Building Applications That Predict User Behavior Through Big Data Using Open-Source Technologies
One of the biggest challenges for data engineers building real-world predictive applications with Big Data is the steep learning curve of multiple data-processing frameworks, learning algorithms and scalable programming.
In this class, you will get hands-on instructions for data engineers to add predictive features, such as personalization, recommendation and content discovery, to your applications using Big Data. The class will begin with a brief overview of scalable machine learning for Big Data. You will then see demonstrations with the use of open-source technologies such as Hadoop, Cascading, Scalding and PredictionIO with live sample codes. A number of collaborative filtering algorithms will be explained.
You will also see the use of open-source user-friendly control interfaces to evaluate, compare, select and deploy learning algorithms; tune hyperparameters of algorithms manually or automatically; and review the predictive model training status. By the end of the class, you will master the core concepts of Machine Learning and be able to apply scalable algorithms into real software production environment.
Level : Advanced