Computational Intelligence for Digital Marketing and Online Sales/Services (WCCI-CIDM)

The market share of online/e-commerce sales has been rapidly increasing during the last three decades. In 2018, for the first time, the amount of total online sales has exceeded the in-store sales in the USA. Moreover, Google and Facebook generated 116.3 and 55.8 billion US dollars respectively in 2018 form online advertising only. Unlike in-store sales, digital marketing and online sales generate big and valuable data about products, consumers' engagement and behaviour which was not available for business before (e.g. where customers are coming from? what devices they are using? what items do they buy? or view and for how long? how shoppers respond to digital marketing ads and emails? and much more). Moreover, social media has changed how companies advertise their products, engage with potential consumers and understand market segments needs. There is a huge demand for new computational intelligence and machine learning methods to improve and optimize digital marketing and online business operations. This is area is attracting researchers from industry and academia. For example, in addition to NetFlix’s famous MoviLlens dataset, in 2018 Spotify has released 1 million playlist dataset to challenge the academic community to come up with best AI methods to help its users create and extend their own playlists.

The session will provide a forum for both academia and industry to disseminate and discuss recent advances in neural networks, machine learning, evolutionary and fuzzy methods and their integration into the broad area of digital marketing and e-commerce.

This session seeks contributions on the latest developments and emerging research related, but are not limited to:

• Computational intelligence for digital strategy optimization and automatic discovery.
• Recommender Systems.
• Computational intelligence for automatic consumer segmentation and clustering.
• Deep learning for image and content based Recommender systems.
• Neural Networks and Machine learning for consumer behaviour prediction (classification).
• Computational intelligence for online content optimization.
• Purchase prediction.
• Stock and delivery optimization.
• Split testing and bucket testing optimization/automation.
• Personalisation and behavioural targeting.
• Budget optimization problem and pay per click.