Obesity prevalence among children in the United States has almost doubled in the past three decades. To address the rising rates of obesity, community-level interventions have been implemented. However, it remains unclear whether resources are reaching all communities with need or what factors determine the allocation of scarce resources. Communities most burdened by obesity should be prioritized for intervention. However, due to a lag time in data availability, current obesity estimates needed to identify communities with the greatest needs for intervention are not available. Furthermore, evidence demonstrating the contribution of place-based interventions to changes in population-level rates of childhood obesity has been limited. A database of interventions tackling obesity in Los Angeles County since 2003 was created. Neighborhood-level intervention data was linked with neighborhood-level obesity prevalence and sociodemographic data. Generalized linear models with a Gamma distribution and log link were run to examine the allocation of resources for obesity prevention across communities based on their obesity prevalence and sociodemographic characteristics. Machine learning algorithms were used to build models predicting future prevalence of neighborhood-level obesity rates using existing neighborhood sociodemographic and obesity data. Machine learning algorithms were also applied to build a model to estimate neighborhood-level prevalence of obesity under no intervention, which was used to create a counterfactual comparison group. This model was applied to neighborhoods that received intervention(s) in a given year to estimate what their obesity prevalence would have been under no intervention. We ran fixed-effects models to examine the relationship between various types of obesity-related interventions and change in obesity prevalence. Neighborhoods with more poverty and a higher proportion of Black or Hispanic residents were more likely to receive obesity-related interventions. We also demonstrated that future prevalence of neighborhood-level obesity could be reasonably predicted using the most recent sociodemographic and obesity data available. Finally, we found that neighborhoods that received more obesity-related interventions saw greater declines in obesity prevalence. In particular, neighborhoods that received multicomponent interventions were likelier to see greater declines in obesity prevalence. Macro-level interventions were more effective at reducing neighborhood-level prevalence of obesity than micro-level interventions.