In lactating sows, high milk production and low voluntary feed intake generally lead to nutrient deficiencies, which in turn may have negative effects on their subsequent reproductive performance and longevity. To accurately handle individual variability, precision feeding systems require to predict nutritional requirements of sows according to their individual milk production. The objective of this study was thus to predict litter weight gain (LWG) from birth to weaning as a proxy variable of milk production. Data were collected on 13,364 lactating sows from 6 farms. Data include information on body weight and parity of sows, litter size and weight at birth, cross-fostering of piglets, lactation duration, litter size and weight at weaning. Five subsets with differences in their attribute’s composition were created (S1, S2, S3, S4, and S5). Subsets were randomly split into learning and testing according to an 80:20 ratio. Six supervised machine learning algorithms, namely Linear Regression, Random Forests, k-Nearest-Neighbor, Neural Network, Gradient Tree Boosting and Voting Regressor were selected and trained. The quality of their predictions was assessed in terms of mean absolute error (MAE), and root mean square error in percentage (RMSEP). Average litter weight gain was 67.7 (±20.42) kg. Gradient Tree Boosting algorithm outperformed all other algorithms, on S1, S2, S3, S4, and S5, regarding to every evaluation criterion. Best results were obtained on the subset S5 containing all attributes (r2=0.80). In details, Gradient Tree Boosting allowed to predict LWG during lactation with a MAE of 8.1 kg, and a RMSEP of 12%. According to this study, Gradient Tree Boosting is a good candidate to accurately predict individual LWG of individual lactating sows and could be embedded in precision feeding decision support system in lactation. This work was supported by the French National Research Agency under the Investments for the Future Program, referred as ANR-16-CONV-0004 (#DigitAg) and was also supported by the European Union’s Horizon 2020 research and innovation program (grant agreement no. 633531).