Using state-level data on India's MidDay Meal program (school lunch program for children) we scrutinize if funds disbursed and food-grains supplied for the purpose can actually serve as good determinants of number of children covered (fed) by the scheme (our dependent variable). Our standard regression studies find that the effect of food-grain supplied has statistically significant effect on the dependent variable while the marginal effects of funds/money disbursed is not statistically significant. Using LASSO based Machine Learning techniques and after controlling for several correlated variables and state level factors we find that both policy variables-funds and food-grains however act as good out-of-sample predictors of number of children being covered. Evaluation of out-of-sample prediction performance of regression models and covariates is a very important but mostly an uncharted territory in development economics. Note that funds are used partly to provide fixed costs of the food service provided and therefore it is not surprising that the coefficient estimate of this covariate (i.e., its marginal effect on dependent variable) does not appear to be statistically significant; but it can still act as a good overall predictor for our dependent variable.