What We Are Reading

R Generation: 25 Years of R - Link

R has become 25 years old this August.

After 25 years, R is still growing, and a lot. It’s an open source software so it is hard to grasp the real impact in the world. (we won’t see any media or TV ads of R, for example, unlike other commercial products.) But I’m sure it’s huge either via direct or indirect.

And the modern R a.k.a. tidyverse has influenced even much wider audience. I’ve seen many Exploratory users originally converted from Excel now typing dplyr commands directly in the command input, and telling me how much they love tidyverse.

R community’s focus on welcoming new and diverse users and making it easier to start using R is such an amazing gift in this world.

DAU/MAU is an important metric to measure engagement, but here’s where it fails - Link

There is no one metric that fits all. Different startups need different metrics.

“So let’s say that you want your DAU/MAU to increase – so what do you do? Funny enough, a lot of people seem to implement emails and push notifications thinking it’ll help. My experience is that it tends to increase casual numbers (the MAU) but not the daily users. In other words, it’ll actually lower your DAU/MAU to focus on notifications because you’ll grow your MAUs more highly than your DAUs.”

What Machine Learning Can and Cannot Do - Link

It’s a good summary listing up 8 things we need to know when we employ ML. Also, a good reminder that ML is not simply eliminating jobs in the low skill market, it’s actually increasing depending on what type.

“At the same time, we’ve seen the steady growth of jobs involving non-routine, low skill manual tasks, - e.g., food and cleaning services, personal care and health care aides, - and non-routine, high skill cognitive tasks, - e.g., managerial, professional and technical occupations.”

Guidelines For Ab Testing - Link

Good summary of what you need to know when you do A/B test in 12 points. Start early, and start small.

New data tools for relief organizations: network coverage, power, and displacement - Link

Data Science teams at Facebook continues to amaze me in both technical and humanity ways. They are making positive and real impacts to our world, and this side of Facebook should be talked about more in media.

Quote of the Week

“Experience by itself teaches nothing.”

by Edward Demings

What We Are Writing

We have written the following 3 blog posts recently.

• Visualizing a Dramatic Increase of Opioid Addicted Mothers Giving Birth - Link
• 5 Most Common Data Wrangling Operations with Date & Time Data - Link
• Cohort Analysis by Pivot Table and Layer Cake Graph - Link

What We Are Working On

Exploratory v5.0

We’re planning to release the next big thing most likely in October.

We are adding a few new Analytics, and one of them is Market Basket Analysis (Association Rules). You can run it as the data wrangling step (Link) and visualize it nicely in Note (Link), but in v5.0 you can simply click a button to run and get nice visualizations on the fly under Analytics view.

Also, we are adding Decision Tree. At the end of the day, people still love Decision Tree because of its simplicity and better interpretability. This will be available under Analytics view as well.

Data Science Booster Training

Our next online Data Science Booster training will be in this coming September. If you are interested in learning Data Science without programming, make sure to sign up soon!

Enroll September Booster Training!

If you are a current student, click here to get the student discount.

That’s it for this week.

Have a wonderful week!

Kan CEO/Exploratory

Subscribe Weekly Updates!

This is a weekly email update of what I have seen in Data Science / AI and thought were interesting, plus what Team Exploratory is working on.