Credit Evaluation System Based on Blockchain for Multiple Stakeholders in the Food Supply Chain

Abstract

The food supply chain is a complex system that involves a multitude of “stakeholders” such as farmers, production factories, distributors, retailers and consumers. “Information asymmetry” between stakeholders is one of the major factors that lead to food fraud. Some current researches have shown that applying blockchain can help ensure food safety. However, they tend to study the traceability of food but not its supervision. This paper provides a blockchain-based credit evaluation system to strengthen the effectiveness of supervision and management in the food supply chain. The system gathers credit evaluation text from traders by smart contracts on the blockchain. Then the gathered text is analyzed directly by a deep learning network named Long Short Term Memory (LSTM). Finally traders’ credit results are used as a reference for the supervision and management of regulators. By applying blockchain, traders can be held accountable for their actions in the process of transaction and credit evaluation. Regulators can gather more reliable, authentic and sufficient information about traders. The results of experiments show that adopting LSTM results in better performance than traditional machine learning methods such as Support Vector Machine (SVM) and Navie Bayes (NB) to analyze the credit evaluation text. The system provides a friendly interface for the convenience of users.

Application of Deep Learning in Food: A Review

“…Mao et al. () presented a credit evaluation system based on blockchain for food supply chain using a deep learning network named LSTM. The evaluation task was carried out by analyzation of credit evaluation texts.…”

“…The research in (Mao et al., ) solved a problem that how to transform large number of credit evaluation text data into some simple evaluation indicators. Similarly, another article (Kim, ) introduced a sentence classification method using deep learning, which can be tested using the dataset mentioned in Mao et al.…”

“…It is hard for regulators, such as governments, to obtain reliable food information due to the unreliable information from the supply chain, which can easily lead to food fraud and food safety problems. Mao et al (2018) presented a credit evaluation system based on blockchain for food supply chain using a deep learning network named LSTM. The evaluation task was carried out by analyzation of credit evaluation texts.…”

“…The research in solved a problem that how to transform large number of credit evaluation text data into some simple evaluation indicators. Similarly, another article (Kim, 2014) introduced a sentence classification method using deep learning, which can be tested using the dataset mentioned in Mao et al (2018) for comparison. Such research relies heavily on big data, so much work (such as dataset in the type of audio, text, and so on, for food domain should be collected, for example) remains to be done in the future.…”

Introduction of highly effective proactive food safety management programs into food distribution channels: For safe food labeling and safe advertisements

“…Food contact materials are related to consumer product usage and must be properly indicated (Janjarasskul & Suppakul, ). Producer and traceability information (Table , checklist clauses 2 and 3) and advertisement are safety devices for reverse tracing when microbial/chemical hazards occur to prevent further harm, deduce causes, and take rapid actions (Adams, ; Liu et al, ; Mao, Wang, Hao, & Li, ; Meyerding, ; Russo & Tufi, ; Tibola, da Silva, Dossa, & Patricio, ; Tinacci et al, ). Eco‐friendliness, agricultural quality control, and geographical information and certifications (Table , checklist clauses 3 and 6) secure the economic value of food and relate to consumers’ preferences (Liu et al, ; MAFRA & MOF, ; Park, Kim, You, You, Kim, et al, ).…”