Converts real HKDSE maths papers into structured item banks, then generates topic- and difficulty-profiled mock papers in LaTeX — with distractor-to-error mapping that turns wrong MC answers into revision signals.
Solo buildA pipeline that converts real HKDSE maths papers into a structured item bank — LaTeX normalisation, question segmentation, mark verification — then generates mock papers profiled by topic and difficulty.
The piece I'm proudest of is distractor-to-error mapping: each wrong multiple-choice option is tagged with the misconception it reveals, so a mock's results read as a diagnosis rather than a score.
Built for my own tutoring work; every paper that enters the bank is spot-checked by hand before it's trusted.
PythonLaTeXItem bankingStatistics