Learn the work behind Data, AI & Forward Deployed Engineering
Practical explanations, career decisions and reproducible workflows. Read the reasoning, inspect the evidence and follow the next skill into a real programme.
INNER JOIN versus LEFT JOIN with unmatched customers
An INNER JOIN returns matching combinations from both inputs. A LEFT JOIN also preserves rows from its left input when no right-side match exists, filling the missing right-side values with NULL.
Inspect a model failure without overstating saliency maps
A saliency map highlights pixels whose small local changes affect a model output. It can help inspect a failure, but it does not prove which pixels caused the real-world outcome, what the model “understands,” or whether
Integrate a legacy system through a typed adapter
Legacy integration becomes fragile when old field names and encodings spread through business logic. A typed adapter confines that instability. It translates the source contract into a domain contract, rejects ambiguous
Intermittent demand: why ordinary averages disappoint
Intermittent demand contains many zero periods separated by irregular nonzero orders. A constant mean can achieve a modest average error by predicting a small positive value every period, yet it predicts neither when dem
Inventory ageing: identify slow stock without misleading averages
An average inventory age can hide a small quantity of expensive old stock. Calculate age at the remaining-lot level and report both units and value in age bands. The right priority may depend more on capital tied up, exp
Isolation forests with an analyst-review budget
An anomaly model produces a continuous ranking. Operations need a cutoff, often defined by how many cases analysts can review. A contamination parameter or zero score threshold should not silently become the business pol
JSON schema validation at an API boundary
JSON syntax only proves that text can be parsed. The application still needs a contract for fields, types, values and additional properties.
K-means: choose features before choosing the number of clusters
K-means minimizes squared Euclidean distance to centroids. Features and units therefore define what “close” means before the algorithm ever considers the number of clusters. Searching k on a weak representation only opti
K-nearest neighbours: why scaling changes the prediction
K-nearest neighbours predicts from nearby training observations, so the meaning of “nearby” is part of the model. Changing one feature's units can change distances, selected neighbours and the predicted class even when t
Keep secrets out of tool descriptions and logs
Tool descriptions may be sent to models and cached in traces. Logs can reach broad observability systems. Neither should contain credentials.
Know when a spreadsheet formula is better than an AI agent
A spreadsheet formula is often the better fit when the input table is manageable, the calculation rule is fixed and the user needs a transparent result inside an existing workbook. An AI agent becomes relevant when the w
LAG and LEAD for repeat-purchase intervals
LAG retrieves a value from an earlier row in a window's ordering; LEAD retrieves one from a later row. Partitioning by customer and ordering by purchase time lets you compare each purchase with the previous or next obser
Not sure which programme fits?
Tell us your background and we will map it to the right entry point — including saying so when a cheaper programme is the better fit. A counsellor replies within one working day.