Forecasting the OMXS30 - a comparison between ARIMA and LSTM
Machine learning is a rapidly growing field with more and more applications being proposed every year, including but not limited to the financial sector. In this thesis, historical adjusted closing prices from the OMXS30 index are used to forecast the corresponding future values using two different...
Main Authors: | , |
---|---|
Format: | Others |
Language: | English |
Published: |
Uppsala universitet, Statistiska institutionen
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-413793 |
id |
ndltd-UPSALLA1-oai-DiVA.org-uu-413793 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-uu-4137932020-06-23T03:32:30ZForecasting the OMXS30 - a comparison between ARIMA and LSTMengAndréasson, DavidMortensen Blomquist, JesperUppsala universitet, Statistiska institutionenUppsala universitet, Statistiska institutionen2020machine learningdeep learningneural networksRNNtime seriesstock marketindexProbability Theory and StatisticsSannolikhetsteori och statistikMachine learning is a rapidly growing field with more and more applications being proposed every year, including but not limited to the financial sector. In this thesis, historical adjusted closing prices from the OMXS30 index are used to forecast the corresponding future values using two different approaches; one using an ARIMA model and the other using an LSTM neural network. The forecasts are made on three different time intervals: 90, 30 and 7 days ahead. The results showed that the LSTM model performs slightly better when forecasting 90 and 30 days ahead, whereas the ARIMA model has comparable accuracy on the seven day forecast. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-413793application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
machine learning deep learning neural networks RNN time series stock market index Probability Theory and Statistics Sannolikhetsteori och statistik |
spellingShingle |
machine learning deep learning neural networks RNN time series stock market index Probability Theory and Statistics Sannolikhetsteori och statistik Andréasson, David Mortensen Blomquist, Jesper Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
description |
Machine learning is a rapidly growing field with more and more applications being proposed every year, including but not limited to the financial sector. In this thesis, historical adjusted closing prices from the OMXS30 index are used to forecast the corresponding future values using two different approaches; one using an ARIMA model and the other using an LSTM neural network. The forecasts are made on three different time intervals: 90, 30 and 7 days ahead. The results showed that the LSTM model performs slightly better when forecasting 90 and 30 days ahead, whereas the ARIMA model has comparable accuracy on the seven day forecast. |
author |
Andréasson, David Mortensen Blomquist, Jesper |
author_facet |
Andréasson, David Mortensen Blomquist, Jesper |
author_sort |
Andréasson, David |
title |
Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
title_short |
Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
title_full |
Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
title_fullStr |
Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
title_full_unstemmed |
Forecasting the OMXS30 - a comparison between ARIMA and LSTM |
title_sort |
forecasting the omxs30 - a comparison between arima and lstm |
publisher |
Uppsala universitet, Statistiska institutionen |
publishDate |
2020 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-413793 |
work_keys_str_mv |
AT andreassondavid forecastingtheomxs30acomparisonbetweenarimaandlstm AT mortensenblomquistjesper forecastingtheomxs30acomparisonbetweenarimaandlstm |
_version_ |
1719323063528456192 |