A machine learning application in wine quality prediction
The wine business relies heavily on wine quality certification. The excellence of New Zealand Pinot noir wines is well-known worldwide. Our major goal in this research is to predict wine quality by generating synthetic data and construct a machine learning model based on this synthetic data and avai...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266682702200007X |
| _version_ | 1817976861668409344 |
|---|---|
| author | Piyush Bhardwaj Parul Tiwari Kenneth Olejar, Jr Wendy Parr Don Kulasiri |
| author_facet | Piyush Bhardwaj Parul Tiwari Kenneth Olejar, Jr Wendy Parr Don Kulasiri |
| author_sort | Piyush Bhardwaj |
| collection | DOAJ |
| description | The wine business relies heavily on wine quality certification. The excellence of New Zealand Pinot noir wines is well-known worldwide. Our major goal in this research is to predict wine quality by generating synthetic data and construct a machine learning model based on this synthetic data and available experimental data collected from different and diverse regions across New Zealand. We utilised 18 Pinot noir wine samples with 54 different characteristics (7 physiochemical and 47 chemical features). We generated 1381 samples from 12 original samples using the SMOTE method, and six samples were preserved for model testing. The findings were compared using four distinct feature selection approaches. Important attributes (referred as essential variables) that were shown to be relevant in at least three feature selection methods were utilised to predict wine quality. Seven machine learning algorithms were trained and tested on a holdout original sample. Adaptive Boosting (AdaBoost) classifier showed 100% accuracy when trained and evaluated without feature selection, with feature selection (XGB), and with essential variables (features found important in at least three feature selection methods). In the presence of essential variables, the Random Forest (RF) classifier performance was increased. |
| first_indexed | 2024-04-13T22:09:17Z |
| format | Article |
| id | doaj.art-b79157c2d60e4305b64ff3a0afa13ad1 |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-04-13T22:09:17Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-b79157c2d60e4305b64ff3a0afa13ad12022-12-22T02:27:49ZengElsevierMachine Learning with Applications2666-82702022-06-018100261A machine learning application in wine quality predictionPiyush Bhardwaj0Parul Tiwari1Kenneth Olejar, Jr2Wendy Parr3Don Kulasiri4Centre for Advanced Computational Solutions (C-fACS), Lincoln University, Christchurch 7608, New Zealand; Department of Wine, Food and Molecular Biosciences, Lincoln University, New ZealandCentre for Advanced Computational Solutions (C-fACS), Lincoln University, Christchurch 7608, New Zealand; Department of Wine, Food and Molecular Biosciences, Lincoln University, New ZealandChemistry Department, Colorado State University – Pueblo, 2200 Bonforte Blvd., Pueblo, CO 81001, USAFaculty of Agriculture and Life Sciences, Lincoln University, Christchurch 7608, New ZealandCentre for Advanced Computational Solutions (C-fACS), Lincoln University, Christchurch 7608, New Zealand; Department of Wine, Food and Molecular Biosciences, Lincoln University, New Zealand; Corresponding author at: Department of Wine, Food and Molecular Biosciences, Lincoln University, New Zealand.The wine business relies heavily on wine quality certification. The excellence of New Zealand Pinot noir wines is well-known worldwide. Our major goal in this research is to predict wine quality by generating synthetic data and construct a machine learning model based on this synthetic data and available experimental data collected from different and diverse regions across New Zealand. We utilised 18 Pinot noir wine samples with 54 different characteristics (7 physiochemical and 47 chemical features). We generated 1381 samples from 12 original samples using the SMOTE method, and six samples were preserved for model testing. The findings were compared using four distinct feature selection approaches. Important attributes (referred as essential variables) that were shown to be relevant in at least three feature selection methods were utilised to predict wine quality. Seven machine learning algorithms were trained and tested on a holdout original sample. Adaptive Boosting (AdaBoost) classifier showed 100% accuracy when trained and evaluated without feature selection, with feature selection (XGB), and with essential variables (features found important in at least three feature selection methods). In the presence of essential variables, the Random Forest (RF) classifier performance was increased.http://www.sciencedirect.com/science/article/pii/S266682702200007XMachine learningPinot noirSMOTERandom ForestXGBOOSTStochastiC Gradient Decision Classifier |
| spellingShingle | Piyush Bhardwaj Parul Tiwari Kenneth Olejar, Jr Wendy Parr Don Kulasiri A machine learning application in wine quality prediction Machine Learning with Applications Machine learning Pinot noir SMOTE Random Forest XGBOOST StochastiC Gradient Decision Classifier |
| title | A machine learning application in wine quality prediction |
| title_full | A machine learning application in wine quality prediction |
| title_fullStr | A machine learning application in wine quality prediction |
| title_full_unstemmed | A machine learning application in wine quality prediction |
| title_short | A machine learning application in wine quality prediction |
| title_sort | machine learning application in wine quality prediction |
| topic | Machine learning Pinot noir SMOTE Random Forest XGBOOST StochastiC Gradient Decision Classifier |
| url | http://www.sciencedirect.com/science/article/pii/S266682702200007X |
| work_keys_str_mv | AT piyushbhardwaj amachinelearningapplicationinwinequalityprediction AT parultiwari amachinelearningapplicationinwinequalityprediction AT kennetholejarjr amachinelearningapplicationinwinequalityprediction AT wendyparr amachinelearningapplicationinwinequalityprediction AT donkulasiri amachinelearningapplicationinwinequalityprediction AT piyushbhardwaj machinelearningapplicationinwinequalityprediction AT parultiwari machinelearningapplicationinwinequalityprediction AT kennetholejarjr machinelearningapplicationinwinequalityprediction AT wendyparr machinelearningapplicationinwinequalityprediction AT donkulasiri machinelearningapplicationinwinequalityprediction |