Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain
Abstract
:1. Introduction
- 1)
- This paper implements a credit evaluation system that adopts blockchain technology to strengthen the supervision and management of traders in food supply chain. The whole flow of processing logic about the system is given by smart contracts which are written by “chaincode” [11].
- 2)
- The system applies Hyperledger blockchain [14] to meet the challenges of the different authentications and permissions needed for different roles (traders and regulators) in the food supply chain. It also ensures that traders can be held accountable for the credit evaluation process while traders’ (or evaluators’) real identities remain anonymous.
- 3)
- The merge system is responsible for combining blockchain technology and a deep learning model LSTM [15]. It adopts a trained LSTM model to directly analyze and process the gathered credit evaluation text about traders. Finally the credit evaluation results of traders are generated and the results fed back to regulators.
2. Materials and Methods
2.1. System Design Decision
2.1.1. Hyperledger Blockchain
- The nodes of traders mainly respond to block generation and credit evaluation generation when transactions are completed.
- Traders keep the records of transactions related to themselves.
- The nodes of regulators perform checking at regular intervals (for example, a week) from all nodes of traders to supervise and mange traders in the food supply chain.
- Regulators have the highest authority to manage the authentication, authorization and monitoring of traders. They can access and manage all information of traders in a blockchain.
- Regulators maintain the complete records of traders including the transaction and credit evaluation information.
- 1)
- Transparency and tamper-resistance. Blockchain consists of a continuously growing list of records, called blocks, which are linked and secured using cryptography. Each block typically contains a hash pointer as a link to a previous block, a timestamp and transaction data. All information of traders or transactions are stored in blocks. They are public to regulators and can hardly be modified. This can effectively avoid the risk arising from “information asymmetry” [17] in the supply chain.
- 2)
- Accountability and privacy. The credit evaluation system based on blockchain provides a reliable platform to collect information of transaction and credit evaluation. Traders’ identities are anonymous during the evaluation process. Thus they don’t have to worry about their identities being exposed or the contents of their comments leaked, which enhances users’ confidence. On the other hand, traders on the blockchain can be held accountable for their actions in the process of transaction or credit evaluation because of the transparent and tamper-resistant information provided.
- 3)
- Authorization and permission. The features of the consortium blockchain Hyperledger can provide different access control permissions via the CA. Regulators acquire higher authority than ordinary nodes of traders in the system based on Hyperledger blockchain, making it more suitable for regulators to supervise and manage traders in the food supply chain.
- 4)
- Chaincode. Hyperledger Fabric provides the logic of the system by smart contracts. Smart contracts run on the blockchain-based virtual machine and can be automatically executed by calling “chaincode”. Chaincode provides a variety of functions to invoke, update or query the data stored in the ledger. It can more quickly meet the needs of users and it is more effective for integrating regulators’ work into existing systems with a minimum of cost. In the system, traders complete the transaction and credit evaluation by chaincode. Regulators also call chaincode to query a transaction or gather the credit evaluation text of traders.
2.1.2. LSTM Method for Credit Evaluation
2.2. Workflow of the Credit Evaluation System
- 1)
- Traders A and B complete a food trading transaction such as a sale of vegetables and fruit based on blockchain.
- 2)
- Trader B gives a credit evaluation to his trading partner A based on his satisfaction with his purchases, logistics service quality and food quality during the trade.
- 3)
- Collect the credit evaluation text of A at regular intervals (e.g., a week). These credit evaluation texts may be given by B, C and so on.
- 4)
- Input the gathered credit evaluation text into the trained LSTM model to analyze the sentiments of these texts.
- 5)
- The LSTM model outputs a credit evaluation result as “positive” or “negative”. For example, if A received more reviews like “The fruit doesn’t look very fresh”, “Its service is awful” or “The logistics service is a little bit slower”, then these texts are input into the trained LSTM model and the model will output a “negative” result for A.
- 6)
- The same steps 2 to 5 are performed by the other trader B.
- 7)
- Regulators periodically monitor and check traders’ credit evaluation results. They can verify the results and take corresponding measures in time.
3. Results
3.1. The Interface of the Integrated System and the Experimental Environment
3.2. The Implementation of Smart Contracts
3.3. The Implementation of LSTM Model
3.3.1. Experimental Dataset
3.3.2. Evaluation Metrics
3.3.3. Evaluation Results of the Experiments
4. Discussion
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Madichie, N.O.; Yamoah, F.A. Revisiting the European Horsemeat Scandal: The Role of Power Asymmetry in the Food Supply Chain Crisis. Thunderbird Int. Bus. Rev. 2017, 59, 663–675. [Google Scholar] [CrossRef]
- Wu, M.Y.C.; Hsu, M.Y.; Chen, S.J.; Hwang, D.K.; Yen, T.H.; Cheng, C.M. Point-of-Care Detection Devices for Food Safety Monitoring: Proactive Disease Prevention. Trends Biotechnol. 2017, 35, 288–300. [Google Scholar] [CrossRef] [PubMed]
- Bombaywala, M.; Riandita, A. Stakeholders’ collaboration on innovation in food industry. Procedia Soc. Behav. Sci. 2015, 169, 395–399. [Google Scholar] [CrossRef]
- Peng, Y.; Li, J.; Xia, H.; Qi, S.; Li, J. The effects of food safety issues released by we media on consumers’ awareness and purchasing behavior: A case study in China. Food Policy 2015, 51, 44–52. [Google Scholar] [CrossRef]
- Deng, A.; Chen, Z. Managing Online Supply Chain finance Credit Risk of “Asymmetric Information”. World J. Res. Rev. 2017, 4, 29–32. [Google Scholar]
- Tian, F. A supply chain traceability system for food safety based on HACCP, blockchain & Internet of things. In Proceedings of the 2017 14th International Conference on Services Systems and Services Management (ICSSSM), Dalian, China, 16–19 June 2017. [Google Scholar]
- Tian, F. An agri-food supply chain traceability system for China based on RFID & blockchain technology. In Proceedings of the 2016 13th International Conference on Service Systems and Service Management (ICSSSM), Kunming, China, 24–26 June 2016. [Google Scholar]
- Hofmann, E.; Strewe, U.M.; Bosia, N. Concept–Where Are the Opportunities of Blockchain–Driven Supply Chain Finance? In Supply Chain Finance and Blockchain Technology; Springer: Berlin, Germany, 2018; pp. 51–75. [Google Scholar]
- Foth, M. The promise of blockchain technology for interaction design. In Proceedings of the 29th Australian Conference on Computer-Human Interaction, Brisbane, Australia, 28 November–1 December 2017; pp. 513–517. [Google Scholar]
- Di Pierro, M. What Is the Blockchain? Comput. Sci. Eng. 2017, 19, 92–95. [Google Scholar] [CrossRef]
- Holotescu, C. Understanding Blockchain Opportunities and Challenges. eLearn. Softw. Educ. 2018, 4, 276–283. [Google Scholar]
- Kim, H.M.; Laskowski, M. Toward an ontology-driven blockchain design for supply-chain provenance. Intell. Syst. Account. Finance Manag. 2018, 25, 18–27. [Google Scholar] [CrossRef]
- Lu, Q.; Xu, X. Adaptable Blockchain-Based Systems: A Case Study for Product Traceability. IEEE Softw. 2017, 34, 21–27. [Google Scholar] [CrossRef]
- Cachin, C. Architecture of the Hyperledger blockchain fabric. In Proceedings of the Workshop on Distributed Cryptocurrencies and Consensus Ledgers, Chicago, IL, USA, 25–29 July 2016. [Google Scholar]
- Chen, H.; Li, S.; Wu, P.; Yi, N.; Li, S.; Huang, X. Fine-grained Sentiment Analysis of Chinese Reviews Using LSTM Network. J. Eng. Sci. Technol. Rev. 2018, 11, 5. [Google Scholar] [CrossRef]
- Tiedan, W.; Xue, L.; Dinghong, P. A Research on Quality Credit Evaluation System of Food Enterprises Based on Picture Fuzzy Sets. J. Kunming Univ. Sci. Technol. Soc. Sci. Ed. 2015, 15, 59–67. [Google Scholar]
- Nakasumi, M. Information sharing for supply chain management based on block chain technology. In Proceedings of the 2017 IEEE 19th Conference on Business Informatics (CBI), Thessaloniki, Greece, 24–27 July 2017; pp. 140–149. [Google Scholar]
- Cambria, E.; Poria, S.; Gelbukh, A.; Thelwall, M. Sentiment analysis is a big suitcase. IEEE Intell. Syst. 2017, 32, 74–80. [Google Scholar] [CrossRef]
- Liao, S.; Wang, J.; Yu, R.; Sato, K.; Cheng, Z. CNN for situations understanding based on sentiment analysis of twitter data. Procedia Comput. Sci. 2017, 111, 376–381. [Google Scholar] [CrossRef]
- Liang, W.; Zhang, Q. Research of Electronic Commerce Credit Model on the Basis of Dynamic Game Analysis. J. Shandong Univ. Sci. Technol. Soc. Sci. 2017, 19, 74–83. [Google Scholar]
- Ding, Q.; Li, Z.; Batta, P.; Trajković, L. Detecting BGP anomalies using machine learning techniques. In Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary, 9–12 October 2016; pp. 003352–003355. [Google Scholar]
- Peng, H.; Ma, Y.; Li, Y.; Cambria, E. Learning multi-grained aspect target sequence for Chinese sentiment analysis. Knowl.-Based Syst. 2018, 148, 167–176. [Google Scholar] [CrossRef]
- Cheung, D.; Sit, D. Services in Global Value Chains and the Impact of Policy. In The Intangible Economy: How Services Shape Global Production and Consumption; Cambridge University Press: Cambridge, UK, 2017; p. 167. [Google Scholar]
- Nakamoto, S. Bitcoin: A Peer-To-Peer Electronic Cash System. 2009. Available online: https://bitcoin.org/bitcoin.pdf (accessed on 9 January 2009).
- Moreno-Sanchez, P.; Zafar, M.B.; Kate, A. Listening to whispers of ripple: Linking wallets and deanonymizing transactions in the ripple network. Proc. Priv. Enhanc. Technol. 2016, 2016, 436–453. [Google Scholar] [CrossRef]
- Ayed, A.B.; Belhajji, M.B. The Blockchain Technology: Applications and Threats. Int. J. Hyperconnect. Internet Things 2017, 1, 1–11. [Google Scholar] [CrossRef]
- Fernández-Caramés, T.M.; Fraga-Lamas, P. A Review on the Use of Blockchain for the Internet of Things. IEEE Access 2018. [Google Scholar] [CrossRef]
- Treleaven, P.; Brown, R.G.; Yang, D. Blockchain Technology in Finance. Computer 2017, 50, 14–17. [Google Scholar] [CrossRef]
- Omohundro, S. Cryptocurrencies, Smart Contracts, and Artificial Intelligence. AI Matters 2014, 1, 19–21. [Google Scholar] [CrossRef]
- Tse, D.; Zhang, B.; Yang, Y.; Cheng, C.; Mu, H. Blockchain application in food supply information security. In Proceedings of the 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, 10–13 December 2017; pp. 1357–1361. [Google Scholar]
- Edwards, N. Blockchain meets the supply chain. MHD Supply Chain Solut. 2017, 47, 48. [Google Scholar]
- Kim, H.M.; Laskowski, M.; Nan, N. A First Step in the Co-Evolution of Blockchain and Ontologies: Towards Engineering an Ontology of Governance at the Blockchain Protocol Level. arXiv, 2018; arXiv:1801.02027. [Google Scholar] [CrossRef] [Green Version]
- Leng, K.; Bi, Y.; Jing, L.; Fu, H.-C.; Van Nieuwenhuyse, I. Research on agricultural supply chain system with double chain architecture based on blockchain technology. Future Gener. Comput. Syst. 2018, 86, 641–649. [Google Scholar] [CrossRef]
Characteristic | Hyperledger Fabric | Ethereum |
---|---|---|
Category | Consortium blockchain | Public blockchain |
Description | Modular platform | Generic platform |
Governance | Linux Foundation | Ethereum developers |
Authority | Permissioned, private | Permissionless, public or private |
Smart contracts | Chaincode (e.g., Go, Java) | Smart contract code (e.g., Solidity) |
Environment | Details |
---|---|
PC | Intel (R) Xeon (R) CPU 2.40 GHz (2 Processors), 12.0 GByte Memory |
OS | Ubuntu 16.04 Desktop |
Language | go 1.9.2 Linux/AMD64, jquery-3.1.1, bootstrap-3.3.7, Python 3.5 |
Containerization | Docker 17.10.0 |
Hash Function | SHA-256 |
© 2018 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
Mao, D.; Wang, F.; Hao, Z.; Li, H. Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain. Int. J. Environ. Res. Public Health 2018, 15, 1627. https://doi.org/10.3390/ijerph15081627
Mao D, Wang F, Hao Z, Li H. Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain. International Journal of Environmental Research and Public Health. 2018; 15(8):1627. https://doi.org/10.3390/ijerph15081627
Chicago/Turabian StyleMao, Dianhui, Fan Wang, Zhihao Hao, and Haisheng Li. 2018. "Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain" International Journal of Environmental Research and Public Health 15, no. 8: 1627. https://doi.org/10.3390/ijerph15081627
APA StyleMao, D., Wang, F., Hao, Z., & Li, H. (2018). Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain. International Journal of Environmental Research and Public Health, 15(8), 1627. https://doi.org/10.3390/ijerph15081627