Flash Statistics | Marco Andreoni
August 3rd, 2020
48 mins 17 secs
About this Episode
On this episode of The Artists of Data Science, we get a chance to hear from Marco Andreoni, a statistician and data scientist who has a master's degree in mathematics and machine learning, as well as a master's degree in mathematics and cryptography.
He is the lead data scientist at Quantyca, where he covers every part of the data lifecycle from ingestion, storage, analytics, web applications, cloud storage and beyond.
Marco shares with us his passion for teaching other statistics in a more meaningful way. This led him to create Flash statistics, a way to make statistics more accessible to people. Marco brings an interesting perspective into sharing knowledge in a creative way, that all of our listeners should develop to be competitive!
WHAT YOU'LL LEARN
[5:59] Relationship between cryptography and data science
[23:57] What happens when you deploy a model to production
[27:11] The importance of version controlling models
[28:47] The importance of version controlling data
[30:33] Evaluation metrics for post production
[32:00] The importance of creativity
[36:00] Tips on communicating effectively
[21:03] "You don't need to memorize every single equation…But you must know the underlying idea."
[31:23] "Only if you measure something, you can control something"
[35:00] "Focus on the process, the result takes care of itself"
FIND MARCO ONLINE
[00:01:24] Introduction for our guest
[00:02:43] Talk to us about your journey, how you first got interested in statistics, machine learning, data science? What drew you to the field?
[00:04:10] Can you give us an overview of what cryptography is?
[00:05:52] How do you see machine learning and cryptography kind of inter playing in the near future?
[00:07:52] GDPR and data science
[00:08:53] Talk to us about the genesis of flash statistics? What was your inspiration for creating it?
[00:09:35] The mission of flash statistics
[00:10:23] Did you feel any type of internal hesitation or a fear with creating the content? And if you did, how did you overcome it?
[00:12:19] The challenge of creating content
[00:13:21] Do you have a personal favorite graphic from the archives?
[00:13:57] Correlation and causation explained via the story of the Stork.
[00:16:20] The one flash statistics painting you need to check out
[00:17:21] What would you say is the most misunderstood concept from statistics and machine learning?
[00:17:51] Would you mind clarifying or demystifying that concept for us?
[00:20:35] Do you think it's important to learn all the formula and equations even though we have advanced software that doesn't work?
[00:21:15] Do you have any tips or any good ways for somebody to learn the underlying idea behind what the software is doing?
[00:22:27] Do you consider Data science and machine learning to be an art or purely hard science? And why?
[00:23:57] What happens when you deploy a model to production
[00:27:11] The importance of version controlling models
[00:28:47] The importance of version controlling data
[00:30:33] Evaluation metrics for post production
[00:31:46] How to be creative
[00:35:57] How to effectively communicate
[00:38:22] The creative process in data science and the artistic process
[00:39:24] What's the one thing you want people to learn from your story?
[00:40:12] The lightning round