Sequence Embeddings in Python: Classification & User journey Comparison
Pramod Singh (~pramodchahar) |
Millions of visitors visit business websites every day and each one of them takes different set of steps in order to seek the right information/product. Yet most of them leave disappointed or dejected for some reason and very few get to the right page within the website. In this kind of situation, it becomes difficult to find out if the visitor actually got the information that he was looking for? Also, the individual journeys of these visitors can’t be compared to each other since every visitor has done different set of activities. So, how can we know more about these journeys and compare these visitors to each other? Sequence Embedding is a powerful way that offers us the flexibility to not only compare any two distinct visitors entire journey in terms of similarity but also to predict the probability of visitor’s conversion. Sequence embeddings essentially helps us to move away from using traditional features to make predictions and considers not only the order of the activities of a user but also the average time spent on each of the unique pages to translate into more robust features and used in Supervised Machine Learning across multiple use cases (next possible action prediction, converted vs non-converted, product classification) .Using traditional Machine learning models on the advanced features like sequence embeddings, we can achieve tremendous results in terms of prediction accuracy but the real benefit lies in visualizing all these user journeys and observing how distinct are these paths from the ideal ones.
This session will unfold the process creating sequence embeddings for each user’s journey in python and use them to build machine learning classification model to predict visitor conversion along with comparing all the user journeys in terms of similarity score.
Basic understanding of Machine Learning , Python Basics
Co-Founder of DataScienceBridge and currently Sr. Data Scientist at SapientRazorfish core Data Science Team has around 8 years’ experience in the industry, ranging from large scale IT enterprise business development to building complex Machine Learning models by applying state of the art techniques. He has completed his Master’s in Business at Symbiosis International University and certified professional in Machine Learning from IIM-Calcutta. His core expertise involves Machine Learning, Deep Learning, Recommendation Systems using python, spark and Tensorflow for various projects. He is president of Data Science meet up group at SapientRazorfish and conducts multiple webinars on Machine Learning. Along with that he is also a speaker and recently presented a talk at “Great Indian Developer Summit “(GIDS 2018). In his spare time, he likes to read, code and help aspiring Data Scientists.