Introduction: The baseline endemicity profile of lymphatic filariasis (LF) is a keybenchmark for planning control programmes, monitoring their impact on transmissionand assessing the feasibility of achieving elimination. Presented in this work is themodelled serological and parasitological prevalence of LF prior to the scale-up of massdrug administration (MDA) in Nigeria using a machine learning based approach.Methods: LF prevalence data generated by the Nigeria Lymphatic Filariasis ControlProgramme during country-wide mapping surveys conducted between 2000 and 2013were used to build the models. The dataset comprised of 1103 community-levelsurveys based on the detection of filarial antigenaemia using rapidimmunochromatographic card tests (ICT) and 184 prevalence surveys testing for thepresence of microfilaria (Mf) in blood. Using a suite of climate and environmentalcontinuous gridded variables and compiled site-level prevalence data, a quantileregression forest (QRF) model was fitted for both antigenaemia and microfilaraemia LFprevalence. Model predictions were projected across a continuous 5 × 5 km griddedmap of Nigeria. The number of individuals potentially infected by LF prior to MDAinterventions was subsequently estimated.Results: Maps presented predict a heterogeneous distribution of LF antigenaemia andmicrofilaraemia in Nigeria. The North-Central, North-West, and South-East regionsdisplayed the highest predicted LF seroprevalence, whereas predicted Mf prevalencewas highest in the southern regions. Overall, 8.7 million and 3.3 million infections werepredicted for ICT and Mf, respectively.Conclusions: QRF is a machine learning-based algorithm capable of handling high-dimensional data and fitting complex relationships between response and predictorvariables. Our models provide a benchmark through which the progress of ongoing LF control efforts can be monitored.