This study assesses whether a hybrid prediction–optimisation workflow can be used as an exploratory exercise for Brazilian federal budget allocation under severe data constraints. Using executed expenditure by budgetary function (2000–2023; N = 24), a multi-output XGBoost model is estimated to link spending profiles to GDP growth, inflation, and the Gini index; Bayesian optimisation (Tree-structured Parzen Estimator/Optuna) is then applied to search, within explicit bounds and penalties, for allocation vectors that maximise a stated objective function favouring higher growth and lower inflation and inequality. To mitigate data scarcity, the short series is augmented with 1048 synthetic observations generated through controlled noise injection, bootstrapped resampling and variational autoencoder reconstruction. Under randomised K-fold cross-validation on the augmented dataset, the model achieves mean R2 = 0.97 and mean MSE = 0.04, while diagnostics indicate larger errors at extreme values and a persistent training–validation gap. A secondary robustness check uses an anti-leakage design by applying cross-validation to the 24 real observations and generating synthetic data only within each training fold. This yields markedly weaker generalisation for GDP growth and inflation (overall mean MSE = 1.03; overall mean R2 = −0.45), with positive performance remaining only for the Gini index (R2 = 0.60). Under these conditions, the optimisation step identifies a scenario that satisfies the objective function on standardised outputs (GDP growth = 1.15; inflation = −0.04; Gini = −0.17). The results support the use of the workflow to compare scenarios under explicit assumptions, rather than to produce prescriptive budget guidance.

This article presents evidence that high-ranking public officials in the Ministry of Strategy and Finance in South Korea affect local budget allocation. Applying a regression model on a uniquely constructed panel dataset, I found that the growth rate of the per-capita National Subsidy, which is a subcomponent of the national budget susceptible to discretionary behaviors, increases approximately 7 percent in the hometowns of high-ranking bureaucrats. To validate these findings and address causality, I conducted a battery of auxiliary robustness checks, which yielded confirmatory results. This study also found that enhancing transparency in the budget allocation system can alleviate concerns about bureaucratic hometown favoritism, providing suggestive evidence of bureaucrats’ rent-seeking behaviors without government transparency.

We investigate allocation of funds by citizens across management options addressing impairments to coastal water quality. We study systematic variation in citizen allocation of funds to adaptive versus preventative strategies including the impact of referundum choices and test whether allocations will be impacted by cuing in the design of the referendum. Two key policy insights from our results: citizens who vote no on a water quality referendum have different preferences over allocating funds and providing cues to voters influenced allocation behavior. These results can assist decision makers in thinking about language used to communicate coastal water quality issues, particularly budget referenda.

This research develops a multiregional optimal control model that incorporates regional allocation of a public budget for controlling invasive plants when regionally differential recreation demand functions and species control costs are present. Our equimarginal condition for optimal budget allocation equates the relative marginal economic benefits per dollar spent across regions. The model was applied to Florida Public Conservation Land regions, and results indicate that the magnitude of an annual management budget affects its distribution among species management regions, but the size of the intrinsic growth rate does not affect the pattern of budget allocation among regions.