Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
An investigation into table grape risk factors that affect quality along the export supply chain
Thesis (MCom)--Stellenbosch University, 2022.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2022
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614140466462720 |
|---|---|
| access_status_str | Open Access |
| author | Rossouw, Christopher Guillaume |
| author2 | Goedhals-Gerber, Leila Louise |
| author_browse | Goedhals-Gerber, Leila Louise Rossouw, Christopher Guillaume |
| author_facet | Goedhals-Gerber, Leila Louise Rossouw, Christopher Guillaume |
| author_sort | Rossouw, Christopher Guillaume |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MCom)--Stellenbosch University, 2022. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/126114 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:47:18.472Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/126114 An investigation into table grape risk factors that affect quality along the export supply chain Rossouw, Christopher Guillaume Goedhals-Gerber, Leila Louise Mantadelis, Theofrastos Stellenbosch University. Faculty of Economic and Management Sciences. Dept. of Logistics. Grapes -- Diseases and pests -- South Africa Table grapes -- South Africa Fruit trade -- South Africa Food supply -- South Africa UCTD Thesis (MCom)--Stellenbosch University, 2022. ENGLISH SUMMARY: Table grapes are a highly perishable product, where a large proportion of grapes produced for export to Europe arrive in a substandard condition. Fruit in this condition requires repacking to remove the rotten food parts, or in extreme cases, the entire shipment is dumped resulting in a total loss. Both outcomes’ result in a potential loss of income for stakeholders and food waste, which could be avoided if proper upstream intervention had been taken. This ongoing occurrence prompted the investigation into what the factors are that cause the poor arrival quality of table grapes. The study also applied machine learning techniques to predict the probable arrival scores (green, amber, and red) based on input variables gathered throughout the supply chain. The data analysed was obtained from five diverse secondary sources consisting of intake quality shed reports, arrival quality reports, logistical nominal data, recorder temperature data, and climate data. The eventual dataset consisted of 467 observations. The analysis process applied consisted of descriptive and inferential statistics to explain the relationship between the upstream variables and the downstream resultant quality scores as well as how the upstream variables interact with one another. The results from the preliminary analysis aided in feature selection for the model building process. Four classification models, consisting of Logistic Regression, k-Nearest Neighbours, Decision Trees, and Random Forests (RF), were trained, and evaluated. The RF classifier demonstrated the best cross-validation score on the training data and was retained for further evaluation. The RF classifier’s accuracy score was 0.63 for the unseen test set and performed best when predicting red class-labels but struggled on green and performed worst for amber class predictions. Variables that had the largest impact on the arrival quality scores consisted of the climactic variables two weeks prior to harvest, the specific variety and ˚Brix at harvest, the number of decayed berries found in the packhouse as well as the overall packhouse quality score, and the type of packaging used (either punnets or loose pack). The effect of the supply chain was also evaluated but did not have any effect for the 2020 season. The attributes of poor quality were also identified in relation to the most important variables, so that upstream mitigation strategies could be determined to reduce financial claims and food waste. The potential upside of accurate arrival quality predictions prior to shipping would allow for improved allocation decisions leading to profit maximisation through loss reduction and cost savings. From an environmental perspective, assured sound arrival quality would reduce end of chain food waste and would increase product shelf life for consumers. AFRIKAANSE OPSOMMING: Tafeldruiwe is ‘n hoogs bederfbare produk en hierdie karaktereienskap het tot gevolg dat ‘n groot hoeveelheid tafeldruiwe wat vir die uitvoermark geproduseer word in ‘n onvoldoende toestand in Europa aankom. Druiwe in die toestand moet gewoonlik herverpak word om die vrot gedeeltes te verwyder en in sommige gevalle moet die hele besending weggegooi word. In beide gevalle is daar ‘n verlies aan inkomste vir belanghebbendes sowel as voedsel vermorsing wat vermy kon word indien daar voldoende stroomop intervensies toegepas is. Hierdie voortdurende gebeurtenis het die ondersoek aangespoor na wat die faktore is wat die swak aankoms gehalte van tafeldruiwe veroorsaak. Hierdie studie het ook masjienleer tegnieke toegepas om die waarskynlike aankoms graderings (groen, geel en rooi) gebaseer op inset veranderlikes wat regdeur die voorsieningsketting versamel is, te voorspel. Die data wat ontleed is, is verkry uit vyf diverse sekondere bronne wat bestaan uit inname kwaliteit pakhuis verslae, aankoms kwaliteit verslae, logistieke nominale data, koue ketting temperatuur data en klimaat data. Die uiteindelike datastel het uit 467 waarnemings bestaan. Die toegepaste analitiese proses het uit beskrywende en inferensiele statistiek bestaan om die verhouding tussen die stroomop veranderlikes en die stroomaf resulterende kwaliteit graderings te verduidelik asook hoe die stroomop veranderlikes met mekaar in wisselwerking tree. Die resultate van die voorafgaande analise het gehelp met die kenmerk keuse vir die model-bouproses. Vier klassifikasie modelle, bestaande uit Logistiese Regressie, k-Nearest Neighbours, Decision Trees, en Random Forests (RF), is opgelei en geevalueer. Die RF-klassifiseerder het die beste kruis-validasie gradering op die opleidingsdata getoon en is vir verdere evaluering behou. Vir die onsigbare toetsstel was die RF-klassifiseerder se akkuraatheid telling 0.63 en het die beste presteer wanneer rooi klas etikette voorspel word, maar het op groen gesukkel en die swakste gevaar vir geel klasvoorspellings. Veranderlikes wat die grootste impak op die aankomskwaliteit gradering gehad het, het bestaan uit die klimaat veranderlikes twee weke voor oes, die spesifieke varieteit en ˚Brix tydens oes, die aantal verrotte druiwe korrels in die pakhuis gevind, asook die algehele pakhuis kwaliteit gradering en die tipe verpakking wat gebruik word (in “punnets” of los gepak). Die effek van die koue ketting op tafeldruiwe is ook geevalueer, maar het geen effek vir die 2020-seisoen gehad nie. Die eienskappe van swak gehalte is ook geidentifiseer in verband met die belangrikste veranderlikes sodat stroomop mitigeringstrategiee bepaal kon word om finansiele eise en voedselvermorsing te verminder. Die potensiele voordeel van akkurate aankomskwaliteit-voorspellings voor versending sal verbeterde allokasie besluite moontlik maak wat gevolglik tot wins maksimering deur verliesvermindering en kostebesparings sal lei. Vanuit 'n omgewingsperspektief sal goeie aankomskwaliteit voedselvermorsing aan die einde van die koue ketting verminder en produk raklewe vir verbruikers verleng. Masters 2022-11-24T08:28:41Z 2023-01-16T12:50:47Z 2022-11-24T08:28:41Z 2023-01-16T12:50:47Z 2022-12 Thesis http://hdl.handle.net/10019.1/126114 en_ZA Stellenbosch University application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Grapes -- Diseases and pests -- South Africa Table grapes -- South Africa Fruit trade -- South Africa Food supply -- South Africa UCTD Rossouw, Christopher Guillaume An investigation into table grape risk factors that affect quality along the export supply chain |
| title | An investigation into table grape risk factors that affect quality along the export supply chain |
| title_full | An investigation into table grape risk factors that affect quality along the export supply chain |
| title_fullStr | An investigation into table grape risk factors that affect quality along the export supply chain |
| title_full_unstemmed | An investigation into table grape risk factors that affect quality along the export supply chain |
| title_short | An investigation into table grape risk factors that affect quality along the export supply chain |
| title_sort | investigation into table grape risk factors that affect quality along the export supply chain |
| topic | Grapes -- Diseases and pests -- South Africa Table grapes -- South Africa Fruit trade -- South Africa Food supply -- South Africa UCTD |
| url | http://hdl.handle.net/10019.1/126114 |
| work_keys_str_mv | AT rossouwchristopherguillaume aninvestigationintotablegraperiskfactorsthataffectqualityalongtheexportsupplychain AT rossouwchristopherguillaume investigationintotablegraperiskfactorsthataffectqualityalongtheexportsupplychain |