# Integrating Machine Learning, Radio Frequency Identification, and Consignment Policy for Reducing Unreliability in Smart Supply Chain Management

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Contribution of Authors

#### 1.2. Problem Definition, Assumptions, and Notation

#### 1.2.1. Problem Definition

#### 1.2.2. Assumptions

- A supply chain management is considered with manufacturer and retailer as two players.
- Demand depends on the service b, and it is a decision variable.
- In the traditional model, the inventory is controlled by the retailer. In the ML-RFID model, the manufacturer controls the inventory by giving a fixed fee along with a commission to the retailer for each product sold.
- The lead time demand does not follow a known probability distribution function but it has a known value of the mean and standard deviation ([26]).
- As the retailer is unreliable, the manufacturer installs RFID technology at the retailer’s place to get real-time information about the inventory ([24]).
- The demand dataset consists of ten years of data, and $65\%$ of the data are taken as the training dataset while the remaining $35\%$ are taken as the test dataset.
- The data in the test set do not exist in the train set and the demand is always greater than zero.
- Using Stackelberg game theory, the manufacturer acts as a leader and controls the inventory. The retailer acts as a follower of the manufacturer ([27]).

#### 1.2.3. Notation

## 2. Traditional Model

#### 2.1. Retailer’s Traditional Model

**Lemma**

**1.**

**(i)**The expected quantity for overstock:

**(ii)**The expected quantity for understock:

#### 2.2. Manufacturer’s Traditional Model

#### 2.3. Total Expected Profit for the Traditional Model

## 3. Integrating ML, RFID, and Consignment Policy to Reduce Unreliability (ML-RFID Model)

#### 3.1. Forecasting Future Demand to Remove Uncertainty

#### Formulation of LSTM

#### 3.2. Retailer’s Expected Profit for the ML-RFID Model

#### 3.3. Manufacturer’s Expected Profit for the ML-RFID Model

#### 3.4. Total Expected Profit for the ML-RFID Model

## 4. Experimental Results

#### 4.1. Forecasting Using LSTM

#### 4.2. Numerical Analysis

#### 4.3. Sensitivity Analysis

## 5. Managerial Implications

## 6. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## Abbreviations

RFID | Radio Frequency Identification |

SCM | Supply Chain Management |

ML | Machine Learning |

LSTM | Long Short-Term Memory |

RNN | Recurrent Neural Network |

## Appendix A. Notation

**Decision variables**

${Q}_{r}$ | retailer’s order quantity (units) |

b | service by the retailer |

L | lead time (weeks) |

${e}_{\eta}$ | measurement for the environmental effect ($/unit) |

**Parameters**

p | each product’s retail price ($/unit) |

${h}_{r}^{TM}$ | retailer’s holding cost for the traditional model ($/unit/unit time) |

${s}_{r}^{TM}$ | retailer’s shortage cost for the traditional model ($/unit) |

${h}_{r}^{CM}$ | retailer’s holding cost for the ML-RFID model ($/unit/unit time) |

${s}_{r}^{CM}$ | retailer’s shortage cost for the ML-RFID model ($/unit) |

${h}_{m}^{CM}$ | manufacturer’s holding cost for the ML-RFID model ($/unit/unit time) |

${s}_{m}^{CM}$ | manufacturer’s shortage cost for the ML-RFID model ($/unit) |

k | manufacturing cost ($/unit) |

$\omega $ | wholesale price ($/unit) |

$\delta $ | standard deviation |

$\u03f5$ | cost of one RFID tag ($/unit) |

T | fixed cost for RFID implementation ($) |

a | scaling parameter |

$\gamma $ | shape parameter |

$\rho $ | scaling parameter |

$\beta $ | shape parameter |

$C\left(L\right)$ | lead time crashing cost |

A | fixed cost given by the manufacturer to retailer ($) |

$\theta $ | commission for each product sold ($/unit) |

**Other notation**

${\Pi}_{r}^{TM}$ | profit of retailer under the traditional model |

${\Pi}_{r}^{CM}$ | profit of retailer under the ML-RFID model |

${\Pi}_{m}^{TM}$ | profit of manufacturer under the traditional model |

${\Pi}_{m}^{CM}$ | profit of manufacturer under the ML-RFID model |

${\Pi}_{j}^{TM}$ | joint profit under the traditional model |

${\Pi}_{j}^{CM}$ | joint profit under the ML-RFID model |

${x}^{+}$ | maximum value of x and 0 |

$E(.)$ | mathematical expectation |

## Appendix B

## References

- Ru, J.; Wang, Y. Consignment contracting: Who should control inventory in the supply chain? Eur. J. Oper. Res.
**2010**, 201, 760–769. [Google Scholar] [CrossRef] - Taleizadeh, A.A.; Yadegari, M.; Sana, S.S. Production models of multiple products using a single machine under quality screening and reworking policies. J. Model. Manag.
**2019**, 14, 232–259. [Google Scholar] [CrossRef] - Gautam, P.; Kishore, A.; Khanna, A.; Jaggi, C.K. Strategic defect management for a sustainable green supply chain. J. Clean. Prod.
**2019**, 233, 226–241. [Google Scholar] [CrossRef] - Sarkar, M.; Sarkar, B. How does an industry reduce waste and consumed energy within a multi-stage smart sustainable biofuel production system? J. Clean. Prod.
**2020**, 262, 121200. [Google Scholar] [CrossRef] - Moon, I.; Shin, E.; Sarkar, B. Min–max distribution free continuous-review model with a service level constraint and variable lead time. Appl. Math. Comput.
**2014**, 229, 310–315. [Google Scholar] [CrossRef] - Shin, D.; Guchhait, R.; Sarkar, B.; Mittal, M. Controllable lead time, service level constraint, and transportation discounts in a continuous review inventory model. RAIRO-Oper. Res.
**2016**, 50, 921–934. [Google Scholar] [CrossRef] - Zhang, L.H.; Li, T.; Fan, T.J. Radio-frequency identification (RFID) adoption with inventory misplacement under retail competition. Eur. J. Oper. Res.
**2018**, 270, 1028–1043. [Google Scholar] [CrossRef] - Wu, L.; Yue, X.; Jin, A.; Yen, D.C. Smart supply chain management: A review and implications for future research. Int. J. Logist. Manag.
**2016**, 27, 395–417. [Google Scholar] [CrossRef] - Zhu, X.; Mukhopadhyay, S.K.; Kurata, H. A review of RFID technology and its managerial applications in different industries. J. Eng. Technol. Manag.
**2012**, 29, 152–167. [Google Scholar] [CrossRef] - Biswal, A.K.; Jenamani, M.; Kumar, S.K. Warehouse efficiency improvement using RFID in a humanitarian supply chain: Implications for Indian food security system. Transp. Res. Part E
**2018**, 109, 205–224. [Google Scholar] [CrossRef] - Perez, H.D.; Hubbs, C.D.; Li, C.; Grossmann, I.E. Algorithmic Approaches to Inventory Management Optimization. Processes
**2021**, 9, 102. [Google Scholar] [CrossRef] - Bhuniya, S.; Pareek, S.; Sarkar, B.; Sett, B.K. A Smart Production Process for the Optimum Energy Consumption with Maintenance Policy under a Supply Chain Management. Processes
**2020**, 9, 19. [Google Scholar] [CrossRef] - Abbasimehr, H.; Shabani, M.; Yousefi, M. An optimized model using LSTM network for demand forecasting. Comput. Ind. Eng.
**2020**, 143, 106435. [Google Scholar] [CrossRef] - Cirera, J.; Carino, J.A.; Zurita, D.; Ortega, J.A. A Data-Driven-Based Industrial Refrigeration Optimization Method Considering Demand Forecasting. Processes
**2020**, 8, 617. [Google Scholar] [CrossRef] - Choi, J.; Tosyali, A.; Kim, B.; Lee, H.S.; Jeong, M.K. A Novel Method for Identifying Competitors Using a Financial Transaction Network. IEEE Trans. Eng. Manag.
**2019**, 1–16. [Google Scholar] [CrossRef] - Carbonneau, R.; Laframboise, K.; Vahidov, R. Application of machine learning techniques for supply chain demand forecasting. Eur. J. Oper. Res.
**2008**, 184, 1140–1154. [Google Scholar] [CrossRef] - Scarf, H. A min-max solution of an inventory problem. In Studies in the Mathematical Theory of Inventory and Production; RAND Corporation: Santa Monica, CA, USA, 1993. [Google Scholar]
- Gallego, G.; Moon, I. The distribution free newsboy problem: Review and extensions. J. Oper. Res. Soc.
**1993**, 44, 825–834. [Google Scholar] [CrossRef] - Ouyang, L.Y.; Chen, C.K.; Chang, H.C. Quality improvement, setup cost and lead-time reductions in lot size reorder point models with an imperfect production process. Comput. Oper. Res.
**2002**, 29, 1701–1717. [Google Scholar] [CrossRef] - Dias, J.C.Q.; Calado, J.M.F.; Luís Osório, L.F.; Morgado, L.F. RFID together with multi-agent systems to control global value chains. Annu. Rev. Control
**2009**, 33, 185–195. [Google Scholar] [CrossRef] - Sarac, A.; Absi, N.; Dauzère-Pérès, S. A literature review on the impact of RFID technologies on supply chain management. Int. J. Prod. Econ.
**2010**, 128, 77–95. [Google Scholar] [CrossRef] - Kim, T.; Glock, C.H. On the use of RFID in the management of reusable containers in closed-loop supply chains under stochastic container return quantities. Transp. Res. Part E. Logist. Transp. Rev.
**2014**, 64, 12–27. [Google Scholar] [CrossRef] - Sarkar, B.; Zhang, C.; Majumder, A.; Sarkar, M.; Seo, Y.W. A distribution free newsvendor model with consignment policy and retailer’s royalty reduction. Int. J. Prod. Res.
**2018**, 56, 5025–5044. [Google Scholar] [CrossRef] - Guchhait, R.; Pareek, S.; Sarkar, B. How does a radio frequency identification optimize the profit in an unreliable supply chain management? Mathematics
**2019**, 7, 490. [Google Scholar] [CrossRef] [Green Version] - Sardar, S.K.; Sarkar, B. How Does Advanced Technology Solve Unreliability Under Supply Chain Management Using Game Policy? Mathematics
**2020**, 8, 1191. [Google Scholar] [CrossRef] - Cobb, B.R.; Johnson, A.W.; Rumí, R.; Salmerón, A. Accurate lead time demand modeling and optimal inventory policies in continuous review systems. Int. J. Prod. Econ.
**2015**, 163, 124–136. [Google Scholar] [CrossRef] - Pakseresht, M.; Mahdavi, I.; Shirazi, B.; Mahdavi-Amiri, N. Co-reconfiguration of product family and supply chain using leader-follower Stackelberg game theory: Bi-level multi-objective optimization. Appl. Soft Comput.
**2020**, 91, 106203. [Google Scholar] [CrossRef] - Alkahtani, M.; Omair, M.; Khalid, Q.S.; Hussain, G.; Sarkar, B. An Agricultural Products Supply Chain Management to Optimize Resources and Carbon Emission Considering Variable Production Rate: Case of Nonperishable Corps. Processes
**2020**, 8, 1505. [Google Scholar] [CrossRef] - Jemai, J.; Chung, B.D.; Sarkar, B. Environmental effect for a complex green supply-chain management to control waste: A sustainable approach. J. Clean. Prod.
**2020**, 277, 122919. [Google Scholar] [CrossRef] - Xia, X.; Zhang, C. The impact of authorized remanufacturing on sustainable remanufacturing. Processes
**2019**, 7, 663. [Google Scholar] [CrossRef] [Green Version] - Greff, K.; Srivastava, R.K.; Koutník, J.; Steunebrink, B.R.; Schmidhuber, J. LSTM: A search space odyssey. IEEE Trans. Neural Netw. Learn. Syst.
**2016**, 28, 41–49. [Google Scholar] [CrossRef] [Green Version] - Apaydin, H.; Feizi, H.; Sattari, M.T.; Colak, M.S.; Shamshirband, S.; Chau, K.W. Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting. Water
**2016**, 12, 1500. [Google Scholar] [CrossRef] - Zhang, D.; Gao, Z. Improvement of Refrigeration Efficiency by Combining Reinforcement Learning with a Coarse Model. Processes
**2019**, 7, 967. [Google Scholar] [CrossRef] [Green Version]

Author(s) | Smart | Inventory | Unreliability | RFID | Consignment | Machine |
---|---|---|---|---|---|---|

SCM | Control | Policy | Learning | |||

Scarf [17] | √ | |||||

Gallego and Moon [18] | √ | |||||

Ouyang et al. [19] | √ | |||||

Dias et al. [20] | √ | |||||

Sarac et al. [21] | √ | |||||

Kim and Glock [22] | √ | |||||

Sarkar et al. [23] | √ | √ | ||||

Guchhait et al. [24] | √ | √ | √ | |||

Sardar and Sarkar [25] | √ | √ | √ | √ | ||

This research | √ | √ | √ | √ | √ | √ |

Hyper-Parameter | Value |
---|---|

Visible layer | 1 visible layer with 1 input |

Hidden layer | 1 hidden layer with 4 blocks |

Learning rate | $0.01$ |

Number of iterations | 100 |

Batch size | 1 |

Activation function | Sigmoid |

Optimization algorithm | Adam |

Loss function | Mean Squared Error |

${\mathit{Q}}_{\mathit{r}}^{*}$ | ${\mathit{L}}^{*}$ | ${\mathit{b}}^{*}$ | ${\mathit{e}}_{\mathit{\eta}}^{*}$ | Expected Profit | |
---|---|---|---|---|---|

Traditional model | $1795.275$ | $3.000$ | $2.288$ | $96.587$ | 81,289.458 |

ML-RFID model | $2471.347$ | $3.000$ | $2.789$ | $65.433$ | 116,313.921 |

Parameter(s) | % Changes | Expected Profit Changes |
---|---|---|

p | $+50\%$ | $+164.052$ |

$+25\%$ | $+77.307$ | |

$-25\%$ | $-69.688$ | |

$-50\%$ | $-73.984$ | |

${h}_{r}^{CM}$ | $+50\%$ | $-4.129$ |

$+25\%$ | $-2.029$ | |

$-25\%$ | $+1.964$ | |

$-50\%$ | $+3.867$ | |

${s}_{r}^{CM}$ | $+50\%$ | $-7.583$ |

$+25\%$ | $-3.665$ | |

$-25\%$ | $+3.443$ | |

$-50\%$ | $+6.691$ | |

${h}_{m}^{CM}$ | $+50\%$ | $-38.159$ |

$+25\%$ | $-15.907$ | |

$-25\%$ | $+12.591$ | |

$-50\%$ | $+23.034$ | |

${s}_{m}^{CM}$ | $+50\%$ | $-9.090$ |

$+25\%$ | $-3.234$ | |

$-25\%$ | $+2.022$ | |

$-50\%$ | $+3.366$ | |

$\u03f5$ | $+50\%$ | $-1.056$ |

$+25\%$ | $-0.528$ | |

$-25\%$ | $+0.528$ | |

$-50\%$ | $+1.056$ | |

T | $+50\%$ | $-0.300$ |

$+25\%$ | $-0.150$ | |

$-25\%$ | $+0.150$ | |

$-50\%$ | $+0.300$ | |

k | $+50\%$ | $-26.434$ |

$+25\%$ | $-13.208$ | |

$-25\%$ | $+13.203$ | |

$-50\%$ | $+26.405$ |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Sardar, S.K.; Sarkar, B.; Kim, B.
Integrating Machine Learning, Radio Frequency Identification, and Consignment Policy for Reducing Unreliability in Smart Supply Chain Management. *Processes* **2021**, *9*, 247.
https://doi.org/10.3390/pr9020247

**AMA Style**

Sardar SK, Sarkar B, Kim B.
Integrating Machine Learning, Radio Frequency Identification, and Consignment Policy for Reducing Unreliability in Smart Supply Chain Management. *Processes*. 2021; 9(2):247.
https://doi.org/10.3390/pr9020247

**Chicago/Turabian Style**

Sardar, Suman Kalyan, Biswajit Sarkar, and Byunghoon Kim.
2021. "Integrating Machine Learning, Radio Frequency Identification, and Consignment Policy for Reducing Unreliability in Smart Supply Chain Management" *Processes* 9, no. 2: 247.
https://doi.org/10.3390/pr9020247