teacher, and passionate workaholic, who has published a textbook on Data Science and AI and regularly shares her own and other’s writing on this technology, particularly as it relates to e-commerce and NLP, via Medium and Twitter.
With a background in computational linguistics and (deep) machine learning, Katherine began her career with jobs in R&D for Mercedes-Benz and the Fraunhofer Institute, specialising in user interfaces and Natural Language Understanding. She pivoted into Data Science and Software Development for a SaaS+ provider specialised in e-commerce, and now works as a Senior Data Science Consultant. Previously, Katherine has also worked as a university lecturer and a Team Leader in the marketing domain, and now spends her free time as a co-organiser at Women in AI Upper Austria, volunteer mentor at Female Coders Linz, and a trainer for LinkedIn Learning.
Technical Vision Talk: “Eating humble Py: From toy problem to real-world solution in predicting Customer Lifetime Value”
I should have known I was up against it when even my Kaggle solution sucked. I’d been tasked with launching our company’s research efforts into Customer Lifetime Value prediction, so naturally, I turned to that grail of tutorials and toy datasets, and started exploring. Very quickly I learned two things: the go-to CLV dataset was not worth going to, and I really needed some retail domain experts.
This is the story of my team’s journey from play-problem to real-world solution. Learn, as we learned, what is Customer Lifetime Value and why does everyone in retail suddenly want to predict it? Take a tour of common approaches to solving this problem, from machine learning to good old fashioned spreadsheets. Feel all the practical pains our clients inflicted on us, and discover why CLV prediction is not as easy as Towards Data Science makes it out to be.
Whether you’re an analytics enthusiast, a novice data scientist or an experienced practitioner, and whether you work in retail or not, there’s something in this talk for you: a little bit of machine learning theory, a peek into a new domain of application you may not be familiar with, or the chance to just cringe in sympathy at problems you know only too well.