ABSTRACT
Alternative data (together with machine learning) is the topic du jour for many quants and data scientists. These quantitative professionals want to get their hands on some new datasets and try a new machine learning technique on the data. In this chapter, we reflect on this process. We do not focus on the exact approach to take, nor do we analyse a particular dataset. Instead, we hope to give some guidance around not only building models with alternative data but the work that has to go in to changing these models from a prototype into a production ready system which can be run day-to-day.
