Data science applications to investment management: leveraging in alternative data sets and unconventional tetchniques to enhance portfolio performance.

Ayala González, Jonathan

Data science applications to investment management: leveraging in alternative data sets and unconventional tetchniques to enhance portfolio performance.

License

Citation

Ayala González, J. Data science applications to investment management: leveraging in alternative data sets and unconventional tetchniques to enhance portfolio performance.. 2020. handle: http://hdl.handle.net/10230/45818

This citation was generated automatically.

Abstract

“On the other hand, investing is a unique kind of casino—one where you cannot lose in the end, so long as you play only by the rules that put the odds squarely in your favour.” (Benjamin Graham - The Intelligent Investor, 1949). This paper provides a theoretical and practical approach to the uses of data science as a mechanism to support investment decisions. Although data science applications in investment management are quite varied and numerous, this paper focuses on a data typology currently being widely used by large investment institutions worldwide: The Alternative Data Sets. Concretely, the focus is put on the uses of consumption data and 10-K filings as valuable sources of information to support investment decisions. Overall, results show that, despite data science and algorithm-based tools are essential to process and understand underlying business information, these techniques are not by themselves sufficient to develop a consistent investment strategy but, instead, can be employed as very useful systems to boost the understanding of the business that underlays every stock in the market.