Tuesday, April 13, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Data Science

Using Data Science and Google Cloud to Win March Madness…Well, Not Really

March 22, 2019
in Data Science
Using Data Science and Google Cloud to Win March Madness…Well, Not Really
587
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

Credit: Data Science Central

I suck at the NCAA March Madness® bracket selection process.  I let my personal biases get in the way of making decisions based upon the numbers.  I over-rate the well-known Big Ten conference and under-rate the lesser-known Mid Majors and fall in love with the most recent team I saw on TV win their conference tournament.  You see, I fall prey to all the common decision-making traps – recency bias, over-confidence, anchoring, risk aversion, framing – that doom my brackets from the very beginning.  (See the Appendix for more details on these decision-making traps.)

You might also like

NetSuite ERP ushering a digital era for SMEs

Orphaned Analytics: The Great Destroyers of Economic Value

An overview of Augmented reality applications and their future impact on AI

But this year is different because I’m going to take my gut feeling out of the selection process and let Google use the numbers to pick my brackets using “NCAA® March Madness®: Bracketology with Google Cloud” (notice all the registered “March Madness®” trademarks in case one thinks they can use “March Madness®” to tweak their “March Madness®” social following by overly using the “March Madness®” term!).

But even when using pre-configured, push-button Data Science, there is still some work that must be done by the humans.  So even with all of its Machine Learning glory, there are still plenty of opportunities for me to screw this up!

For those data scientist wannabe’s, you can use Google Studioto explore the performance data of each of the selected teams (see Figure 1).

Figure 1: Google Studio

Unfortunately, Google Studio lacks the more advanced analysis features that allow you to easily “slice-and-dice”, and pivot and cross-tab the data with the strong data visualization capabilities that you would see from tools in Tableau.  But if you are lazy like me and don’t want to waste time trying to codify the performance patterns and relationships buried in the data, you can use the simplified Google “Matchup Analysis” tool to guide your selections (see Figure 2).

Figure 2:  Google March Madness® Matchup Analysis

You just pick what variables you want and then weight them as either Low, Medium or High in predictive value, select the [Calculate] button and you are off to picking a winning bracket!

You can see from Figure 2 the variables that I thought were most important from a prediction perspective. Now a really good Machine Learning algorithm would help me discover which variables are likely the best predictors of performance, but alas, no such luck here for this amateur data scientist. 

So, to make my selection and the weighing of the variables, I found I had to first create assumptions that I would translate into the variables.  My assumptions for a successful bracket are:

  • Playing a tough schedule better prepares a team (Strength of Schedule, NET Ranking)
  • Defense wins close games (Defensive Stoppage Power, Defensive Efficiency)
  • The more possessions, the better (Turnovers Per Game, Second Chance Points)
  • 3-point shooting is a game-changer (3-point percentage)

The other issue that I have with the Google selection tool is that I am only allowed three “weightings” per variable:  Low, Medium or High.  In a real world data science project, I’d use a Neural Network to help me identify and weigh the variables that I want to use to try to predict the winners in my brackets. And maybe use Reinforcement Learning to run my selections through an endless number of automated scenarios.

But alas, here is my bracket courtesy of Google!

Duke beating Virginia in the finals?  All #1 seeds in the Final Four?  Heck, I could have predicted that myself using my gut.  Stupid Google Bracket selection tool…

Over-confidence.  We put a great deal of weight on whatever we happen to know and assume that what we don’t know isn’t important.  The casinos of Las Vegas were built on this human flaw (and why my son likes to say that “gambling is a tax on those who are bad at math”).

Anchoring Bias.  Anchoring is the subtle human tendency to glom onto one fact as a reference point for decisions, even though that reference point may have no logical relevance to the decision at hand.  During normal decision-making, individuals anchor, or overly rely, on specific information and then adjust to that value to account for other elements of the circumstance.  Usually once the anchor is set, there is a bias toward that information.

Risk Aversion.  Our tolerance for risk is highly inconsistent.  Risk aversion is a manifestation of people’s general preference for certainty over uncertainty, and for minimizing the magnitude of the worst possible outcomes to which they are exposed.  Risk aversion surfaces in the reluctance of a person to accept a bargain with an uncertain payoff rather than another bargain with a more certain, but possibly lower, expected payoff.

Framing.  How a decision is stated or framed can impact what decision is made. Information, when presented in different formats, alters people’s decisions. Individuals have a tendency to select inconsistent choices, depending on whether the question is framed to concentrate on losses or gains.


Credit: Data Science Central By: Bill Schmarzo

Previous Post

How Artificial Intelligence is Already Changing Medicine

Next Post

Microsoft tech support scammer pleads guilty to defrauding victims of $3 million

Related Posts

NetSuite ERP ushering a digital era for SMEs
Data Science

NetSuite ERP ushering a digital era for SMEs

April 12, 2021
Orphaned Analytics: The Great Destroyers of Economic Value
Data Science

Orphaned Analytics: The Great Destroyers of Economic Value

April 12, 2021
An overview of Augmented reality applications and their future impact on AI
Data Science

An overview of Augmented reality applications and their future impact on AI

April 12, 2021
Data Center Infrastructure Market is Projected to Reach USD 100 Billion by 2027
Data Science

Data Center Infrastructure Market is Projected to Reach USD 100 Billion by 2027

April 12, 2021
Interpretive Analytics in One Picture
Data Science

Interpretive Analytics in One Picture

April 12, 2021
Next Post
Microsoft tech support scammer pleads guilty to defrauding victims of $3 million

Microsoft tech support scammer pleads guilty to defrauding victims of $3 million

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

Bitcoin mining in China could threaten climate policies, new study shows
Blockchain

Bitcoin mining in China could threaten climate policies, new study shows

April 13, 2021
Artificial Intelligence Research at Duke
Machine Learning

Artificial Intelligence Research at Duke

April 13, 2021
Learning Not To Fear Machine Learning | by Dimitry Belozersky | Apr, 2021
Neural Networks

Learning Not To Fear Machine Learning | by Dimitry Belozersky | Apr, 2021

April 13, 2021
Billions of smartphone owners will soon be authorising payments using facial recognition
Internet Security

Billions of smartphone owners will soon be authorising payments using facial recognition

April 13, 2021
Indian Brokerage Firm Upstox Suffers Data Breach Leaking 2.5 Millions Users’ Data
Internet Privacy

Indian Brokerage Firm Upstox Suffers Data Breach Leaking 2.5 Millions Users’ Data

April 13, 2021
Caruso real estate to accept Bitcoin as rent payment in industry first
Blockchain

Caruso real estate to accept Bitcoin as rent payment in industry first

April 12, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • Bitcoin mining in China could threaten climate policies, new study shows April 13, 2021
  • Artificial Intelligence Research at Duke April 13, 2021
  • Learning Not To Fear Machine Learning | by Dimitry Belozersky | Apr, 2021 April 13, 2021
  • Billions of smartphone owners will soon be authorising payments using facial recognition April 13, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates