Gait refers to the walking pattern of an individual and it varies from person to person. Consequently, it can be considered to be a biometric feature, similar to the face, iris, or fingerprints, and can easily be used for human identification purposes. Person identification using gait analysis has direct applications in user authentication, visual surveillance and monitoring, and access control—to name a few. Naturally, gait analysis has attracted many researchers both from academia and industry over the past few decades. Within a small population, the accuracy of person identification could be very high; however, with the growing number of people in a given gait database, identifying a person only from gait becomes a daunting task. Hence, the focus of researchers in this field has exhibited a paradigm shift to a broader problem of sex and age prediction using different biometric parameters—with gait analysis obviously being one of them. Recent works on sex and age prediction using gait pattern obtained from the inertial sensors lacks an analysis of the features being used. In this paper, we propose a number of features inherent to gait data and analyze key features from the time–series data of accelerometer and gyroscopes for the automatic recognition of sex and the prediction of age. We have trained various traditional machine learning models and achieved the highest accuracy of 94% in sex prediction and an $R^2$ score of 0.83 in age estimation.