Python for finance: mastering data-driven finance, 2nd ed.

Abstract

These days, Python is undoubtedly one of the major strategic technology platforms in the financial industry. When I started writing the first edition of this book in 2013, I still had many conversations and presentations in which I argued relentlessly for Python’s competitive advantages in finance over other languages and platforms. Toward the end of 2018, this is not a question anymore: financial institutions around the world now simply try to make the best use of Python and its powerful ecosystem of data analysis, visualization, and machine learning packages. Beyond the realm of finance, Python is also often the language of choice in introductory programming courses, such as in computer science programs. Beyond its readable syntax and multiparadigm approach, a major reason for this is that Python has also become a first class citizen in the areas of artificial intelligence (AI), machine learning (ML), and deep learning (DL). Many of the most popular packages and libraries in these areas are either written directly in Python (such as scikit-learn for ML) or have Python wrappers available (such as TensorFlow for DL). Finance itself is entering a new era, and two major forces are driving this evolution. The first is the programmatic access to basically all the financial data available — in general, this happens in real time and is what leads to data-driven finance. Decades ago, most trading or investment decisions were driven by what traders and portfolio managers could read in the newspaper or learn through personal conversations. Then came terminals that brought financial data in real time to the traders’ and portfolio managers’ desks via computers and electronic communication. Today, individuals (or teams) can no longer keep up with the vast amounts of financial data generated in even a single minute. Only machines, with their ever-increasing processing speeds and computational power, can keep up with the volume and velocity of financial data. This means, among other things, that most of today’s global equities trading volume is driven by algorithms and computers rather than by human traders.