I discovered a crude but functional way of doing this (detailed in this post), but then discovered an extremely convenient python library that does the same thing much more efficiently, with a direct pandas-datareader interface. Although they’ve deprecated their official API, they still have the same data on their website, meaning that it can be scraped if you can be bothered. My main data source has been Yahoo Finance. ![]() I’ve worked broadly with two datasets in particular: historical financial statistics (e.g P/E ratio, price/book) make up the features that my algorithms learn from, but the actual backbone of any strategy is historical price data. As part of this hobby, I’ve spent many more hours parsing and processing data than I have actually applying machine learning. ![]() One of my interests is exploring the applications of machine learning to financial markets.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |