Practical feature engineering
Feature engineering is generally the section that gets left out of machine learning books, but it's also the most critical part in practice. Ted Dunning explores techniques, a few well known, but some rarely spoken of outside the institutional knowledge of top teams, including how to handle categorical inputs, natural language, transactions, and more in the context of machine learning.
|Talk Title||Practical feature engineering|
|Speakers||Ted Dunning (MapR, now part of HPE)|
|Conference||Strata Data Conference|
|Conf Tag||Make Data Work|
|Location||New York, New York|
|Date||September 24-26, 2019|
Feature engineering is generally the section that gets left out of machine learning books, but it’s also the most important part of successful models, even in today’s world of deep learning. While academic courses on machine learning focus on gradients and the latest flavor of recurrent network, Ted Dunning explores the techniques that practitioners in the real world are seeking out better features and figuring out how to extract value using a variety of time-honored (and occasionally exceptionally clever) heuristics. In a sense, feature engineering is the Rodney Dangerfield of machine learning, never getting any respect. It is, however, the task that will get you the most value for time spent in terms of model performance. This work is not just the work of the data scientist. Good features encode business realities as well and are the cross-product of good business sense and good data engineering.