Visible transmission spectroscopy combined with multivariate analysis was used to develop a nondestructive detection system for hatching egg fertility. The transmission spectra (500–750 nm) of 165 light brown-shell broiler hatching eggs were acquired between incubation time 0–144 h at 24 h interval. Several multivariate classification methods, i.e. k-means clustering, linear discriminant analysis (LDA) and support vector machine (SVM) were used to discriminate between fertile and infertile eggs. The LDA and SVM classification models achieved 100% classification accuracy for both fertile and infertile eggs, while the k-means clustering model had a classification accuracy of 96% for fertile eggs and 100% for infertile eggs at 96 h of incubation. These results demonstrate that visible transmission spectroscopy, combined with an appropriate multivariate method, has the potential to use for detection of infertile eggs in commercial hatchery operations.