T he world of finance is inundated with data. Stock quotes, financial statements, news stories, social media posts, credit ratings, sentiment, model signals, transcripts and economic reports are but few of the sources contributing to the widening sea of information that financial professionals attempt to interpret daily. Fortunately, technology has taken on more of the heavy lifting with advanced tools such as artificial intelligence (AI) and machine learning (ML).
Nonetheless, even with these solutions, an analyst still has his or her work cut out. A helpful analogy is the process of painting the inside of a home. Most of the painter’s time is spent in the prep work before rolling on a fresh coat of paint—prep work that includes spackling holes, sanding imperfections, caulking settlement gaps, moving furniture, laying protective material on the ground, choosing a paint color, and “cutting” around corners and trim. Similarly, a significant amount of an analyst’s time is spent on collecting, organizing, and cleaning data before processing it through a model. Thus, analysts need to have a thorough understanding of the various data types and how to appropriately process them for analysis.
Fortunately for us CFA charterholders, the CFA Institute has assembled a comprehensive online learning module called Organizing, Visualizing, and Describing Data, which is based on the identically titled 2021 Level I Refresher Reading that is also available as a free PDF download (on a side note, the 2021 curriculum readings are only available to CFA Institute charterholder members, as current exam candidates will still test off of the 2020 curriculum during the 2021 exam cycle). This course provides the foundational concepts for data analysis and serves as an important pre-requisite for more advanced analysis techniques. The material spans learning the different data classifications (numerical, ordinal, nominal, categorial, etc.), identifying and constructing the different visualization types (scatter plots, box plots, frequency distributions, etc.), understanding and calculating the measures of center and dispersion, and identifying the shape of data distributions with skewness and kurtosis. In addition, at some point in the near future, CFA Institute will also include sample Python code that was used to produce some of the examples in the online learning module (the code will be added to Lesson 7 of the module and will be based in Jupyter notebook).
By the way, the online learning system is a relatively new format that CFA Institute is using to deploy professional learning content, and it is fairly similar to the modernized learning management system (LMS) for CFA exam candidates. Course participants can track their progress, set their own completion deadline, review key terms, check their knowledge with practice questions, search through readings, and even “chill out” or take a break from studies and watch random humorous GIF animations and videos—unfortunately this portion does not count towards your PL credit. We will cover more courses available in this online learning system in future posts.
Last but not least, members can rack up 17.5 PL credit hours with this course (or 3.75 PL hours for those who want to simply read the Refresher Reading). To learn more and enroll in the course, please visit the link below.
Image by Gerd Altmann from Pixabay