Changes in the quality of eggs during storage relate to their shelf life and economic value. Factors such as temperature, relative humidity, the operation of cleaning, and microorganisms have been shown to play a role in the storage quality of eggs. This study thus aimed at investigating the effect of hen age on the storage quality of egg, and predicting egg shelf life using back propagation artificial neural network (BP-ANN) based models. Eggs laid by Jingfen No.1 (27 and 58 weeks of age) and Jingfen No.6 (26 and 57 weeks of age) hens were stored under ambient conditions and evaluated by physicochemical properties. It was found that the shelf life of the lower age group was significantly longer than that of the higher age group. A novel hybrid model combining BP-ANN, cuckoo search and adaptive boosting (CS-BP-AdaBoost) was proposed for predicting the remaining egg shelf life, with the input being Haugh unit, yolk index, air cell depth, albumen pH, hen age, and breed. The tuning process of hyperparameters such as learning rate, training function, and transfer function was presented in detail. Results show that CS-BP-AdaBoost had satisfactory performance on the test set with root mean square error (RMSE) and coefficient of determination (R2) of 0.68 and 0.97, respectively. And it outperformed BP-ANN by reducing RMSE by 0.39 and improving R2 by 0.05. The model used solved the problem that the traditional BP-ANN tends to fall into local minima. The removal of hen age from the input parameters caused a decrease in prediction accuracy (R2 = 0.95, RMSE = 1.00), suggesting an important role of hen age in shelf life prediction. This study demonstrates the great potential of applying combinatorial modeling approaches to predict egg shelf life and the crucial impact of hen age on egg shelf life prediction.