A machine learning algorithm in Azure ML has few parameter settings that you can set — in this post, we will talk about 1) why you should NOT stick with default settings 2) How can “Tune model hyperparameters” module help you do so?
So first up, why you should not be using the default setting? The parameter settings that are applied to a model impacts the accuracy (or call it predictive power) of the algorithm…sometimes it may be significant and sometimes not but either case, you won’t know until you try changing the default values. In other words, by tuning the hyperparameters you could significantly boost your model’s performance!
Now, how do you go about setting the parameters such that it gives optimal performance? Let’s say that there are 3 parameters then that is 27 different combinations! How do you know which one is the best? You could dig a little deeper into the mechanism of how algorithms works and narrow down your list but that would still take some time. So, there should be a better way, right? Luckily there is: This where “Tune Model Hyperparameters” comes in! You can use it with any algorithm in Azure ML. This module helps you tune the hyper-parameters. There’s some things that you still need do like decide: Do you want the module to just try random n combinations? OR Do you want the module to try all combinations (fyi: this is compute-intensive operation!)? … AND you will have to decide what are you are optimizing for? Depending on the algorithm it would let you pick the evaluation metric that you want to optimize.
Now, there are some good articles already written that walks you through how to get about doing this so I am going to share these links with you:
Running the “Entire Grid” mode will slow down the training time for the model. You might want to make sure that it’s acceptable and the cost (longer training time) to benefit (better accuracy) is worth it for your case
When you are comparing algorithms to decide the best one that fits your problem, instead of comparing “model with default parameter settings” with each other, try comparing the “model with tuned hyper-parameters”
Next week, on Mar 15th, 2016, We at Business Analytics VC are hosting a webinar to help you dive a little bit deeper with azure machine learning and learn about building a model to predict customer churn. Even if you don’t use Azure, I think you can still benefit from learning about the use-cases and the framework to solve this problem. You can register using this URL:
If you’re getting started with Data Science & Machine Learning then I think this would be a great resource for you. This “cheat sheet” helps you select the “algorithm” to test depending on the problem you are trying to solve and the data-set that you have.
Why is “Doing Data Science at Twitter” a great read?
This is an insider’s perspective from someone who is working at a company that I classify as having the highest level of analytics maturity — In other words, Twitter is known to apply knowledge gained from data science into their products and business processes.
It’s also important to recognize that every company is different and the analytics/data-science tools/techniques/processes that would be implemented would also vary based on the analytics maturity — I love that this was one of the key insights shared in this article.
Also, the article talks about two types of data scientists…I thought it was great way to classify them because there’s a lot of confusion in the industry around what a Data scientist does. With that, Here’s the URL:
Description: The world is becoming more efficient. Today, seventy percent of the companies that graced the Fortune 1000 list a mere decade ago have vanished. Agility and survival are function of innovation, culture, and the ability to predict the future. To that end, data analytics offers a lifeline, a means of survival that will drive productivity and continue to disrupt and redefine business. However, the resources available to today’s business leaders sit on two vastly different ends of the spectrum. On the one hand, highly technical academic resources and on the other largely fluffy overviews of value propositions and potentials. The state of the industry shouldn’t be surprising. The same dynamics played out in early years of the internet. Software providers, technical leaders, and consulting firms greatly benefit from mystifying the world of data analytics into something that is incomprehensible. That lack of conceptual understanding is incredibly risky and propels the cost of analytics initiatives upwards. This webcast aims to bridge that gap between the technical data scientists and business leaders. Ultimately, this understanding will help to: – Connect the strategic goals of business leaders with the capabilities of technical advisers – Focus investments and initiatives within analytics and technology – Distill immensely complex subject matter into comprehensible examples – Accelerate the path to value and increase the ROI of analytics initiatives
Alex is a Predictive Analytics Architect in the Oil and Gas industry with a passion for distilling complexity into insights and evangelizing data science. His work has been featured on KDNuggets and he was recognized by DataScienceCentral as a top 180 blogger in 2014.