Scalability is one of the biggest challenges in data science. Learn how to evaluate data, choose the right algorithms, and perform predictive modeling at scale.
- [Instructor] All of our organizations are faced with increasing volumes of data, but how much of that data exactly do we need to use in our predictive analytics models, and at what point should we be worried that we might have to upgrade our modeling infrastructure? In this course, we will walk through the modeling process from start to finish and discuss how the amount of data fluctuates, often dramatically, at different stages of the project. My name is Keith McCormick, and I've been building predictive analytics models for more than 20 years.
I'm excited to share with you what I've learned about this critical, yet misunderstood and often neglected topic, so what will you learn? If you're in IT or IT management, you're going to learn enough about the behind-the-scenes of building predictive models to understand exactly what kinds of demands these projects are going to put on the IT infrastructure. If you're a senior executive or perhaps in analytics management, this will give you a much deeper understanding of what critical choices are made regarding what data to use and when you will want to be part of that process.
If you are a modeler, we'll review what at first appears to be some modeling basics, but from a point of view that doesn't get enough attention, and we'll be sure to give you new insights about effective modeling. Also, you would develop some critical skills to draw upon to more effectively collaborate with IT, IT management, your own management, and senior management. I look forward to the course.
Note: This course is software agnostic. The emphasis is on strategy and planning. Examples, calculations, and software results shown are for training purposes only.
- Evaluating the proper amount of data
- Assessing data quality and quantity
- Seasonality and time alignment
- Data preparation challenges
- Data modeling challenges
- Scoring machine-learning models
- Deploying models and adjusting data prep and scoring
- Monitoring and maintenance