This graduate thesis elaborates the field of machine learning with the focus on the recommender systems. It studies and describes types of machine learning, popular machine learning algorithms, characteristics of Python open-source libraries for machine learning and application of machine learning in many fields. Also, it describes the recommender systems, i.e. phases of recommendation process, similarity measures, types of recommender systems, evaluation of recommender systems and it presents an implementation of the recommender system. Today, there is a large amount of data that is collected, processed, stored and used. The computer learns using the available data and it is important to choose the data features and appropriate model well. Machine learning algorithms are trained using large amount of data and thus learn and gain knowledge from data. The types of machine learning are supervised learning, unsupervised learning and reinforcement learning. The machine learning has wide application in many areas. Recommender systems are used to suggest relevant items to users. The types of recommender systems are content-based recommender system, collaborative recommender system and hybrid recommender system. The advantages of recommender systems are business improvement, increased user satisfaction and fidelity, enhanced sales and sales of more diverse items with overall better understanding of user preferences. The practical part of this thesis includes implementation of content-based movie recommender system. It uses Python programming language and Python open-source libraries including Pandas, Scikit-learn, Seaborn and Matplotlib.