HbA1c is a primary marker of long-term average blood glucose, which is an essential measure of successful control in type 1 diabetes. Previous studies have shown that HbA1c estimates can be obtained from 5- 12 weeks of daily blood glucose measurements. However, these methods suffer from accuracy limitations when applied to incomplete data with missing periods of measurements. The aim of this work is to overcome these limitations improving the accuracy and robustness of HbA1c prediction from time series of blood glucose. A novel data-driven HbA1c prediction model based on deep learning and convolutional neural networks is presented. The model focuses on the extraction of behavioral patterns from sequences of self-monitored blood glucose readings on various temporal scales. Assuming that subjects who share behavioral patterns have also similar capabilities for diabetes control and resulting HbA1c, it becomes possible to infer the HbA1c of subjects with incomplete data from multiple observations of similar behaviors. Trained and validated on a dataset, containing 1543 real world observation epochs from 759 subjects, the model has achieved the mean absolute error of 4.80±0.62 mmol/mol, median absolute error of 3.81 ±0.58 mmol/mol and [Formula: see text] of 0.71 ±0.09 on average during the 10 fold cross validation. Automatic behavioral characterization via extraction of sequential features by the proposed convolutional neural network structure has significantly improved the accuracy of HbA1c prediction compared to the existing methods.