DataHour: Feature Engineering and Selection for Machine Learning

Feature engineering includes choosing, modifying, and converting unprocessed data into features that can be applied in supervised learning. It is important to create and train better features in order to make machine learning effective on new tasks. Feature engineering is the process of employing statistical or machine learning techniques to transform unprocessed observations into desired features.

In this DataHour Dr Surbhi will demonstrate how to build a multitask model covering the following topics in detail :

• What is feature engineering?
• Why is it important?
• How to perform Feature engineering for machine learning?
• Practical use case

Prerequisites: Basic understanding of python and enthusiasm of learning Data Science.

Dr. Surabhi Thorat is a Head of Data Science at Aritar. She is  leading a team of Data Scientists and  providing Industry 4.0 AI Solutions for diverse domains. She has specialization in process optimization and time series modeling. She had completed her PhD in Computer Science focused on Computational Linguistics. She has published her work in more than 20 national and international conferences. Previously she also worked as Assistant Professor and Research guide and guided PhD research scholars in Somaiya University.