Have had a few explorations into 'User Journey's. Its a trace of how people travel through coded interaction. From where they begin, what choices they make and where they end up. Ideally measuring how much the journey results in value. Its a kind of business process model based on a path of interactions. It can be used to plan, construct and even optimize user interactions. Here an example by the marketplace Etsy. with considerable detail regarding integration of machine learning.
Modeling User Journeys via Semantic Embeddings Posted by Nishan Subedi in O'Reilly
Etsy is a global marketplace for unique goods. This means that as soon as an item becomes popular, it runs the risk of selling out. Machine learning solutions that simply memorize the popular items are not as effective, and crafting features that generalize well across items in our inventory is important. In addition, some content features such as titles are sometimes not as informative for us since these are seller provided, and can be noisy.
In this blog post, I will cover a machine learning technique we are using at Etsy that allows us to extract meaning from our data without the use of content features like titles, modeling only the user journeys across the site. This post assumes understanding of machine learning concepts, specifically word2vec. ... "
A good Tensorflow Tutorial on Word2vec.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment