IoT-freshness sensor data-driven price information system for food waste reduction in grocery retail stores

Purpose of this paper: Bulk fresh fruits and vegetables at the grocery retail stores are being wasted dramatically as disrupted grocery supply chains produce more food waste than ever before. Perishable foods need to be sold out before reaching the expiry date. Furthermore, insufficient market prices are likely to result in food surplus/food waste in retailers. The purpose of this paper is to meet customers’ quality and price requirements while minimising the food waste (disposal of produce) and increasing the profit of the retailer. The quality loss of a perishable item occurs naturally, and it becomes unacceptable by the customers as it stays on the shelves. Computational logistics applications such as hyperspectral imaging sensors can help grocery stores to reduce the food waste and increase profit by continuously inspecting the food quality and send signals to a computer that updates the unit price based on the freshness score and the remaining quantity of the product. This study explores the food waste reduction challenge by proposing an IoT freshness sensor data-driven four-stage price information system. Design/methodology/approach: In this paper, the food waste problem at the retailer stage is highlighted and an IoT freshness sensor data-driven four-stage price information system is proposed to reduce food waste by performing a pilot project for bulk apple sales. A multi-stage dynamic programming method is used to decide on a pricing strategy for the bulk produce, where real-time IoT sensor data retrieved from hyperspectral imaging sensors is employed to analyse and determine the length of freshness stages. Monte-Carlo simulation is employed to model the daily operation of a grocery store, and a numerical example is performed to illustrate the practicability of the proposed model. Findings: The model is simulated according to scenario-based and parameter effect analysis. Simulations were run to analyse the effects of sales price, the replenishment amount and the discount rate on profit and food waste and also effect of freshness score on profit and inventory level. The analysis show that these parameters have significant effects on the food waste of the grocery store. Value: The novelty part of this paper is to present a real-time IoT sensor data-driven dynamic model to decide pricing at different stages of a sales season at retailers in the perishable food supply chain for the first time, to the best of our knowledge, in a research work in the literature. Research limitations/implications (if applicable): In this research, freshness sensor data retrieved from hyperspectral imaging sensors is used to determine price strategy of produce and the Monte-Carlo simulation is conducted to model the daily operations of grocery store. Practical implications (if applicable): This proposed system is useful for the grocery stores to reduce their food waste, if any grocery supply chain disruption such as due to COVID-19 pandemics occurs. References: Kuswandi B (2017) “Freshness sensors for food packaging”, Reference Module in Food Science, 2017, https://doi.org/10.1016/B978-0-08-100596-5.21876-3. Pal A and Kant K (2018) “IoT-based sensing and communications infrastructure for the fresh food supply chain”, Computer, 51(2), 76-80. Parfitt J, Barthel M and Macnaughton S (2010) “Food waste within food supply chains: quantification and potential for change to 2050”, Philosophical Transactions of the Royal Society B: Biological Sciences, 365(1554), 3065-3081. Sangeetha G and Vijayalakshmi M (2020) “Role of smart sensors in minimising food deficit by prediction of shelf-life in agricultural supply chain”. In S-L, Peng, S. Pal, L. Huang (Eds.), Principles of Internet of Things (IoT) Ecosystem: Insight Paradigm. Intelligent System Reference Library, 174, 153-175, Switzerland: Springer. Tan W, Sun L, Yang F, Che W, Ye D, Zhang D and Zou B (2018) “The feasibility of early detection and grading of apple bruises using hyperspectral imaging”, Journal of Chemometrics, 32(10), 3067.