One of the key issues of wireless communication networks is the spectrum crisis, and studies noted that static licensed bands are in the under-utilization stage. Recently Cognitive Radio Network facilitates a solution to minimize the spectrum crisis in which unlicensed users can utilize the licensed spectrum without transmission interference. To achieve this task we used Machine Learning techniques for analyzing spectrum occupancy which is an efficient method to analyze spectrum occupancy and provides high accuracy. Supervised machine learning algorithms namely Logistic regression, K nearest neighbor, and Naive Bayes are used to classify a given frequency band. In this paper we collect spectrum samples of GSM 900, 1800, and 2100 bands using Rohde & Schwarz FSH6 Handheld Spectrum Analyzer for developing a dataset, using that dataset we trained the classifiers and analyze their classification performance accuracy. Results have shown the best performance on the validation and testing partition for various Unweighted Average Recall (UAR) of each classifier. Here the Logistic Regression classifier learns the best representation from their feature vector. This research is helpful to measure the spectrum occupancy of different static allocated licensed bands for 24/7. This will give better ideas about spectrum utilization, future spectrum allocation and comfort to serve more users in the limited spectrum. The occupancy measurements of current allocated spectrums can not only provide a convincing basis for making future spectrum allocation policies, but also provide technical support for the development of new communication technologies.