Transfer Learning to enable Flexibility of Demand Forecasting: Dropout Profiles to protect from Negative Transfer.
Marek HütschPublished in: ECIS (2021)
Keyphrases
- decision making
- transfer learning
- demand forecasting
- supply chain
- historical data
- knowledge transfer
- learning tasks
- machine learning
- labeled data
- reinforcement learning
- cross domain
- active learning
- collaborative filtering
- transferring knowledge
- text categorization
- multi task
- learning algorithm
- transfer knowledge
- semi supervised learning
- machine learning algorithms
- knowledge management
- domain adaptation
- semi supervised
- data mining
- text classification
- forecasting accuracy
- text mining
- pattern recognition
- cross domain learning