Back to Sources
(2025) Working paper / technical note
Machine learning regionalisation of input data for microsimulation models
CeMPA, University of Essex
Ref: SRC-001-GBR-004
Accessed: 3/19/2026
Summary
Primary 40-page paper describing the hybrid GBM/IPF methodology. Details the ML technique (GBM propensity score estimation), data inputs (FRS + Experian), validation against ASHE and SPI benchmarks, and comparison with Random Forest. Co-authored by Essex County Council staff.
View Harvard reference
Frimpong, R. & Richiardi, M. (2025) 'Machine learning regionalisation of input data for microsimulation models: An application of a hybrid GBM / IPF method to build a tax-benefit model for the Essex region in the UK', CeMPA Working Paper 9/25, University of Essex.
Attached File
SRC-001-GBR-004_Machine_learning_regionalisation_of_input_data_for_microsimulation_models.pdf 1.4 MB
Download