analytics
![Brian Piercy](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="%230A66C2"><path d="M20.447 20.452H16.89v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286zM5.337 7.433a1.982 1.982 0 1 1 0-3.964 1.982 1.982 0 0 1 0 3.964zm1.782 13.019H3.555V9h3.564v11.452zM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003z"/></svg>)
Here's the handout I prepared for my NICAR 2026 workshop "Coding agents for data analysis" - a three hour session aimed at data journalists demonstrating ways that tools like Claude …
ChatGPT helps you get answers, find inspiration, and be more productive.
The rise of "zero-click" searches may signal the coming effect of AI shopping on product discovery and decision-making.
Discover which statistical methods dominate healthcare, finance, tech, retail, and sports analytics, and why these industry-method pairings became indispensable standards.
Learn what Shapley values are and how SHAP tools help explain machine learning predictions.
Learn to calculate and interpret five essential effect size measures with Python examples and clear guidance.
Learn to calculate support, confidence, and lift metrics for market basket analysis using Python's mlxtend library.
Discover hidden customer purchasing patterns with market basket analysis to optimize product placement and increase sales.
In this article, I'll take you through a practical guide to RFM Analysis using Python. A Guide to RFM Analysis using Python.
Umami is a simple, fast, privacy-focused alternative to Google Analytics. - umami-software/umami
Marketers should be wary of open-source programs promoted by purveyors with a walled garden history.
A SWOT analysis helps teams understand how well a product, service, or organization is positioned in the market to serve its customers.
Uncover deeper insights beyond ZIP codes with geospatial analysis. Explore the limitations of ZIP codes and discover alternatives for spatial understanding.
Still, the exact application, challenges and shortcuts related to this technique are relatively unknown, and that’s what this article seeks to change.
Use methods like 5-second testing, first-click testing, and preference testing to gain insights into how users perceive your visual design.
This is a repo with links to everything you'd ever want to learn about data engineering - DataExpert-io/data-engineer-handbook
GA4 provides valuable insights into user interactions on your website. Learn how to analyze key metrics like sessions, session duration, and events to refine your digital strategy.
Goodhart's Law is useless. It tells you about a phenomenon, but it doesn't tell you how to solve it. We look at how organisations actually prevent Goodhart's Law, and illustrate this with Amazon's Weekly Business Review as an example.
How to build upon a previous experiment, without throwing it all away.
Hey guys, welcome back to my R-tips newsletter. Supply chain management is essential in making sure that your company’s business runs smoothly. One of the key elements is managing inventory efficiently. Today, I’m going to show you how to estimate inve...
“If you want to change the game, change the frame.” The game has certainly changed with the data era, and maybe the most drastic change driven by data has occurred in economics, the foundation upon which our modern society is built and sustained. Understanding and mastering the transition from “traditional” economics to modern data-driven economics… Read More »Mastering the Big 12 Data-driven Economic Concepts
Learn which variables you should and should not take into account in your model.
In this article, I'll take you through the task of Customer Satisfaction Analysis with Python. Customer Satisfaction Analysis with Python.
A/B testing is a cornerstone of data science, essential for making informed business decisions and optimizing customer revenue. Here, we delve into six widely used statistical methods in A/B testing, explaining their purposes and appropriate contexts. 1. Z-Test (Standard Score Test): When to Use: This method is ideal for large sample sizes (typically over 30) when the population variance is known. Purpose: Compares the means of two groups to determine if they are statistically different. Applications: This technique is frequently employed in conversion rate optimization and click-through rate analysis. It helps identify whether changes in website elements or marketing strategies
The authoritative guide on how Amazon does WBRs (from former exec Colin Bryar): how it works, how to do it, and how Amazon uses it to win.
Create your first run chart and start interpreting your data using just four rules. Your go-to QI resource.
Analytics, management, and business intelligence (BI) procedures, such as data cleansing, transformation, and decision-making, rely on data profiling. Content and quality reviews are becoming more important as data sets grow in size and variety of sources. In addition, organizations that rely on data must prioritize data quality review. Analysts and developers can enhance business operations by analyzing the dataset and drawing significant insights from it. Data profiling is a crucial tool. For evaluating data quality. It entails analyzing, cleansing, transforming, and modeling data to find valuable information, improve data quality, and assist in better decision-making, What is Data Profiling? Examining
Visual, interactive sample size calculator ideal for planning online experiments and A/B tests.
Window functions are an advanced feature of SQL that provides powerful tools for detailed data analysis and manipulation without grouping data into single output rows, which is common in aggregate functions.
More than half of the NCAA Tournament's top teams have used HD Intelligence services, as basketball's data revolution sweeps through the college game.
At most small and medium-sized e-commerce retailers, prices are typically set and updated in an ad hoc fashion without one clear owner. The process often starts by using a gross margin target, followed by some comparison with competitors, and then some adjustments from there. Many of these retailers would quickly admit that this isn’t an optimal strategy, and that they are likely leaving money on the table — and they’re often right. The authors’ experience with price testing has shown that there is actually a significant amount of money left on the table when pricing is left un-optimized.
Knowing the URLs in search engine result pages leads to further analysis, such as referring domains, page authority, word count, and more.
Evaluating ad targeting product using causal inference: propensity score matching!
In this article, I'll take you through the task of Market Basket Analysis using Python. Market Basket Analysis using Python.
Two principles on collecting data, from the field of Statistical Process Control. As with most principles in SPC, this is both simpler and more important than you might think.
Since starting PostHog in 2020, we’ve learned a bunch about what does and doesn’t work when it comes to marketing to engineers . Paid ads is a…
Using data provided by Vivid Seats and Instagram, I learned that social media clout isn't all it's cracked up to be.
An obsessively detailed guide to Customer Lifetime Value techniques and real-world applications
These tools can help you analyze PPC competitors, track search trends or design ad creative – all without spending a dime.
For non-tech industry folks, an “A/B test” is just a randomized controlled trial where you split users or other things into treatment and control groups, and then later compare key metr…
8 stories · A guide to building an end-to-end marketing mix optimization solution for your organization.
A spreadsheet on ad platform Xandr’s website revealed a massive collection of “audience segments” used to target consumers based on highly specific, sometimes intimate information and inferences
Applying causal machine learning to trim the campaign target audience
How to compare and pick the best uplift model
Looking for the best alternative to Google Analytics 4? Here are 15 web analytics platforms you may want to consider.
Running experiments is equal parts powerful and terrifying. Powerful because you can validate changes that will transform your product for the better…
An in-depth explanation of “Thompson Sampling”, a more efficient alternative to A/B testing for online learning
An in-depth look at seven tools used by enterprises for content optimization, technical SEO, and reporting and analytics.
This article will take you through everything about Cohort Analysis that you should know. What is Cohort Analysis in Data Science?
In this article, I will walk you through the task of Retail Price Optimization with Machine Learning using Python. Retail Price Optimization.
In this article, I will take you through the task of Supply Chain Analysis using Python. Supply Chain Analysis using Python.
From Villa's weirdly disconnected midfield to Forest playing passes near their corner flags, here's what we can learn from analysing passing
How to adjust CATE to consider costs associated with your treatments
When you use supermarket discount cards, you are sharing much more than what is in your cart—and grocery chains like Kroger are reaping huge profits selling this data to brands and advertisers
Effective log management is a fundamental aspect of maintaining and troubleshooting today's complex...
Questions on A/B testing are being increasingly asked in interviews but reliable resources to prepare for these are still far and few…
An easy-to-read, highly condensed analysis of all the known, confirmed, rumored, and absolute myth-level Google ranking factors.
Using and choosing priors in randomized experiments.
Media Mix modeling, its implementation, and practical tips
A Discussion of the go-to methods for 5 Types of A/B Metrics
Learn how to build MMMs for different countries the right way
I recently rewatched "The Wire". The show's central theme is about counter-productive metrics and their corrupting influence on institutions. I've noticed hints of this pattern in software engineering, too
Software culture and the abuse of data
Use these tips to quickly analyze performance data and identify high-impact PPC optimizations that will move the needle.
In many board rooms, the most important go-to-market number this quarter is pipeline health. For some companies, the pipeline may be less clear than a quarter or two ago. Summer seasonality may play a role. Macroeconomics might also be lurking within the numbers. Pipeline fluctuations are normal. But any meaningful & unexpected surprise warrants introspection. Pipeline analysis often has four parts: Craft the sales sandwich to predict your GTM conversion rates & determine if close rates have changed in parallel.
Amazon will continue to be highly competitive. Want to be successful? Optimize your product listings to the fullest with these tips.
How today’s tech companies make data-driven decisions in Machine Learning production
While Fisher’s exact test is a convenient tool for A/B testing, the idea and results of the test are often hard to grasp and difficult to…
There is a huge and ever-widening gap between the devices we use to make the web and the devices most people use to consume it. It’s also no secret
If you go to three different analysts looking for a definition of "churn rate," they will all agree that it's an important metric and that the definition is self evident. Then they will go ahead and give you three different definitions. And as they share their definitions with each other they all have the same response: why is everyone else making this so com
Over the past few years, marketing on the web has become way too much fun. I remember trying to figure out what “hits” on awstats [http://awstats.sourceforge.net/] meant in high school, and I distinctly can recall how disappointed I was when I found out the true meaning. Nowadays,
Getting useful cancellation feedback from customers is tough. The problem is that once people have canceled, they’re no longer engaged and will rarely spend the time to give you feedback. One of the best things I’ve ever done to combat this with Bidsketch was to add a mandatory freeform text field that says: Please help… Continue reading Getting 200% More Actionable Feedback from Customers that Cancel →
Simple Analytics is a privacy-friendly and simple alternative to Google Analytics. No cookies. No trackers. No consent required from your visitors. Just straightforward analytics.
As of 2024, The Data Incubator is now Pragmatic Data! Explore Pragmatic Institute’s new offerings, learn about team training opportunities, and more.
Analyzing the SERPs for these micro intents will help you create the right content that a searcher will want to find.
Marc Andreessen famously said that for startups, “the only thing that matters is getting to product/market fit.” Product/market fit means providing enough value to enough people that the startup can…
I sit down and learn how to get insights from churn rates, conversion rates, and more to answer some important questions about my product.
I have a theory: No Diggity by Blackstreet is timeless. If Frank Sinatra is timeless in 2015, so too is No Diggity in 2050, fondly remembered by our children's children as the icon of the 90s. And I think that I can prove it.
Pricing is hard. Make it too low and you miss out on profit; too high and you miss out on sales. These pricing experiments will help you get it right.
this is a guest post by Kareem Mayan. customer retention was a recent topic in our predictable […]
A/B testing is hitting the mainstream because it is so effective. And with so many tools available it has become very easy and very inexpensive to run. Here are 23 helpful tips on how you can take your A/B tests from basic to the next level.
You must test ads to make your paid search account grow and thrive. That fact is no longer debatable – it is just a best practice fact. Ad testing in
A/B testing tools often lie about whether something is "statistically significant." Here's an extremely simple, mathematically sound formula to compute it for yourself.
A/B tests provide more than statistical validation of one execution over another. They can and should impact how your team prioritizes projects.
Koru CEO Kristen Hamilton helps hundreds of people hire and get hired every year. These are the traits she knows translate into excellent performance on the job.
Contributor Aleh Barysevich breaks down three strategies you can use to boost the effectiveness of your internal link building campaigns to fulfill specific SEO-related goals.
The antidote to vanity metrics when you have less than 1 hour/week for marketing analytics
Simple Analytics is the privacy-first Google Analytics alternative that is 100% GDPR compliant. Give us a try!
We’re Agile, we think lean, we’re data-driven. If you live in the new economy and work in some sort of digital product you hear some of…
An applied introduction to causal inference in tech
In "Email Marketing Metrics, Part 1: The Basics," my article last month, I addressed the primary measurements for email marketing: delivery rate, open
We spoke with Etsy’s iOS Software Engineer, Lacy Rhoades, about their culture of continuous experimentation. Learn about their a/b testing culture
There’s widespread use of adblockers on the web but users are increasingly blocking cookies and other tracking scripts too. Browsers such as Safari, Firefox and Brave are privacy-focused.
If you are working in the field of SEO or if you are managing a content or Ecommerce website then you...
A cohort is a group of people who share a common characteristic or experience within a defined period. This is a handy tool for browsing cohort datasets.
Unlock data to make effective decisions across digital marketing. SEO, content marketing, PPC, digital PR, and more.
Articles, software, calculators, and opinions.
“My biggest surprise was when we launched the Facebook app and it didn’t go viral” -Startup CEO quote “The month after we ...
Deploy and update measurement tags on your websites and mobile apps from a web interface, without major code changes or app releases.
Knowing what to test and how to interpret the results based on nuances and oddities of experiments is an important skill for people, not automations.
A/B testing is a very popular technique of checking granular changes in a product without mistakenly taking into account changes that were…
Hey everyone! I star all kinds of crazy GitHub repos and last week I stumbled on an awesome project...
Multivariate tests indicate how various UI elements interact with each other and are a tool for making incremental improvements to a design.
With the ubiquity of music access and a lack of any need for patience, the term "skip-rate" has crept into the modern music industry lexicon, and some new data behind. Continue reading
The best way to determine what works best for your site is to carry out an A/B test for your landing pages. Check out this A/B significant test calculator.
How to build a free, privacy-focused alternative to Google Analytics
Developers don’t do SEO. They make sure sites are SEO-ready. That means developers hold the key to SEO. It’s true. If you’re a developer and you’re r
Spotify analytics for listeners is how the popular streaming service also captures the hearts of its users. Many websites allow
Content marketing has become an increasingly popular way for brands to promote themselves. It is subtle and generates more leads than traditional
Search engine optimization for ecommerce boils down to four buckets. That's according to Jeff Oxford, founder of 180 Marketing, an Oregon-based firm.
Shoppers' actions on an ecommerce site create opportunities for automated, triggered emails. Such behavior-based email automation is a sure-fire tactic to drive revenue.
Monitoring rankings remains the best way to track organic search performance. In this piece, we list five helpful tools to track your site's positions and your competitors'.
Conjoint analysis is a highly effective means of market research, capable of informing a company’s pricing strategy and product development.
Conjoint analysis is the optimal market research approach for measuring the value that consumers place on features of a product or service. Learn more!
Here are four of the top technical SEO issues that your auditing tools won't show you and how to find them.
Our A/B test calculator will help you to compare two or three variants to determine which test will be statistically significant.
The way we live our lives has an impact on our work. Long lists of typical chores may turn your
Competitive poaching refers to the practice of bidding on ads for a competitor’s search terms, in order to poach customers searching for that brand. It’s a common tactic in the world of digital ads — but is it effective? The author shares results from the first-ever empirical study of this practice, which found that poaching can work well for higher-end brands, but may backfire for lower-end or mass market offerings. Specifically, the study found that when an ad poached customers who searched for a high-end brand, users clicked on it more, but when an ad poached a low-end or mass market target, users were less likely to click. Of course, the author notes that clickthrough rate is just one metric, and there may be other ways in which a poaching campaign could be harmful or beneficial. But these findings can help marketers add a bit of science to the art that is digital advertising, helping them to optimize campaigns for their unique products and customers.
Keyword lists for SEO are often cluttered and seemingly endless. "Clustering" can help by grouping keywords by a common modifier.
The Landing Page report. Universal Analytics has it. GA4 does not. But you can make it! This article will show you how.
It's time to optimize for People Also Asked questions asked around and about your brand in Google's SERPs. Here's why.
The most consistent sales leader I’ve worked with hit plan 27 consecutive quarters. How can a sales leader develop similar repeatability? Much goes into it here are the reports he used to manage his team at the board level. The PQR (pipeline-to-quota) funnel is first. Pipeline is the total value of the accounts within a stage or later. Quota is the aggregate quota on the street for the quarter. Divide P by Q to get PQR.
Tracked analytics metrics should reflect change in the user experience. Vanity metrics appear impressive, but their fluctuations are not actionable.
Elaborate usability tests are a waste of resources. The best results come from testing no more than 5 users and running as many small tests as you can afford.
Keyword Tool is #1 (FREE) alternative to Google Ads Keyword Planner for SEO & PPC keyword research ᐈ Generate 1,000s ✅ long-tail keywords in seconds!
Common mistakes to avoid when you’re getting started with experimentation
A/B testing, the process of exposing randomized visitors to one or more variables, is among the most effective strategies to optimize user experiences and conversion rates. Here is a list of A/B testing tools.
Is Google Analytics still useful and how accurate are its stats? How much data is missing from Google Analytics due to adblockers and privacy-friendly browsers?
Managing a Google ads campaign requires understanding how to check, optimize, test, and change your ads. Read this post to learn more.
Not sure where to start with marketing automation? Here are 25 tools, and how to use them to streamline and improve your marketing.
Technique used to gain insights about consumers’ preferences
Pie charts and scatter plots seem like ordinary tools, but they revolutionized the way we solve problems.
Statistics & Business can share the same Language
A new approach in the way the Census aggregates its data could make it more difficult to do extreme gerrymandering, says Moon Duchin.
In marketing analytics, conjoint analysis is a technique used to gain specific insights about consumers’ preferences. Often derived from consumer surveys, conjoint analysis can tell us, for instance…
Thirty years ago, Billboard changed the way it tabulated its charts, turning the industry on its head and making room for genres once considered afterthoughts to explode in the national consciousness
Should we still be talking about online and offline retail, or about trucks versus boxes versus bikes?
Net dollar churn is a more value-driven way of looking at churn.
Experimentation is widely used at tech startups to make decisions on whether to roll out new product features, UI design changes, marketing campaigns and more, usually with the goal of improving…
The best way to optimise your website is usually the simplest.
Free books, lectures, blogs, papers, and more for a causal inference crash course
Pandas doesn’t handle well Big Data. These two libraries do! Which one is better? Faster?
There’s a reason that online ticket sellers hit you with those extra fees after you’ve picked your seats and are ready to click “buy.” Pure profit. A
How not to fail your online controlled experimentation
Optimizing web marketing strategies through statistical testing
A/B Testing — A complete guide to statistical testing - bjpcjp/AB_Testing
Uplift models seek to predict the incremental value attained in response to a treatment. For example, if we want to know the value of showing an advertisement to someone, typical response models will only tell us that a person is likely to purchase after being given an advertisement, though they may have been likely to purchase already. Uplift models will predict how much more likely they are to purchase after being shown the ad. The most scalable uplift modeling packages to date are theoretically rigorous, but, in practice, they can be prohibitively slow. We have written a Python package, pylift, that implements a transformative method wrapped around scikit-learn to allow for (1) quick implementation of uplift, (2) rigorous uplift evaluation, and (3) an extensible python-based framework for future uplift method implementations.
A heatmap is a graphical representation of data in which data values are represented as colors. That is, it uses color in order to…
The intuitive way of A/B testing. The advantages of the Bayesian approach and how to do it.
You can say goodbye to coding for data wrangling and data cleaning
The Guide to Product Analytics taps dozens of product leaders (from companies like Google, Twitter, and LinkedIn) to break down how PMs can use product analytics to drive product-led growth.
Retail Analytics: Data Science for Retail
.png)
If you make $10 profit each time you sell a product, what cost per conversion should you aim for? Answering this question isn't easy, but it can teach us a lot about how to approach advertising.
PSL Features
Big success. Bigger failure. And lots of lessons. Learn why building a growth team may be a multi-million dollar mistake.
Learn how to interpret what’s happening in your paid search account with your traffic, conversions and sales data.
Every website or PWA you build should automate as much prospecting and selling as possible. The only thing is that visitors enter websites with various mindsets, depending on which part of the buying stage they’re at. This means that you can’t just take every person who enters the site through the same path. You have to design a custom sales funnel (or pathway) for each kind of buyer. In this article, Suzanna Scacca will tell you what you need to keep in mind.
Running an A/B test is easy. Screwing up an A/B test is even easier.
Google Analytics may be the most important application to understand the behavior of your visitors. And whether you’re a beginner or an experienced user, there are many free resources to help. Here is a list of free tutorials for Google Analytics.
There has been a seismic shift in website traffic in the past several years, from desktop to mobile. Google Analytics has rolled out the beta version of cross-device reporting to inform merchants of how their shoppers are interacting via multiple devices.
Increasingly, companies are using experiments to guide them in their decision making—but many are still missing opportunities, or are failing to implement experiments well. When it comes to the rollout of new products, one particularly effective new kind of experiment involves randomizing the introduction of new products across a set of markets. Uber used this strategy before rolling out its Express Pool service, and Airbnb did the same before rollout out a new landing-page design. In both cases, the companies gathered data that allowed them to roll out their products with confidence that they would succeed—as indeed they did. Many companies, even those not in the tech sector, can benefit from this kind of experimentation, especially if they follow a few basic guidelines.
When we think about the data we hold on our services, the first thing that comes to mind is often website analytics. But there are other valuable and occasionally overlooked types of data that can be really useful to user researchers.
How I replaced Google tracking with simple log-based analytics on my personal website.
Google Analytics is a powerful, free web analytics platform. However, it has gaps that are better served by other tools. I'll address those gaps and tools in this post.
Update 2016-10-18: This tutorial has been updated to reflect the latest version of my stack (now with Drip!). I’ve also updated pricing info (it’s technically a $0 stack now) and screenshots. The original outdated article is archived here. “Just tell me what to do so I can stop
“That’s just one person” and “Our real users aren’t like that” are common objections to findings from qualitative usability testing. Address these concerns proactively to ensure your research is effective.
Last week we hosted over 130 experimenters at Optimizely HQ in San Francisco for our first live event of the year. We were lucky enough to be joined by two...
Finding and building the next big idea is the holy grail of any tech company. Unfortunately the statistics are against us: when subjected…
Check out these 3 privacy-focused alternatives to Google Analytics.
Connect with developers sharing the strategies and revenue numbers behind their companies and side projects.
When we need to measure marketing campaigns, most of us have cracked online campaign tracking – we have a cookie
The biggest question in ecommerce A/B testing is not “how.”
A side project that got much bigger than I thought.
Read this guide for an overview of Google Analytics and how you can use all the data to your advantage to boost your SEO and digital marketing.
Sammy Gelfand is the numbers guy behind the Golden State Warriors’ success. Some pretty good players help, too.
Learn how the world's fastest growing companies have hacked their way to success with innovative products, viral promotions and ingenious marketing campaigns. [6500 words]
A/B tests are controlled experiments of two attributes, to measure which one was most popular with users. You can apply A/B testing to just about anything that you can measure. Multivariate testing allows you to measure multiple variables simultaneously.
We will review another fascinating approach that marries heuristic and probabilistic methods. We will link marketing channels with a probability of a customer passing through each step of a Sales Funnel
When deciding whether to track users on the server or on the client, there are many gotchas and factors to consider. Here is a short guide with pros and cons of each.
Data Science, Machine Learning, AI & Analytics
At some point, almost every company faces questions like How good are the customers that we acquire? How do they
Users are rating items on your website. How do you know what the highest-rated items are?