How to forecast demand when you don't have a data science team
A practical way to build a first demand forecast with a spreadsheet or a few lines of Python, and how to tell whether it is any better than guessing.
Blogs
Practical writing on tracking, reporting, experiments, prediction, AI and the everyday problems of working with data.
When it makes sense to hire a data analytics consultant (and when it doesn't)
A practical look at when a data analytics consultant earns their fee, when you'd be better off hiring or waiting, and how to judge one before you sign.
Predictive modelling in plain English: what it can and can't do for a business
What predictive models actually do, the handful of business questions they suit, what data they need and why a model is only the middle of the project.
Where AI actually helps an analytics team, and where it doesn't
The jobs where language models and machine learning save an analytics team real time, the ones where they cause trouble, and how to tell the difference.
How to write KPI definitions that end the "whose number is right" meeting
Most reporting arguments are really definition arguments. Here is a simple format for writing KPI definitions that people actually follow, with an example.
Making sense of thousands of customer reviews with topic modelling
How to turn piles of reviews, questions and survey comments into themes you can count, with a short Python example and the mistakes that waste the most time.
A churn score is useless until someone knows what to do with it
How to build a churn or cancellation model that gets used: define the outcome, avoid leakage, test on a later period and agree the action first.
Power BI, Tableau or Looker: how to pick one without a six-month debate
A plain comparison of Power BI, Tableau and Looker for growing teams, with the questions that actually decide the choice and the ones that don't.
Using ChatGPT-style tools with company data: a sensible policy for small teams
What to keep out of public AI tools, what your options are for safer use, and a short set of working rules a small team can adopt this week.
Why most first AI projects stall, and how to pick one that doesn't
The common reasons early AI projects fizzle after a good demo, and a short checklist for choosing a first project that actually reaches daily use.
A practical checklist for auditing your Mixpanel events
How to audit the events in Mixpanel or any product analytics tool. A step-by-step checklist covering naming, properties, identity, duplicates and gaps.
Ranking and recommending products: simple models that beat "most popular"
Practical ways to rank and recommend products, from popularity baselines and co-purchase counts to predicted click-through, each tested against what you do now.
How I turn messy JSON into a star schema people can actually query
A practical walk-through of turning nested JSON from an app backend into a tidy star schema in a warehouse, with a worked BigQuery example.
Five A/B testing mistakes I keep seeing, and how small teams avoid them
The most common A/B testing mistakes, from stopping early to testing too many things, and simple ways for small teams to run honest experiments.
Marketing mix modelling or attribution: which one do you actually need?
Attribution follows individual customers. Marketing mix modelling works from totals. Here is how they differ, what each needs, and how to choose.
Customer segmentation for online stores, starting with RFM
A simple, practical way to segment customers using recency, frequency and monetary value, with SQL you can run and ideas for what to do with the groups.
Automating a weekly report: where the hours really go
How to automate a manual weekly or monthly report with Python and SQL, where the real time is spent, and the traps that make automation fail quietly.
Data analytics for small and mid-sized businesses in India: where to start
A practical starting point for Indian small and mid-sized businesses that want to use data better, from first questions to free tools and common mistakes.
Marketing attribution 101: how to tell which campaigns actually worked
A beginner's guide to marketing attribution. How the main models work, what each one hides, and a sensible way to start measuring campaign success.
Data ethics for ordinary businesses: a practical guide
Data ethics isn't just for tech giants. A practical guide to collecting less, being clear with customers, avoiding biased models and keeping data safe.
How data helps marketing teams look like heroes, not villains
Marketing often gets blamed when the numbers disappoint. Here is how good measurement turns reports into leverage and builds trust with finance and leadership.
A quick guide to data analytics for busy businesses
Data analytics explained without jargon. The four kinds of analysis, what you actually need to get started, and the mistakes that waste time and money.
Customer 360 explained: what it is and how to build one without a giant platform
What a Customer 360 view is, why teams want one, and a step-by-step way to build it in your own warehouse, including the tricky matching problem.
Have a problem like one of these?
Tell us about it. A short conversation often saves weeks of guessing.