• Working Paper
    • EN
Share
RC - 2022 - 09 - Working Paper - Slider
1.03.2023 39

Time Series Forecasting with Transformer Models and application for Asset Management

Published 

1 March, 2023

> 10 minutes
1.03.2023
39
Time Series Forecasting with Transformer Models and application for Asset Management
Published 

1 March, 2023

> 10 minutes

Abstract


Since its introduction in 2017 (Vaswani et al., 2017), the Transformer model has excelled in a wide range of tasks involving natural language processing and computer vision.
We investigate the Transformer model to address an important sequence learning problem in finance: time series forecasting. The underlying idea is to use the attention mechanism and the seq2seq architecture in the Transformer model to capture long-range dependencies and interactions across assets and perform multi-step time series forecasting in finance. The first part of this article systematically reviews the Transformer model while highlighting its strengths and limitations. In particular, we focus on the attention mechanism and the seq2seq architecture, which are at the core of the Transformer model. Inspired by the concept of weak learners in ensemble learning, we identify the diversification benefit of generating a collection of low-complexity models with simple structures and fewer features. The second part is dedicated to two financial applications. First, we consider the construction of trend-following strategies. Specifically, we use the encoder part of the Transformer model to construct a binary classification model to predict the sign of an asset’s future returns. The second application is the multi-period portfolio optimization problem, particularly volatility forecasting. In addition, our paper discusses the issues and considerations when using machine learning models in finance.

To find more, download the full paper.


This website is solely for informational purposes.
 
This website does not constitute an offer to sell, a solicitation of an offer to buy, or a recommendation of any security or any other product or service. Any securities, products, or services referenced may not be registered for sale with the relevant authority in your jurisdiction and may not be regulated or supervised by any governmental or similar authority in your jurisdiction.
 
Furthermore, nothing in this website is intended to provide tax, legal, or investment advice and nothing in this website should be construed as a recommendation to buy, sell, or hold any investment or security or to engage in any investment strategy or transaction. There is no guarantee that any targeted performance or forecast will be achieved.

Get in touch with us

Our online help service is available to answer your question.

My personal information

If you have a question about our company or one of our products, please complete the form to get in touch. Please do not mention your account numbers or critical data in this form.

Civility*
CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

(*) Required fields
All our job offers (Permanent and temporary position, Internship, Apprenticeship or VIE) are available on our dedicated website: https://jobs.amundi.com.

Register and apply directly online.

Amundi on Twitter