Predicting the Next Pitch
b'
For the past 2 years, Zach\\xa0has been working as a data scientist at an industry leading data consulting firm. \\xa0He works in fraud analytics space where he and his team has saved hundreds of millions of dollars of federal dollars using sophisticated data science techniques. He is\\xa0also a recent graduate of data science program at UC Berkeley.
\\nWhen I met him, I was really impressed with your ability to speak \\u201creal world\\u201d data science and later I found out that he has\\xa0a professional background in teaching complex topics like physics and calculus, which is what makes you such a good communicator in this field.
\\nI sat down with him on a sunny Saturday afternoon to discuss one of the most exciting projects he has worked on in his data science career.\\xa0
\\nHere\'s a quick recap of what we discussed:
\\n- \\n
- Can we predict what pitch is going to be thrown next in major league baseball? Implications for Hitters (batters) equipped with this data is $10M to $15M per season.\\xa0 \\n
- A wave of In-game analytics about to hit the sports industry. This in-game analytics may eat \\u2018Moneyball\\u2019 style static analytics for breakfast \\n
- Are better pitchers tough to predict? Or are they just as easy to predict as others? \\n
- What\\u2019s the correlation between a pitcher\\u2019s ERA and his predictability? ERA is a baseball metric - earned runs average - its used to gauge how well a pitcher is doing in a season. \\n
- Is it better to be 90% accurate 30% of the times or 30% accurate 90% of the times?\\xa0 \\n
- What has Ashton Kutcher to do with Data Science and Social Good? \\n
- How to cultivate the presence of mind when communicating about data?\\xa0 \\n
\\xa0
'