The amount of weight loss in obese children during lifestyle intervention differs strongly between individuals. The metabolic processes underlying this variability are largely unknown. We hypothesize that metabolomics analyses of serum samples might help to identify metabolic predictors of weight loss. In this study, we investigated 80 obese children aged 6-15 years having completed the one-year lifestyle intervention program 'Obeldicks', 40 that achieved a substantial reduction of their body mass index standard deviation score (BMI-SDS) during this intervention (defined as BMI-SDS reduction ≥ 0.5), and 40 that did not improve their overweight status (BMI-SDS reduction < 0.1). Anthropometric and clinical parameters were measured and baseline fasting serum samples of all children were analyzed with a mass spectrometry-based metabolomics approach targeting 163 metabolites. Both univariate regression models and a multivariate least absolute shrinkage and selection operator (LASSO) approach identified lower serum concentrations of long-chain unsaturated phosphatidylcholines as well as smaller waist circumference as significant predictors of BMI-SDS reduction during intervention (p-values univariate models: 5.3E-03 to 1.0E-04). A permutation test showed that the LASSO model explained a significant part of BMI-SDS change (p = 4.6E-03). Our results suggest a role of phosphatidylcholine metabolism and abdominal obesity in body weight regulation. These findings might lead to a better understanding of the mechanisms behind the large inter-individual variation in response to lifestyle interventions, which is a prerequisite for the development of individualized intervention programs.