Abstract
This paper focuses on revealing the superior predictive power of Data mining & Machine learning approaches – compared to manually configured red-flag approaches – in targeting businesses for inspections and in increasing labour inspection’s efficiency in uncovering undeclared work. Unlike manually set red-flag methods, DM&ML tools increase the predictive accuracy by, first, automatically considering variables that traditional paradigms will omit about who, how and why one engages in undeclared work or other labour law violations; and second, by identifying changes in behavioural patterns significantly faster than experts or practitioners.