With the increased adoption of digital solutions, huge amount of data is generated on the web. While this data is readily available on web pages or found in web applications, most of the emphasis in the data analytics world focus more on the predictive modeling aspects and assumes that the data can be easily downloaded from data repositories such as Kaggle. However, this limits the number of AI applications that can be built.
This workshop addresses both the manual mining of web content and predictive modeling of the data. Specifically, students will be taught various systematic techniques on how to mine web content, and how to process the data such as applying predictive modeling and building recommender systems.
