Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 3

Predicting Forex Futures Rates

Group 2

[Author name] 8/20/22 Options Futures and Derivatives


Introduction
To predict upcoming time points, almost all industries employ time series data. Future
forecasting can help analysts and management make more thoughtful decisions to maximise
profits and reduce risks. We shall show that it is possible to predict exchange rates.
It offers a fundamental summary of market information. Exchange rates are influenced by
several variables, including supply and demand, governmental policies, national growth
rates, and others.
There have been numerous technical developments that can foresee future time points fast,
effectively, and correctly. Statistical and machine learning (ML) model introduction in
Python is one of them. The ARIMA model will be used to predict exchange rates.

Libraries
We will use Panda and Numpy from python to analyse the data. These will be used to load
data, view the current records, and basic statistical records.

Expected Result
We expect to analyse the dataset and forecast the price of the futures using Autoregressive
integrated moving average (ARIMA) of the derivate forex rate. This will be used to analyse
the future trade-offs and analyse the datasets accordingly.

ARIMA has 3 models, which are

P — Auto regressive feature of the model

D — Differencing order

Q — Moving average feature of the model

The model will in most cases use 70-80% of the data to train itself and remaining 20-30% of

data to test the initial regression output. We will use the mean squared method to find the

deviation if any.

You might also like