An accurate estimation of the jacking forces likely to be experienced during microtunnelling is a key design concern for the design of pipe segments, the location of intermediate jacking stations and the efficacy of the pipe jacking project itself. This paper presents a Bayesian updating approach for the prediction of jacking forces during microtunnelling. The proposed framework is applied to two pipe jacking case histories completed in the UK including a 275 m drive in silt and silty sand and a 1237 m drive in mudstone. To benchmark the Bayesian predictions, a 'classical' optimisation technique, namely genetic algorithms, is also implemented. The results show that predictions of pipe jacking forces using the prior best estimate of model input parameters provide a significant over-prediction of the monitored jacking forces for both drives. This highlights the difficulty in capturing the complex geotechnical conditions during tunnelling within prescriptive design approaches and the importance of robust back-analysis techniques. Bayesian updating is also shown to be a very effective option where significant improvements in the mean predictions, and associated variance, of the total jacking force are obtained as more data is acquired from the drive.