1luke2 + analytics   24

Kevin Hillstrom on Twitter: "1 - Ok, it's time for a thread / story about analytics. Start by reading the Principle below.… "
10 - During my 6-month study period, my team executed an A/B test. "A" got discounts/promotions for 6 months, "B" got nothing for 6 months.

Guess what?

Spending between A/B was IDENTICAL!! The same!

"B" profit went THROUGH THE ROOF!
ecommerce  analytics  tweetstorm  kevinhillstrom 
3 days ago by 1luke2
Free Whitepaper: How to Create Actionable KPIs and Metrics | BI Brainz Analytics on Fire
If data is king, why are most companies today still struggling with tons of data but very little knowledge? The reality is that most of them have too many KPIs (key performance indicators), but no real way to turn their data into real actions and outcomes. Creating actionable KPIs is the first step to solving this problem. To help you do this, we’ve developed a simple method to transform any KPI into a KPY. KPY = KPI + Why.
Analytics  KPIs  dashboard 
10 weeks ago by 1luke2
4 Key Areas You Should Measure for SEO
I like to track traffic to certain sections of the site:

Main pages.
Category pages.
Product or informational pages.
Blog or news pages.
Analytics  SEO  metrics  Ecommerce 
11 weeks ago by 1luke2
Mode - The Collaborative Analytics Platform for Data Analysts
SQL, Python, and R, together

Analysis requires multiple tools. SQL is ideal for some applications while R and Python are dominant in others. Mode lets you use the language that best suits the job, without jumping between applications.
data  dataviz  Analytics  Tools 
12 weeks ago by 1luke2
That’s Not a Hypothesis – art/work —behind the scenes at patreon
The cornerstone of the scientific method is forming a hypothesis. That’s a nice sentence that leads everyone to nod their head, yet a stunningly high percentage of brilliant product people don’t write real hypotheses. Instead, they write predictions, or solutions, or don’t bother with hypotheses at all.
A good hypothesis is a statement about what you believe to be true today. It is not what you think will happen when you try X. It contains neither the words “If” nor “Then.” In fact, it has nothing to do with what you’re about to try — it’s all about your users.
abtesting  Analytics  AndrewAnderson 
12 weeks ago by 1luke2
Prediction of Lifetime Value / LTV (Part 1)
Maybe this is fine at a high level, but it completely falls apart once we consider that new customers might not behave like old customers. If you've been acquiring customers with $500 in lifetime revenue and then suddenly start giving people $200 off to sign up it stands to reason that you may be attracting totally different people. If we just assume they are worth $500 we will likely be very disappointed. To ignore this is dangerous in the extreme.

So what are we to do? Option one is to measure how much value our cohorts actually create in a year and track that. Deploy a promotion. Wait a year. See whether ARPU went down. Easy! But this will give us 1 year experiment cycles and that is obviously not going to work.

It all boils down to the question of “given X days of customer data, how can I predict their year one revenue and at what accuracy”.
At ezCater we call this predicting EY1R. (Estimated Year 1 Revenue).
Analytics  Ecommerce  LTV 
12 weeks ago by 1luke2
Article Performance Leaderboard
Benchmarking across different sites is hard. The aspirational goal is measuring perceptual load time for a user - when the reader 'thinks' the page has loaded. For now this provides benchmarks to monitor.

Score = Load Time (seconds) * Speed Index * Page Size (MB)

This will be updated soon to also factor in Visually Complete and exploring Time To Interactive (TTI).
Analytics  RWD  dashboard  sitespeed 
12 weeks ago by 1luke2
Making Big Changes
This is a section from a video I did for O'Reilly back in 2015 called Data Driven Products. I think it's pretty good as a standalone set of case studies of how you might go about making changes to a web product if you care about not totally screwing up. If you like this you might also want to look at Data Driven Products Now!, which explains how you'd go about using data to inform the product discovery phase.

You have a strategic goal in mind, and you try to make tactical steps towards it one at a time. If you try a change and it’s better—or at least not worse—and it’s in the direction that you want to go, then you just keep that progress and plot your next step. #
Analytics  Design  Ux  abtesting  product 
may 2018 by 1luke2
Stop Trying to Increase Your Conversion Rates
I’ll end with this analogy of Revenue Per Visitor (RPV) being a speedometer. Remember, RPV is a summary of your conversion rate and your average order value.

Your RPV will be on the high end if you want stability and profitability. It will be on the low end if you’re interested in long term revenue growth and customer acquisition.

It’s up to you to choose where you rev the engine that is your marketing operations.
Ecommerce  Analytics  CRO 
may 2018 by 1luke2
The #1 metric to grow e-Commerce revenue | HiConversion
There are literally hundreds of marketing metrics to choose from, and almost all of them measure something of value. The main metric that will help you achieve revenue growth to your e-Commerce website is Revenue Per Visit (RPV).

Key Takeaways:

Site metrics interact with each other
Customer interaction can be either positive or negative
Revenue Per Visit is a composite index influenced by conversion rate and average order value
Ecommerce  Analytics  CRO  abtesting 
may 2018 by 1luke2
Why Revenue Per Visitor is the best metric for ecommerce
Why else do we like RPV?
Quite simply, RPV recognises that there are multiple levers which can drive an increase in profitability. Moreover, RPV is a true ecommerce metric dealing in traffic once it has been acquired. This rewards the efforts of your merchandising teams in promoting the kinds of products that lead to more business growth.
Ecommerce  Analytics 
may 2018 by 1luke2
Statistical Significance for Non-Binomial Metrics – Revenue per User, AOV, etc. | Analytics-Toolkit.com
In this article I cover the method required to calculate statistical significance for non-binomial metrics such as average revenue per user, average order value, average sessions per user, average session duration, average pages per session, and others. The focus is on A/B testing in the context of conversion rate optimization, landing page optimization and e-mail marketing optimization, but is applicable to a wider range of practical cases.
Analytics  Ecommerce  CRO  abtesting  gameplans  statistics 
may 2018 by 1luke2
Kevin Hillstrom on Twitter: "1 - I recently spoke with an Executive. This was a very bright individual. He had one flaw in his playbook."
This is a common "professional flaw" out here on Twitter. Gurus or jerks telling you global trends and strategies ... but no answers for a specific brand stuck in a specific situation.
Analytics  advice  tweetstorm 
may 2018 by 1luke2
Andrew Anderson: I am proposing 3 new rules to make all analysts and optimizers more effective and to stop the BS.
3) No one will ever use information rationally. It is hard wired in our brains to use it towards our own preconceived notions. All analysis needs to focus on the action and not give in to any red herrings or "whys" when there is no way to answer them. This is what we see, this is what we can do, this is the advantages and risks, here is the probabilities, here are possible actions." Period. End of Story. Anything more and you are just doing statistical masturbation.
Analytics  CRO  abtesting  advice 
may 2018 by 1luke2
The Seattle Times is making it everyone’s job to grow digital subscribers | Poynter
The Times' in-house analytics hub measures all the things most analytics tools measure, but it also looks at the work that leads people to pay for journalism.

The team that built it includes Josh Hart, a mobile product manager, David Parks, a data analyst engineer, and Steven Speicher, a software engineer. They tapped into data from Google Analytics, Chartbeat, LiveFyre and Crowdtangle.

Here’s how it works:

Digital subscriptions are measured by something called the “influence report.” That report produces a score based on what users clicked on before becoming subscribers over three sets of time periods. The time periods are:

One visit (people click on more than one story per visit)

One week and five pageviews

Thirty days and 25 pageviews
news  Analytics  dashboard  case-study  subscriptions 
may 2018 by 1luke2
Real attribution of retargeting ads (ultimate A/B test) - Adequate
In case of remarketing, we can, however, run an experiment that will show the exact ROI of retargeting campaigns.

We assign to each user who visited the website, on a random basis, a Google Analytics custom variable with a value of “A” or “B”. It is a user-level variable (not session-level or page-level), and re-visit does not overwrite the value.

Then we use Google Analytics remarketing list (custom variable “A” and “B”) and display the remarketing campaign only to the users from the “A” list.
Retargeting  adwords  Analytics  Ppc 
april 2018 by 1luke2
From Project To Process | Simo Ahava's blog
A typical example is in Ecommerce tracking. Ecommerce comprises such a huge number of variables that successful comparison across date ranges would require that these variables be encoded consistently across different points in time. How often does that happen? I’m willing to say rarely, and the likelihood decreases with time. However, still we see people comparing Revenue from last quarter (which included shipping and tax) with Revenue from a year ago (which did not include shipping and tax). The very fact that they have different aggregation methods means that they can’t be compared unless you know how these methods differ. Unfortunately, this information is often misplaced when teams and organizations change.
In other words, data collection is an investment. It requires labor, love, and a crystal ball. It’s one of the most difficult things to get right, and requires a lot of experience. But there’s nothing, nothing as frustrating as data that’s missing or incorrectly collected.
2. Analytics as a PROJECT is the root of all evil

Here we go: diving into the controversial end of the pool. Let me juice it up with another claim.
Ecommerce  GTM  Analytics  gameplans  Business  advice 
april 2018 by 1luke2
The ULTIMATE eCommerce Analytics Guide | Oribi Blog
Any eCommerce website owner’s main goal is to increase its sales and revenues. The most effective way to do so is choosing the right analytics tool (or tools) for your needs, learning how to make the most out of it, and taking data-driven decisions based on the detailed data provided.
Ecommerce  Analytics 
april 2018 by 1luke2
Sophie Bakalar on Twitter: "Some KPI benchmarks for consumer brands: - AOV (online): $60+ (ideally $100+) - GM%: 30-40% for bev/frozen, 40-60% for food, 50%+ for apparel, 70%+ for personal care - Retention (subscription): 1M: 80%+, 6M: 30-40% - CAC: $25-7
Some KPI benchmarks for consumer brands:
- AOV (online): $60+ (ideally $100+)
- GM%: 30-40% for bev/frozen, 40-60% for food, 50%+ for apparel, 70%+ for personal care
- Retention (subscription): 1M: 80%+, 6M: 30-40%
- CAC: $25-75
- LTV/CAC: 4x+
- Organic acq.: 25%+
ecommerce  analytics 
april 2018 by 1luke2
GTM Guide: dataLayer.push with examples - Analytics Mania
DataLayer.push is a way for you/developers/3rd-party-plugins to pass some useful data to the Data Layer. And from there you can “play with it” in Google Tag Manager.

DataLayer.push should be the only way how you should be adding data. Even though Google Tag Manager official documentation still mentions/recommends using a regular Data Layer declaration (dataLayer = [{}]), you should not fall for that.
GTM  googletagmanager  Analytics 
april 2018 by 1luke2
What Product Managers Can Learn From Digital Analytics - Blair Reeves
Nancy: One of the big things I’ve learned is that educating everyone else around me at my company was a big part of my role, and no one (including myself) really anticipated that. The biggest items I had to continually preach: Implementation is not a “set it and you’re done” exercise. Any and all change introduced to a website or app can disrupt or break tracking. It’s so much more fragile than anyone ever thinks. The fact that QA had to happen with every release – and simply to try to preserve the tracking and data collection we had in place. And, focusing on what was truly important to measure, and making sure our data collection was rock solid.
Analytics  Business  Interview 
april 2018 by 1luke2
A dirty dozen: twelve common metric interpretation pitfalls in online controlled experiments | the morning paper
A dirty dozen: twelve common metric interpretation pitfalls in online controlled experiments Dmitriev et al., KDD 2017

Pure Gold! Here we have twelve wonderful lessons in how to avoid expensive mistakes in companies that are trying their best to be data-driven. A huge thank you to the team from Microsoft for sharing their hard-won experiences with us.
abtesting  metrics  analytics 
january 2018 by 1luke2
Picking a cloud database for analytics: the SQL options | Parse.ly
This post will compare:
1 Amazon RDS (Postgres)
2 Google Cloud SQL (MySQL)
3 Amazon Redshift
4 Google BigQuery
It will also serve as a guide for choosing between these options, including the technical pro’s and con’s of each.
Mysql  BigQuery  SQL  Analytics 
december 2017 by 1luke2

Copy this bookmark:



description:


tags: