Data Science & Machine Learning

The course covers the process of data science, i.e. a multidisciplinary approach to find, extract and discover patterns in data through a fusion of analytical methods, domain expertise and technology. In this context, the fields of data mining, forecasting, machine learning, predictive analytics, statistics and text analytics are covered. Within the framework of the iterative data science process, business understanding is treated with problem identification for the specification of key variables that are to function as model goals and identification of relevant data sources. It also includes the formulation of questions that define business goals and that can be quantified by computer science technicians. To control data quality, the acquisition of raw data, data processing (ETL), examination of data and modeling are included. To facilitate the development of model(s) and to find the model that best answers the initial questions, so called feature engineering is used, when raw data is extracted and distinctive features are created. Finally, the evaluation of modeling and analysis, presentation of results and commissioning are discussed.