Search results

The purpose of this paper is to demonstrate the efficacy of machine learning (ML) in managing natural language processing tasks, specifically by developing two ML models to systematically classify a substantial number of food waste interventions.

A literature review was undertaken to gather global food waste interventions. Subsequently, two ML models were designed and trained to classify these interventions into predefined supply chain-related groups and intervention types. To demonstrate the use of the models, a meta-analysis was performed to uncover patterns amongst the interventions.

The performance of the two classification models underscores the capabilities of ML in natural language processing, significantly enhancing the efficiency of text classification. This facilitated the rapid and effective classification of a large dataset consisting of 2,469 food waste interventions into six distinct types and assigning them to seven involved supply chain stakeholder groups. The meta-analysis reveals the most dominant intervention types and the strategies most widely adopted: 672 interventions are related to “Process and Operations Optimisation”, 457 to “Awareness and Behaviour Interventions” and 403 to “Technological and Engineering Solutions”. Prominent stakeholder groups, including “Processing and Manufacturing”, “Retail” “Government and Local Authorities” and “NGOs, Charitable Organisations and Research and Advocacy Groups”, are actively involved in over a thousand interventions each.

This study bridges a notable gap in food waste intervention research, a domain previously characterised by fragmentation and incomprehensive classification of the full range of interventions along the whole food supply chain. To the best of the authors’ knowledge, this is the first study to systematically classify a broad spectrum of food waste interventions while demonstrating ML capabilities. The study provides a clear, systematic framework for interventions to reduce food waste, offering valuable insight for practitioners in the food system, policymakers and consumers. Additionally, it lays the foundation for future in-depth research in the food waste reduction domain.

Sugar from cane remains an important economic contributor in many countries. A lack of collaboration has been identified as a key problem in many of these regions. To date, few sugar researchers have exploited the valuable supply chain collaboration knowledge available in the literature, such as the Supply Chain Collaboration Index (SCCI). This paper seeks to address these issues.

Qualitative and quantitative data were collected from three sugarcane milling areas. The SCCI was contextualised from a psychological perspective and used in the quantitative data analyses. A special objective was to raise a number of pertinent questions, which would fast track stakeholders to a new level of collaboration.

Many relationships in the supply chain remain relatively positive. The main attributes of concern are stability, reliability, trust, personal relationships and communication. A lack of these attributes causes fragmentation, opportunism and a desire to over‐control. Mutuality and communication are key leverages in the system.

There is a need to understand how collaboration could be enhanced when stakeholders hold different balances of power. This study is still limited to sugarcane milling in South Africa.

This paper demonstrates a partially quantitative research methodology to understand collaboration in a food supply chain. The authors also propose a tool to help industry stakeholders to resolve current problems.

The psychological profiling of SCCI attributes and subsequent correspondence analyses is original. A framework of collaboration questions combined with Kepner‐Tregoe Problem Analyses is unique. These tools are generic to any agricultural supply chain.

The purpose of this paper is to develop and demonstrate a driving factors-based approach for identifying and ranking performance indicators in integrated sugarcane supply and processing systems (ISSPSs) on an on-going basis.

The research included a literature review, development of an approach, testing of the approach in four ISSPSs and checking the tests’ results for consistency with Southern Africa sugar industry benchmarks and external knowledge of the four ISSPSs.

The research offers a systematic approach for identifying and ranking performance indicators based on existing driving factors in ISSPSs. Results obtained from the application of the approach in four ISSPSs are consistent with industry benchmarks and external knowledge of the ISSPSs.

The approach was tested in only four ISSPSs. It is recommended that the approach should be tested in other complex systems to further validate its effectiveness. It is further recommended that the approach should be systematically compared with existing approaches that are used for identifying and ranking performance indicators.

This research is of academic value and of practical value to practitioners in ISSPSs. The research blends knowledge from network theory and cause-and-effect analysis to come up with a systematic approach for identifying and ranking performance indicators in ISSPSs on an on-going basis. Further, the approach identifies and ranks performance indicators as part of one data set. This approach has never, to the authors’ knowledge, been used in agro-industry before.