Data Science: A review of case studies

---

Rosaria Silipo

KNIME, Switzerland

: J Comput Eng Inf Technol

Abstract

---

Twenty-five years in the field of data science. Some things have changed, some have not. Some use cases are innovative, some are always the same. I would like to talk with you about some of those use cases, the traditional ones and their historical solutions, sometimes neglected but still valid. I would also like to illustrate some of the most recent use cases, those that were impossible to solve twenty years ago and have found a new life in the modern era of data science. All in all, I would like to take you through a time ride and see what has changed, what has stayed the same, what is still a practical solution to the customer and what is an awe-inspiring dream. From a classic churn prediction, that everybody should know by now how to quickly implement, to a rap song generator via free text generation techniques; from an anomaly detector in the manufacturing industry to convolutional networks for image recognition; from the recommendation engines popular in the 00 years to reinforcement learning to teach a machine to play tic tac toe. While exploring these case studies, we will focus on the new technique, the trick, the new hardware that made the solution feasible.

Biography

---

Rosaria Silipo, PhD, principal data scientist now at KNIME, has spent 25+ years in applied AI, predictive analytics and machine learning at Siemens, Viseca, Nuance Communications, and private consulting. Sharing her practical experience in a broad range of industries and deployments, including IoT, customer intelligence, financial services, social media, and cybersecurity, Rosaria has authored 50+ technical publications, including her recent books: “Guide to Intelligent Data Science” (Springer) and “Codeless Deep Learning with KNIME” (Packt).