Melbourne-based analytics, data products and applied AI grounded in 10+ years of commercial experience.
Data Quality.
All insightsMost of the data problems I've run into weren't nulls or duplicates. They were a metric that meant something different to the person reading it, a comparison that quietly stopped being like-for-like when a boundary or product hierarchy changed, or a detailed model nobody had added back up to a total they already knew. Clean data can still give you the wrong answer, so I treat checking it as part of the analysis rather than a chore before it starts.
Our Shopping List Thinks We Buy Toilet Paper Every Five DaysThree months of grocery data from Pantrify looked like a purchase history, until it turned out to be a record of checkbox taps.
Read article ⟶
The Bug That Made Australia Double in Size in My DatasetA granular projection produced an estimate of 52 million Australians. Rolling the result back up to the national total exposed the problem.
Read article ⟶
The Fastest Data Check Is Often a Definition CheckBefore checking nulls and duplicates, make sure the metric, population, and time period mean what you think they mean.
Read article ⟶
What I Look for Before Trusting a DatasetBefore I build a dashboard, automate a report, or start analysing trends, I try to answer one question first: can this dataset actually be trusted? Here's what I check before relying on data for decisions.
Read article ⟶