Comparison of the Quality of Predictions of Artificial Neural Networks with Traditional Forecasting Methods Based on the USD/JPY Rate

Student: Matyushin Daniil

Faculty: St.Petersburg School of Economics and Management

Educational Programme: Economics (Bachelor)

Year of Graduation: 2020

In this work, an analysis of the foreign exchange market and a comparison of traditional forecasting methods with artificial neural networks was carried out. The work was performed to demonstrate the advantage of artificial neural networks in forecasting the exchange rate using the USD / JPY currency pair as an example. Comparison of forecast qualities was carried out by comparing the average absolute forecast errors on the horizon of 120 and 60 days using the Jupiter Notebook program. The results partially met the initial expectations; on the horizon of 120 days, the neural network showed the best results, but on the horizon of 60 days it was not so effective. This work will be useful as a basis for developing forecasting models by financial institutions and private investors.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses