Machine Learning
Episode 10
Episode 10 Transcript
Hi, I’m John Colias, Senior Vice President of Decision Analyst’s Advanced Analytics Group, today to talk about machine learning models, and how these models can be used to optimize the return on media spend. And we’ll talk today primarily about the digital space.
So, imagine as in the diagram that a person is traveling, or journeying through the internet, by clicking on various websites and eventually come to, to my company’s website, or your company’s website, and as the person clicks on different websites, content tags are created, and the website URL is generated. So, we know where the person has been and what they’re interested in, because the content tag contains information about what they’re interested in. So, where the person has been in, and what areas they’re interested in, can become predictor variables in a machine learning model.
Machine learning model is really a predictive model that learns to predict very well by optimizing certain parameters that avoid overfitting of historical data. One of the outputs from these machine learning models is the importance of each of those predictor variables in the prediction itself.
So, in essence, we can learn from these models how to optimize our advertising by knowing what to talk about in advertisements, and where to actually place advertisements because those are variables in the predictive model that comes out of the machine learning model. So, these is, this is an important new way that the advertising spend can be optimized by using this new area of research, which is, which is machine learning models.
Thank you.
Presenter
John Colias, Ph.D.
Senior VP Research & Development
As a leader with both university teaching and business consulting experience, John focuses on predictive modeling, prescriptive analytics, and artificial intelligence. As Senior Vice President, Research & Development, at Decision Analyst, John combines academic and business interests to help analytics professionals by offering cutting-edge analytic solutions tempered by business realism. He holds a doctorate in economics from The University of Texas at Austin, with specializations in econometrics and mathematical modeling methods.
