We all know that the human mind learns much better when we can visualize the concept. Or, as people say, "a picture is worth a thousand words". Learning Data Science is no different.
Ironically, instead of using a visual tool, many entry-level data science courses and books make the mistake of starting out right away with Python or R. While knowing how to code up a machine learning algorithm in Python or R can make students feel more prepared to tackle real-world problems, it's much more important to understand how the algorithm works in an intuitive way.
Enters Excel
. Despite its data size limitation (and poor performance on computationally-heavy tasks), Excel is much more useful as the teaching tool for beginners in Data Science. Students can bypass the mental cost of visualizing matrix manipulation in memory (or Pandas/R dataframes), and visualize how popular Data Science algorithms in action on spreadsheets.
The author does a stellar job of explaining how many algorithms work for many fun real-world problems:
Using K-means Clustering
to segment a customer base
Implementing Naïve Bayes Filter
to analyze tweets about "Mandrill" (a product brand) vs. "Mandrill" (the animal)
Applying Optimization Modeling
for the Orange Juice supply chain
and many more...
Target Audience
Anyone working with Data Scientists: Product Managers, Software Engineers, Business Analysts, ...
Anyone lacking support from a Data Science team but looking to extract business insights out of existing data.
About the author
John W. Foreman had been the Chief Data Scientist at the famous startup MailChimp.com
until he was promoted to VP of Product. If you're looking to learn how to apply different Data Science algorithms to day-to-day business problems to extract actionable insights, he's the teacher you need.
We all know that the human mind learns much better when we can visualize the concept. Or, as people say, "a picture is worth a thousand words". Learning Data Science is no different.
Ironically, instead of using a visual tool, many entry-level data science courses and books make the mistake of starting out right away with Python or R. While knowing how to code up a machine learning algorithm in Python or R can make students feel more prepared to tackle real-world problems, it's much more important to understand how the algorithm works in an intuitive way.
Enters Excel
. Despite its data size limitation (and poor performance on computationally-heavy tasks), Excel is much more useful as the teaching tool for beginners in Data Science. Students can bypass the mental cost of visualizing matrix manipulation in memory (or Pandas/R dataframes), and visualize how popular Data Science algorithms in action on spreadsheets.
The author does a stellar job of explaining how many algorithms work for many fun real-world problems:
Using K-means Clustering
to segment a customer base
Implementing Naïve Bayes Filter
to analyze tweets about "Mandrill" (a product brand) vs. "Mandrill" (the animal)
Applying Optimization Modeling
for the Orange Juice supply chain
and many more...
Target Audience
Anyone working with Data Scientists: Product Managers, Software Engineers, Business Analysts, ...
Anyone lacking support from a Data Science team but looking to extract business insights out of existing data.
About the author
John W. Foreman had been the Chief Data Scientist at the famous startup MailChimp.com
until he was promoted to VP of Product. If you're looking to learn how to apply different Data Science algorithms to day-to-day business problems to extract actionable insights, he's the teacher you need.