Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing
This research work describes an architecture for building a system that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in a manufacturing demand forecasting use case and can be extended to other domains. In...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/12/11/473 |
| _version_ | 1827676459111546880 |
|---|---|
| author | Patrik Zajec Jože M. Rožanec Elena Trajkova Inna Novalija Klemen Kenda Blaž Fortuna Dunja Mladenić |
| author_facet | Patrik Zajec Jože M. Rožanec Elena Trajkova Inna Novalija Klemen Kenda Blaž Fortuna Dunja Mladenić |
| author_sort | Patrik Zajec |
| collection | DOAJ |
| description | This research work describes an architecture for building a system that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in a manufacturing demand forecasting use case and can be extended to other domains. In addition, the system provides the means for knowledge acquisition by gathering data from users. Finally, it implements an active learning component and compares multiple strategies to recommend media news to the user. We compare such strategies through a set of experiments to understand how they balance learning and provide accurate media news recommendations to the user. The media news aims to provide additional context to demand forecasts and enhance judgment on decision-making. |
| first_indexed | 2024-03-10T05:24:35Z |
| format | Article |
| id | doaj.art-4d99dfedc7cd44ed9f543efd8e3dbe79 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T05:24:35Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-4d99dfedc7cd44ed9f543efd8e3dbe792023-11-22T23:45:44ZengMDPI AGInformation2078-24892021-11-01121147310.3390/info12110473Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in ManufacturingPatrik Zajec0Jože M. Rožanec1Elena Trajkova2Inna Novalija3Klemen Kenda4Blaž Fortuna5Dunja Mladenić6Jožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova 39, 1000 Ljubljana, SloveniaThis research work describes an architecture for building a system that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in a manufacturing demand forecasting use case and can be extended to other domains. In addition, the system provides the means for knowledge acquisition by gathering data from users. Finally, it implements an active learning component and compares multiple strategies to recommend media news to the user. We compare such strategies through a set of experiments to understand how they balance learning and provide accurate media news recommendations to the user. The media news aims to provide additional context to demand forecasts and enhance judgment on decision-making.https://www.mdpi.com/2078-2489/12/11/473artificial intelligencemachine learningactive learningknowledge acquisitionexplainable artificial intelligencemanufacturing |
| spellingShingle | Patrik Zajec Jože M. Rožanec Elena Trajkova Inna Novalija Klemen Kenda Blaž Fortuna Dunja Mladenić Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing Information artificial intelligence machine learning active learning knowledge acquisition explainable artificial intelligence manufacturing |
| title | Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing |
| title_full | Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing |
| title_fullStr | Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing |
| title_full_unstemmed | Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing |
| title_short | Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing |
| title_sort | help me learn architecture and strategies to combine recommendations and active learning in manufacturing |
| topic | artificial intelligence machine learning active learning knowledge acquisition explainable artificial intelligence manufacturing |
| url | https://www.mdpi.com/2078-2489/12/11/473 |
| work_keys_str_mv | AT patrikzajec helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT jozemrozanec helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT elenatrajkova helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT innanovalija helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT klemenkenda helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT blazfortuna helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing AT dunjamladenic helpmelearnarchitectureandstrategiestocombinerecommendationsandactivelearninginmanufacturing |