Hello and Welcome from 360DigiTMG. This is a video playlist to explain the life cycle of a data science project. In the previous video we talked about EDA and Visualization. Now let us discuss about the sub module in Data Preparation – Feature Engineering


Feature Engineering: This phase too is not listed as part of the CRISP-DM framework but is widely recognized as an integral part of the data science life cycle. Every unique attribute of the data is considered a feature. For example, when designing a solution for a problem of predicting customer churn, you start with the customer data that has been collected over time. The customer data captures features (also known as attributes), such as customer location, age, income level, and recent purchases.

Feature engineering is a process to select and transform variables when creating a predictive model using machine learning or statistical modeling. Feature engineering typically includes feature creation, feature transformation, feature extraction, and feature selection.
• Feature creation identifies the features in the dataset that are relevant to the problem at hand.
• Feature transformation manages replacing missing features or features that are not valid. Some techniques include forming Cartesian products of features, non- linear transformations (such as binning numeric variables into categories), and creating domain-specific features.
• Feature extraction is the process of creating new features from existing features, typically with the goal of reducing the dimensionality of the features.
• Feature selection is the filtering of irrelevant or redundant features from your dataset. This is usually done by observing variance or correlation thresholds to determine which features to remove.

Best Practices for feature engineering:

• Use domain experts to help evaluate the feasibility and importance of features
• Remove redundant and irrelevant features (to reduce the noise in the data and reduce correlations)
• Start with features that generalize across contexts
• Iterate as you build your model (new features, feature combinations, and new
tuning objectives)

That concludes this video. In the next video we will talk about the next phase in the life cycle – Model Development.


SUBSCRIBE TO 360DigiTMG’s YOUTUBE CHANNEL NOW
https://www.youtube.com/channel/UCNGIDQ466bNY87eEeKeQuzA

We have specifically created a Facebook Group for all our Data Science aspirants. You can use the below link to join.
In addition to this, we are going to host 2 FREE training sessions Every Single Month on various topics inside this group.

Join FREE Data Science Facebook Group
https://www.facebook.com/groups/DataScience.MachineLearning.ArtificialIntellegence/


CONNECT WITH 360DigiTMG ON SOCIAL MEDIA

Facebook: https://www.facebook.com/360Digitmg/
Linkedin: https://www.linkedin.com/company/360digitmg/
Instagram: https://www.instagram.com/360.digitmg/
YouTube: https://www.youtube.com/channel/UCNGIDQ466bNY87eEeKeQuzA

About 360DigiTMG
360digiTMG is a 5-year-old training & consulting organization led by stalwarts of the industry who are alumnus of premier institutions like the Indian Institute of Technology, Indian Institute of Management and Indian School of Business. 360digiTMG since its inception has been the forerunner in the space of management and niche programs that aid in up-skilling and cross skilling executives across various levels and domains. 360digiTMG has been conducting training programs across the globe for corporate and individuals alike.
360DigiTMG is one stop solution to all the trainings in emerging technologies such as Artificial Intelligence, Machine Learning, Big Data, Project Management, Quality Management, etc. 360DigiTMG is a training company, which is a division of the analytics consulting firm Innodatatics Inc.

For more Information Contact us @::
India : +91 99899 94319
Malaysia: +603 2092 9488

Email: [email protected]
Web: https://360digitmg.com/

Did you find this video helpful? Leave a comment below!
#DataScience #ArtificialIntelligence #Scholarship #DataAnalytics #Jumpstart #360DigiTMG #Malaysia