business class-skewed constraints linked to default and nondefault instances. The original small business dataset used in this study was taken from 3111 records from a Chinese commercial bank. By implementing a thorough experimental study of extensively skewed data-modeling scenarios, a multilevel experimental setting was established for a rare event domain. Based on the proper evaluation measures, this study proposes that the random forest classifier used in the WSMOTE-ensemble model provides a good trade-off between the performance on default class and that of nondefault class. The ensemble solution improved the accuracy of the minority class by 15.16% in comparison with its competitors. This study also shows that sampling methods outperform nonsampling algorithms. With these contributions, this study fills a noteworthy knowledge gap and adds several unique insights regarding the prediction of small business credit risk.

show abstract

“…It is utilized for forecasting the demand for spare parts (S. Li & Kuo, 2008). Backorder prediction is traditionally based on stochastic approximation, thus overlooking the substantial amount of useful information hidden in historical inventory data (Hajek & Abedin, 2020). Ensemble learning approaches and specific metrics are proposed for identifying parts with the highest chances of shortage prior to its occurrence (de Santis et al, 2017).…”

Section: Inventory and Logisticsmentioning

confidence: 99%

AI-enabled Enterprise Information Systems for Manufacturing

Zdravković

Panetto

Weichhart

2021

Enterprise Information Systems

View full text Add to dashboard Cite

Research work presented in this paper considers the contemporary Enterprise Information Systems (EIS) functional architecture and carries out the literature review of AI applications integrated in Customer Relationship Management, Supply Chain Management, Inventory and logistics, Production Planning and Scheduling, Finance and accounting, Product Lifecycle Management and Human Resources, with special attention to the manufacturing enterprises. As a review outcome, the enhanced capabilities are identified in each of those processes and proposed as AI services. AI-enablement is related to the capabilities of the enterprise to implement improved decision making or automation by using (a) Machine Learning (ML) models or (b) logicbased systems. It is a process of the enterprise transformation leading to the convergence of the 4 major disruptive technologies, namely Industrial Internet of Things (or Cyber-Physical Systems), Agent-based Distributed Systems, Cloud Computing and Artificial Intelligence (non-symbolic AI like Machine Learning, Neural Networks; symbolic AI like Reasoning and Logic/Model-based AI).

show abstract

A Profit Function-Maximizing Inventory Backorder Prediction System Using Big Data Analytics

Cited by 49 publications

References 64 publications

[Retracted] Pharmaceutical Reagent Inventory Strategy Based on Contract Shelf Life and Patient Demand

[Retracted] Pharmaceutical Reagent Inventory Strategy Based on Contract Shelf Life and Patient Demand

Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk

AI-enabled Enterprise Information Systems for Manufacturing

Contact Info

Product

Resources

About