fruhj/udacity-machine-learning-nanodegree

Capstone Project - Predicting weekly returns in DXY Index

Udacity-Machine-Learning-Nanodegree

Capstone Project - Predicting weekly returns in DXY Index.

Project Title The study of this project is the foreign currency (FX) market and specifically the US Dollar Index. The US Dollar Index is a futures contract on what is considered to be the world’s most widely traded currency index for the international value of the US Dollar (ICE US Dollar Index). Note that financial media often refers to this index as the DXY Index (pronounced “Dixie”). Non-US currencies that are part of the DXY are as follows:

Currency DXY Index Euro 57.60% Japanese Yen 13.6% British Pound 11.9% Canadian Dollar 9.1% Swedish Krona 4.2% Swiss Franc 3.6% *see ICE FX Indexes Methodology for details

A research report produced by my employer, Bank of America, examines the FX markets from a quantitative perspective (see ‘BAML FX Quant Primer – FORTE & OCTAVE’). This report was the catalyst for this project. As stated in the report ‘Cross-asset and macroeconomic factors are essential drivers of FX movements…We use cross-asset drivers to produce an optimal currency portfolio. Inputs in our factor model include carry, interest rate trends, rates momentum, and equity momentum’ (see page 2). In this project we will use data for short term US interest rates, short term European interest rates, US equity markets (i.e. S&P 500 Index), and US-Europe interest rate differentials (e.g. the difference between the US and German 3 month interest rates).

Getting Started These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites Matplotlib Numpy Pandas Seaborn SKlearn

License This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments Inspiration - BAML Research report 'FX Quant Primer'