Search

Short-cycle agricultural product sales forecasting significantly reduces food waste by accurately predicting demand, ensuring producers match supply with consumer needs. However, the forecasting is often subject to uncertain factors, resulting in highly volatile and discontinuous data. To address this, a hierarchical prediction model that combines RF-XGBoost is proposed in this work. It adopts the Random Forest (RF) in the first layer to extract residuals and achieve initial prediction results based on correlation features from Grey Relation Analysis (GRA). Then, a new feature set based on residual clustering features is generated after the hierarchical clustering is applied to classify the characteristics of the residuals. Subsequently, Extreme Gradient Boosting (XGBoost) acts as the second layer that utilizes those residual clustering features to yield the prediction results. The final prediction is by incorporating the results from the first layer and second layer correspondingly. As for the performance evaluation, using agricultural product sales data from a supermarket in China from 1 July 2020 to 30 June 2023, the results demonstrate superiority over standalone RF and XGBoost, with a Mean Absolute Percentage Error (MAPE) reduction of 10% and 12%, respectively, and a coefficient of determination (R2) increase of 22% and 24%, respectively. Additionally, its generalization is validated across 42 types of agricultural products from six vegetable categories, showing its extensive practical ability. Such performances reveal that the proposed model beneficially enhances the precision of short-term agricultural product sales forecasting, with the advantages of optimizing the supply chain from producers to consumers and minimizing food waste accordingly. [ABSTRACT FROM AUTHOR]

Short-cycle agricultural product sales forecasting significantly reduces food waste by accurately predicting demand, ensuring producers match supply with consumer needs. However, the forecasting is often subject to uncertain factors, resulting in highly volatile and discontinuous data. To address this, a hierarchical prediction model that combines RF-XGBoost is proposed in this work. It adopts the Random Forest (RF) in the first layer to extract residuals and achieve initial prediction results based on correlation features from Grey Relation Analysis (GRA). Then, a new feature set based on residual clustering features is generated after the hierarchical clustering is applied to classify the characteristics of the residuals. Subsequently, Extreme Gradient Boosting (XGBoost) acts as the second layer that utilizes those residual clustering features to yield the prediction results. The final prediction is by incorporating the results from the first layer and second layer correspondingly. As for the performance evaluation, using agricultural product sales data from a supermarket in China from 1 July 2020 to 30 June 2023, the results demonstrate superiority over standalone RF and XGBoost, with a Mean Absolute Percentage Error (MAPE) reduction of 10% and 12%, respectively, and a coefficient of determination (R2) increase of 22% and 24%, respectively. Additionally, its generalization is validated across 42 types of agricultural products from six vegetable categories, showing its extensive practical ability. Such performances reveal that the proposed model beneficially enhances the precision of short-term agricultural product sales forecasting, with the advantages of optimizing the supply chain from producers to consumers and minimizing food waste accordingly.

Suboptimal food is defined as physically imperfect food that deviates from the norm in terms of appearance without compromising its intrinsic quality or safety. Consumers' quality perception and acceptance of suboptimal food contribute to food waste. Therefore, this study aims to explore consumers' quality perception and acceptance of suboptimal food and the factors associated with the acceptance of suboptimal food. An online survey was conducted among 414 consumers residing in Selangor and Kuala Lumpur, Malaysia, through convenience sampling. They completed an online questionnaire asking for sociodemographic information, quality perception and acceptance of suboptimal food, and information related to food waste. Only 11.4% of consumers chose suboptimal foods, with visually deviated suboptimal foods (apples with brown spots) having the lowest acceptance (9.9%). Consumers perceived suboptimal foods as unattractive and that they should be consumed quickly. Malays were less likely to accept suboptimal foods, while middle-income households were more likely to accept suboptimal foods at home. In conclusion, consumers have a low acceptance of suboptimal food, and suboptimal food was perceived as unappealing and that it should be consumed quickly. Notwithstanding the findings that emerge from this, the results may lack generalisability to the wider population as only a convenience sample was used. [ABSTRACT FROM AUTHOR]

Food waste has become a significant issue in the foodservice industry. However, food waste management in buffet restaurants has rarely been investigated. Considering the popularity of buffet restaurants in Taiwan, this study serves as the first attempt to identify a corporate management approach to food waste reduction in Taiwanese buffet restaurants. The study case comprises two buffet restaurants of a large chain restaurant company in Taiwan. This study uses both individual in-depth interviews and a focus group, comprising 15 managers, chefs, and front-line employees. The results identify various strategies to mitigate food waste in buffet restaurants at different stages of operation: establishing a central kitchen, cooperating with qualified suppliers, accurate forecasting of food demand, aesthetic buffet table design, redesigning the service method, continually monitoring food waste, and proactive communication to customers. The 3R (Reduce–Reuse–Recycle) food waste hierarchy is also developed to encourage buffet restaurant practitioners to design appropriate food waste mitigation programs. [ABSTRACT FROM AUTHOR]

Suboptimal food is defined as physically imperfect food that deviates from the norm in terms of appearance without compromising its intrinsic quality or safety. Consumers’ quality perception and acceptance of suboptimal food contribute to food waste. Therefore, this study aims to explore consumers’ quality perception and acceptance of suboptimal food and the factors associated with the acceptance of suboptimal food. An online survey was conducted among 414 consumers residing in Selangor and Kuala Lumpur, Malaysia, through convenience sampling. They completed an online questionnaire asking for sociodemographic information, quality perception and acceptance of suboptimal food, and information related to food waste. Only 11.4% of consumers chose suboptimal foods, with visually deviated suboptimal foods (apples with brown spots) having the lowest acceptance (9.9%). Consumers perceived suboptimal foods as unattractive and that they should be consumed quickly. Malays were less likely to accept suboptimal foods, while middle-income households were more likely to accept suboptimal foods at home. In conclusion, consumers have a low acceptance of suboptimal food, and suboptimal food was perceived as unappealing and that it should be consumed quickly. Notwithstanding the findings that emerge from this, the results may lack generalisability to the wider population as only a convenience sample was used.

Food waste has become a significant issue in the foodservice industry. However, food waste management in buffet restaurants has rarely been investigated. Considering the popularity of buffet restaurants in Taiwan, this study serves as the first attempt to identify a corporate management approach to food waste reduction in Taiwanese buffet restaurants. The study case comprises two buffet restaurants of a large chain restaurant company in Taiwan. This study uses both individual in-depth interviews and a focus group, comprising 15 managers, chefs, and front-line employees. The results identify various strategies to mitigate food waste in buffet restaurants at different stages of operation: establishing a central kitchen, cooperating with qualified suppliers, accurate forecasting of food demand, aesthetic buffet table design, redesigning the service method, continually monitoring food waste, and proactive communication to customers. The 3R (Reduce–Reuse–Recycle) food waste hierarchy is also developed to encourage buffet restaurant practitioners to design appropriate food waste mitigation programs.

Given the large amount of food waste coming from households, reducing household food waste is essential to the mitigation of overall food waste and the provision of multi-faceted benefits for both people and the planet. This study identifies factors and management strategies for the reduction of household food waste in the Taiwanese household setting. Using snowball sampling, semi-structured interviews are conducted to collect data from 27 household food providers in Taipei. The research findings identify four critical motivators and four barriers to minimizing household food waste in Taiwan. The most frequently mentioned motivator for the reduction of food waste is a convenient shopping environment, and the most important barrier is lack of knowledge for assessing the edibility of food. Additionally, four major prevention strategies are identified to help reduce household food waste: (1) planned purchase schedule; (2) skills to keep food fresh and longer; (3) understanding family preferences and leftover management, and (4) sharing additional food and co-procurement and cooking. The results of this study not only help improve the understanding and application of Chinese household food waste reduction, but also demonstrate the significance of its socio-cultural impacts in future studies.

Given the large amount of food waste coming from households, reducing household food waste is essential to the mitigation of overall food waste and the provision of multi-faceted benefits for both people and the planet. This study identifies factors and management strategies for the reduction of household food waste in the Taiwanese household setting. Using snowball sampling, semi-structured interviews are conducted to collect data from 27 household food providers in Taipei. The research findings identify four critical motivators and four barriers to minimizing household food waste in Taiwan. The most frequently mentioned motivator for the reduction of food waste is a convenient shopping environment, and the most important barrier is lack of knowledge for assessing the edibility of food. Additionally, four major prevention strategies are identified to help reduce household food waste: (1) planned purchase schedule; (2) skills to keep food fresh and longer; (3) understanding family preferences and leftover management, and (4) sharing additional food and co-procurement and cooking. The results of this study not only help improve the understanding and application of Chinese household food waste reduction, but also demonstrate the significance of its socio-cultural impacts in future studies. [ABSTRACT FROM AUTHOR]