What we're about

This is a group for anyone interested in analytics and data science. Our goal is to explore topics on the cutting edge of the data revolution, discuss developments in the Australian market, gain common ground on tools and approaches and get to know who's who in the Sydney data community. We meet fortnightly for breakfast in the CBD.

Upcoming events (1)

Hands on Data Science - Third Meeting, and Features in Modelling

This is not the regular breakfast meetup… This is a new stream where Data Practitioners can come together, share prepared material on a topic of the group’s choosing, and provide constructive feedback to each other. We welcome expressions of interest to attend - please feel free to RSVP, but in order to be moved from the wait-list, you will need to fill out the following google form, and be open to actively participating in future meetups. If you have filled out an expression of interest before, you can ignore this step. Link to Google Form: http://bit.ly/2V4Vbu2 Topic for today’s session: Feature selection and feature engineering Required Prep: Please prepare a case study or example of feature selection or feature engineering, and the impact on model performance. Agenda: 7:30 am - breakfast and networking. 7:55 - Javed Sheikh - Intro to Hands on Data Science Format, and today’s topic. 8:05 - Speaker (TBC) - Model explainability 8:25 - Evaluator (TBC) - Feedback for explainability presentation 8:30 - Lightning Talks - Your commercial case study, and group discussion. 8:55 am - Javed+ group - selection of topic/roles for next session, and close. Topic Abstract: Machine learning workflows depend on feature engineering and feature selection. However, they are often mistakenly equated by the data science communities. Although they have some overlap, these two concepts have different objectives in Machine learning/Data Science. In machine learning and statistics, feature selection, also known as variable selection, is the process of selecting a subset of relevant features (variables, predictors) for use in model construction.Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work. Feature engineering is fundamental to the application of machine learning and is both difficult and expensive. But when done properly, can result in wonders. Feature engineering and feature selection is the difference between the same algorithm working poorly and working awesome!

Photos (59)