This month’s event was over a year in the making, but it was well worth the wait! It was a joint meetup of R-Ladies Columbus and Columbus WAW:

• For the R crowd, it was an introduction to digital analytics data
• For the digital analytics crowd, it was an introduction to R
• For the crowd that had already been crossing over, it was an evening where the peanut butter and chocolate finally came together to make an Reeses’s cup!

Dr. Katie Schafer from Covail provided an introduction to R using a (still available!) RStudio Cloud project and then walked through a set of Google Analytics data all the way from some basic exploration of the data to a linear model attempting to predict the drivers of revenue per visit (RPV). The model itself was not very “good,” but the point of the exercise was to provide a basic introduction to the platform and approach, as well as to show how to both run and evaluate a model.

Some of the basic exploration of the data…and of ggplot and faceted plots:

Some more exploration using a scatterplot:

And some of the results of a generalized linear model:

It was a fun evening!

It was our third virtual event, and we’re slowly managing to find our groove in this meetup-by-Zoom era. With an unexpected boost by way of a tweet from @googleanalytics, we had a strong and engaged showing, including attendees from four continents (North America, Europe, Australia, and Africa)! The crowd was not disappointed, as Mai AlOwaish from InfoTrust provided a concise, but quite thorough, rundown of the ins and outs of Google App+Web.

A smattering of takeaways:

• As a platform that draws heavily on Firebase Analytics, it is a fundamentally user-centric platform that relies on an event-based model. Fare thee well “all hits are of type: pageview, event, or transaction!”
• The event-based model has great power…but also will take some getting used to for those who are steeped in a long tradition of Universal Analytics
• The platform has been in beta since July 2019. But, what does “beta” even mean in Google terms? Don’t they keep things in beta when they’re clearly ready for production use? Well, yes…but it would be pretty risky to just deploy App+Web at this point. Functionality to match, for instance Enhance Ecommerce has not yet rolled out (but there are many signals that it is imminent)
• Unlike the cutover from the original Google Analytics to Universal Analytics, dual-tagging a site with both Universal Analytics and App+Web is not a problem: they use different measurement protocols and send data to different realms within the Googleverse.
• App+Web—a free platform—has native connectivity to Google BigQuery (one of those things that used to stand out as a differentiator between free Google Analytics and GA360). Of course, depending on the volume of traffic you’re sending to BigQuery, you may wind up with a bill for that, but the analytics platform itself does not incur a cost.
• The “Analytics Hub” adds a more robust analyst tool for working in a browser to drag and drop dimensions and metrics and do handy visualizations like Venn diagrams to visualized the overlap between two segments.

And much, much more! But, you can just watch the video of her presentation for a full run-down (or check out the slides):

There were a few notable links shared in the chat for more information:

• Mai’s DAA blog post about App+Web
• Simo Ahava’s tweet that shows the non-NDA version of the App+Web roadmap

This meetup was, once again, also a fundraiser for the Mid-Ohio Food Collective. With help from our sponsors we’re matching the first $1,000 donated! Thanks so much to those who have already donated, it means a lot to us and even more to the people you’re helping. We’ve still got matching funds available, you can donate here now. We’ll be running the campaign for the rest of the month so it’s not too late!

For our June event, Mai Alowaish from Blast Analytics and Marketing made the trip down I-71 from Cleveland/Akron to share an information-packed presentation on the many facets of mobile app analytics.

Her presentation covered:

• An overview of what mobile app analytics is (and how it differs from mobile site analytics and hybrid app analytics)
• The different underlying types of app analytics: marketing analytics (downloads, shares, deep linking performance, etc.), performance analytics / app health (crashes, errors, latency, etc.), and in-app analytics / product analytics (funnel behavior, personas and demographics, drop-off points, etc.)
• The myriad different platforms for app analytics — which type(s) of app analytics they cover, as well as what their interfaces look like and enable
• The different considerations when it comes to how to implement app analytics: to TMS or not to TMS? API hubs? CDPs?
• How to actually go about planning what to track (see the speech bubble below for a key to that!)

The presentation is available for detailed perusal here.

We had a full house of engaged attendees!

And, as we’ve been doing all year, we had Columbus Web Analytics Wednesday T-shirts as a door prize drawing! One of the lucky winners was actually in town from the Bay Area, so we pretty much assume that “cbusdaw” will be assumed to be a hot new startup inside of a week, and we’ll be fending off venture capital funding offers:

If you’d like to experience the presentation almost as though you were there:

1. Load up a plate with a few slices of pizza
2. Get yourself a tasty beverage
3. Watch the video below that Mai was kind enough to record with her slides and her voiceover!

We’ll be continuing our streak of fantastic content from out-of-town speakers next month when Valerie Kroll joins us to share her tips for presenting results that inspire action. We hope to see you there!

For our May event, we cast our speaker net out-of-state and convinced Jim Gianoglio from Bounteous to make the trip from Pittsburgh to share his experience and his thoughts on the myriad paths that exist for perambulation from “analyst” to “data scientist.” Or, as Jim subtitled his talk: “the transfiguration from reporting squirrel to unicorn:”

It was a packed house for the event, as Jim walked through his various explorations of options for advancing his analytics skills into the world of data science, which he boiled down to three options:

1. Entering a formal degree program (online or offline)
2. Relying on the various online courses and content that are available for free or a nominal fee
3. Attending a bootcamp.

Jim initially dabbled in online courses, but, ultimately, went for a formal degree through Carnegie Mellon. The pros of that approach:

1. The cost and face-to-face schedule meant that, even as the going got tough, bailing wasn’t really an option.
2. The in-person interactions with professors and students made for productive collaboration and deeper learning (…including on the subject of — wait for it — deep learning, presumably </editorial license>).
3. The networking benefits — in a traditional sense, this would mean that Jim was set up to hop to another role following the program, but, in this case, it meant that two of his fellow students got hired by Bounteous!
4. The cachet of having a Master’s degree from a school like Carnegie Mellon — that’s good for the resume!

Of course, there were also downsides:

1. It was an intensive and exhausting two years, as Jim continued to work full-time throughout the program, while also having a wife and three young children.
2. It wasn’t cheap. Jim did the math as to how/when he would expect a return on his investment, and it made sense.
3. There were still some “dud” professors, which can also happen in the online world, but, when you find yourself calculating a “cost per hour” during a lecture and getting a little steamed, that can be disheartening.

While Jim opted for the in-person, formal degree program, he also discussed — and provided a number of resources — for other options (some of which he availed himself of both before and after his formal coursework):

• Online degree programs from accredited universities
• Open courseware and content — use resources like the Open Source Data Science Masters to put together your own curriculum!
• Bootcamps — although Jim warned that there is an explosion of these being offered, so the quality varies wildly, and bootcamps can make unrealistic claims (“Become a data scientist in just 14 weeks with our bootcamp!”)

Ultimately, there are an overwhelming number of options, which can be intimidating, but it also means that analysts can do some research and introspection and then figure out what is the best option for them!

Ultimately, with a little bit of statistics, some Python, and a little bit of R, you, too, can catch yourself speaking like a data scientist!

Jim shared his slides (with notes) here if you missed the event or attended and would like to reference the material. A smattering of resources he referenced and recommended are:

• An Introduction to Statistical Learning with Applications in R — a free, downloadable book
• The Data Science Specialization on Coursera
• Kaggle’s Data Science Education resources
• fast.ai online courses

Join us in June for a discussion of mobile app analytics as Mai Alowaish from Blast Analytics & Marketing shares tips and best practices for mobile app analytics!

At our November event, we brought back a past speaker — Tim Wilson from Search Discovery (and the Digital Analytics Power Hour podcast) — and a past topic: data visualization.

The one governing idea that Tim tried to convey (see the recap of Ruth Milligan’s presentation from our August event) was that effective data visualization is not about art or creativity nearly as much as it is about neuroscience. Simply reducing the cognitive load we’re placing on our audience is the best way to get them to focus on the data and message we’re trying to convey. Reducing the cognitive load means simplifying the visualization, and then simplifying it some more!

The slides from his session:

Or, if you think Tim’s dynamic delivery of the material would enhance your review, a video of said delivery (with the bonus of the Rev1 poltergeist glitching the slides regularly throughout the presentation):

The books Tim recommended for attendees to learn more were:

• Brain Rules: 12 Principles for Surviving and Thriving at Work, Home, and School by John Medina — for learning more about the relevant neuroscience when it comes to how we take in and retain information
• Information Dashboard Design: Displaying Data for At-a-Glance Monitoring by Stephen Few — a mix of neuroscience and tactical tips for effective data visualization
• The Wall Street Journal Guide to Information Graphics: The Dos and Don’ts of Presenting Data, Facts, and Figures by Dona M. Wong — a handy reference with specific guidelines for effective data visualization

One of Tim’s tips was about building dashboards using Microsoft Excel (using very narrow columns to provide a somewhat flexible layout grid). He referenced that he had also presented in more detail on this topic, and, based on the overwhelming interest* in that material, we’re going ahead and including one of those presentations in YouTube form below:

* One person asked him about it after the presentation.

It’s undeniable that the world of analytics is rapidly evolving, so our May event dove into what that really means. Third time #cbusdaw speaker Mike Amer gazed into his crystal ball and shared his thoughts on the subject:

The topic was actually prompted by a discussion he had with Dave Culbertson at a WAW earlier this year, when Dave asked, “Should I be worried that AI is going to take my job?” Mike’s conclusion, “Dave, you’re probably old enough that you’re okay, but there are plenty of younger folk who need to assess what their job is, because AI will be eliminating a lot of tasks (the drudgery ones, mostly) that we do today.”

Ultimately, we need to be very cognizant that any analytics-related technology or capability can be plotted somewhere on the Gartner Hype Cycle:

It can be tricky, in the moment, to figure out exactly where a particular technology falls. But, they all follow this pattern — ramping up to grossly inflated expectations before cratering into the trough of disillusionment.

What’s not really new is “the math.” Humankind figured out calculus 300 years ago (although whether Gottfried Liebniz or Sir Isaac Newton should get credit for that can be debated):

In short:

• The volume of data being generated doubles every year
• The tools are getting better and better at managing that data
• Natural language processing is coming on strong, BUT
• We’re a lonnnng way from Skynet, and we’re a lonnnng way from AI being effective at storytelling
• While AI will be taking on drudgery/tedious tasks sooner rather than later, there is still plenty of work to be done in analytics that requires human thought

As always, it was an engaged crowd, including an unintentional display of rabbit ears:

And, as always, there was good food and drink:

No topic and low key at Plank’s. That’s the way we traditionally roll in December, and this year was no different!

Tommy’s arrival was latter than usual, but he stopped in to let us know that he is NOT a fan of Aaron Judge of the Yankees.

Our November event was part 1 of a loose 2-part series (with part 2 coming in January, because not even attribution will get in the way of our annual holiday event in December!). For our November event, Jason Packer of Quantable walked through the basics of marketing channel attribution.

“Basics” undersells the content a bit. Among other aspects of the subject that Jason covered:

• How “attribution” questions often really turn out to be (cross-device / cross-session) user identification questions
• How even imperfect efforts at attribution (which all attribution will be) is still better than no attribution
• That “last click” is attribution… but it’s the form of attribution that is perhaps the closest to no attribution and the farthest from perfect attribution
• The two fundamental approaches to attribution: heuristic (the “pick your weighting” approach offered in the free version of Google Analytics) and data-driven, or algorithmic (if you’re working with Shapley values or Markov chains, then you’re in the data-drive world of attribution)
• That not all heuristic approaches are created equally, including an explanation as to why some make more intuitive sense than others

See the full slide deck below:

Or, check out a video of Jason’s presentation courtesy of Mixt Media:

Some links for further reading:

• Assisted conversions explained (by Jason)
• Markov Chains for Attribution
• Shapley and Markov models compared using R
• Markov explained visually
• Shapley explained

For our September event, Beth Sibbring from Tangible Impact walked us through the concept of a “creative intervention” when it comes to digital creative. But, before she could get to that, emcee Dave Culbertson closed his eyes and took us all the way back to 1979 — the year that Compuserve was founded:

He assured this was a number of years before he worked for Beth there!

Beth then walked us through common pitfalls she sees companies fall into when it comes to developing, testing, and optimizing the creative for their digital campaigns. She opened with this statement from comScore ARS Executive Vice President Jeff Cox:

“Based on our years of research…we’ve determined that the quality of the creative is four times more important than other characteristics of the media plan in generating sales.”

Yet, as Beth noted, a slew of other factors often drive the actual creative that hits the internet:

• Adherence to production specs and brand standards…without the creatives being accountable for campaign results
• Existing creative that already exists…even if it’s not the most appropriate for the campaign or tactic
• Deadlines that slip in the planning and buying phases of the effort such that the creative becomes a “just get us something as fast as you can” exercise
• The design opinions of one or more members of the brand team…who do not have training or knowledge about best practices for the medium

And, of course, Beth used several examples to illustrate the importance of testing multiple creative approaches and planning for and committing to mid-campaign optimization!

Beth’s complete slide deck is below:

As an added bonus for the (WAW) old-timers at the event, the third original co-founder of Columbus WAWs wayyyy back in 2008, Scott Zakrajsek, made his triumphant return to central Ohio after an 8-year hiatus in Boston. Three weeks after his return to Columbus, he returned to WAW!

(Is it, then, only a matter of time before Monish Datta, too, returns?)

For our July event, we mixed things up by heading to Nationwide Arena to be hosted the Columbus Blue Jackets digital marketing team. Jeff Eldersveld, the Director of Digital Marketing an Analytics for the Blue Jackets, walked through the role of digital in a professional sports league — the dual calculations of immediate return (a ticket sale) versus lifetime value, the importance of being ready to respond to team news that fans will care about, and the challenges of marketing when a major driver of results is the team’s performance.

Click on the image below to view Jeff’s presentation:

Following Jeff’s presentation, we took a tour behind the scenes at Nationwide Arena, including walking out on center ice (well, center concrete — the season has been over for a bit at this point!):

We even had a few of the players stop by, and, wow, did their body proportions surprise us!