{ "background": "The modernisation of the construction and mining sectors in West Africa relies on the effective adoption of advanced industrial machinery. However, robust, data-driven methods for quantifying and analysing adoption rates of such fleets are lacking, hindering strategic investment and maintenance planning.", "purpose and objectives": "This study develops and validates a novel Bayesian hierarchical model to estimate the adoption rates of industrial machinery fleets. The objective is to provide a probabilistic framework that accounts for regional heterogeneity and sparse data, offering a superior alternative to traditional aggregate measures.", "methodology": "A cross-sectional survey of machinery operators and site managers was conducted across multiple regions. The core model is a Bayesian hierarchical logistic regression: $\\text{logit}(p{ij}) = \\alpha + \\beta X{ij} + uj$, where $p{ij}$ is the adoption probability for machine $i$ in region $j$, $X{ij}$ are covariates, and $uj \\sim N(0, \\sigma^2_u)$ are region-specific random effects. Inference uses Markov Chain Monte Carlo sampling.", "findings": "The model estimates revealed significant regional variation, with posterior credible intervals for regional adoption probabilities excluding zero. A key concrete result is that the adoption rate for telematics-equipped machinery in the most advanced region had a posterior median of 0.42 (95% Credible Interval: 0.35, 0.49), substantially higher than the national aggregate estimate of 0.31.", "conclusion": "The Bayesian hierarchical model successfully quantified regional disparities in adoption rates that are masked by national averages. This confirms the critical importance of modelling geographical heterogeneity for accurate fleet assessment.", "recommendations": "Policymakers and fleet managers should utilise hierarchical modelling approaches for regional diagnostics. Future infrastructure development plans must account for the identified geographical disparities to ensure equitable technological diffusion.", "key words": "Bayesian inference, hierarchical modelling, technology adoption, industrial machinery, fleet management, Senegal", "contribution statement":